Search

The controversial account of Jesus in Josephus’s Jewish Antiquities 18.63–64, known as the Testimonium Flavianum, has puzzling similarities to Luke 24.18–24, a portion of the Emmaus narrative. This article proposes an explanation based on established research into Josephus’s methods of composition. Through a phrase-by-phrase study, this article finds that the Testimonium can be derived from the Emmaus narrative using transformations Josephus is demonstrated to have employed in paraphrasing known sources for the Antiquities. Precedents are identified in word adoption/substitution and content modification. Consequently, I submit that the Testimonium is Josephus’s paraphrase of a Christian source. This result also resolves the difficulties that have raised doubts about the Testimonium’s authenticity, with implications for the understanding of the historical Jesus.

In recent years, with the development of the social Internet of Things (IoT), all kinds of data accumulated on the network. These data, which contain a lot of social information and opinions. However, these data are rarely fully analyzed, which is a major obstacle to the intelligent development of the social IoT. In this paper, we propose a sentence similarity analysis model to analyze the similarity in people’s opinions on the hot topics in social media and news pages. Most of these data are unstructured or semi-structured sentences, so the accuracy of sentence similarity analysis largely determines the model’s performance. For the purpose of improving accuracy, we propose a novel method of sentence similarity computation to extract the syntactic and semantic information of the semi-structured and unstructured sentences. We mainly consider the subjects, predicates and objects of sentence pairs, and use Stanford Parser to classify the dependency relation triples to calculate the syntactic and semantic similarity between two sentences. Finally, we verify the performance of the model with the Microsoft Research Paraphrase Corpus (MRPC), which consists of 4076 pairs of training sentences and 1725 pairs of test sentences, and most of the data came from the news of social data. Extensive simulations demonstrate that our method outperforms other state-of-the-art methods regarding the correlation coefficient and the mean deviation.

Modern Arabic literature owns its development to the works of Naguib Mahfouz during the five decades of his writing career. Mahfouz brings together various ancient Egyptian tales and prophetic stories into 1950s Egypt. The story that Mahfouz builds in his novels echoes the author's childhood story as well as various other stories. This article aims to explore to what extends the novel echoes the prophetic stories as well as the author’s childhood experiences. The researcher employs intextuality to meet the objective of this study. The findings reveal that Mahfouz adopt and paraphrase various events and figures from Al-Quran and the Bible then put those events and figures into a new context in Awl?d H?ratina Indonesian Edition #3 (Rifa’at Sang Penebus). Besides, Mahfouz portrays the novel’s setting as the reflection of his childhood residence.

Paraphrase identification is a crucial task in natural language understanding, especially in cross-language information retrieval. Nowadays, Multi-Task Deep Neural Network (MT-DNN) has become a state-of-the-art method that brings outstanding results in paraphrase identification [1]. In this paper, our proposed method based on MT-DNN [2] to detect similarities between English and Vietnamese sentences, is proposed. We changed the shared layers of the original MT-DNN from original the BERT [3] to other pre-trained multi-language models such as M-BERT [3] or XLM-R [4] so that our model could work on cross-language (in our case, English and Vietnamese) information retrieval. We also added some tasks as improvements to gain better results. As a result, we gained 2.3% and 2.5% increase in evaluated accuracy and F1. The proposed method was also implemented on other language pairs such as English – German and English – French. With those implementations, we got a 1.0%/0.7% improvement for English – German and a 0.7%/0.5% increase for English – French.

What if the patients most health professionals actively seek to avoid, people with "medically unexplained" or functional symptoms, were those who hold the key to a more successful, more rewarding and more just system of medical practice for all? I think they do. They force us to answer the question, to paraphrase Wittgenstein: What is left over, if I subtract the fact that I have a disease, from the fact that I am ill? Within the answer to this question is the human, participatory aspect of illness, which, despite hundreds of mission statements to the contrary from healthcare organisations the world over, is not adequately addressed in our medical training, practice and principles. We can and should do better, and this is a proposal for how.

Data augmentation is an approach for several text generation tasks. Generally, in the machine translation paradigm, mainly in low-resource language scenarios, many data augmentation methods have been proposed. The most used approaches for generating pseudo data mainly lay in word omission, random sampling, or replacing some words in the text. However, previous methods barely guarantee the quality of augmented data. In this work, we try to build the data by using paraphrase embedding and POS-Tagging. Namely, we generate the fake monolingual corpus by replacing the main four POS-Tagging labels, such as noun, adjective, adverb, and verb, based on both the paraphrase table and their similarity. We select the bigger corpus size of the paraphrase table with word level and obtain the word embedding of each word in the table, then calculate the cosine similarity between these words and tagged words in the original sequence. In addition, we exploit the ranking algorithm to choose highly similar words to reduce semantic errors and leverage the POS-Tagging replacement to mitigate syntactic error to some extent. Experimental results show that our augmentation method consistently outperforms all previous SOTA methods on the low-resource language pairs in seven language pairs from four corpora by 1.16 to 2.39 BLEU points.

Why is there a long-standing debate about paraphrase in poetry? Everyone agrees that paraphrase can be useful; everyone agrees that paraphrase is no substitute for the poem itself. What is there to disagree about? Perhaps this: whether paraphrase can specify everything that counts as a contribution to the meaning of a poem. There are, we say, two ways to take the question; on one way of taking it, the answer is that paraphrase cannot. Does this entail that there is meaning mysteriously locked in a poem, meaning that cannot be represented in any way other than via the poem itself? If that were so it would have profound implications for poetry’s capacity to convey insight. We suggest reasons for thinking that the entailment does not hold. Throughout, we connect the traditional debate over paraphrase, which has largely been conducted within the fields of philosophy and literary theory, with recent empirically oriented thinking about the communicability of meaning, represented by work in pragmatics. We end with a suggestion about what is to count as belonging to meaning, and what as merely among the things that determine meaning.

Community question answering has become increasingly important as they are practical for seeking and sharing information. Applying deep learning models often leads to good performance, but it requires an extensive amount of annotated data, a problem exacerbated for languages suffering a scarcity of resources. Contextualized language representation models have gained success due to promising results obtained on a wide array of downstream natural language processing tasks such as text classification, textual entailment, and paraphrase identification. This paper presents a novel approach by fine-tuning contextualized embeddings for a medical domain community question answering task. The authors propose an architecture combining two neural models powered by pre-trained contextual embeddings to learn a sentence representation and thereafter fine-tuned on the task to compute a score used for both ranking and classification. The experimental results on SemEval Task 3 CQA show that the model significantly outperforms the state-of-the-art models by almost 2% for the '16 edition and 1% for the '17 edition.

We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is to capture similarities as well as idiosyncrasies among typologically different languages. In this article, we show that models trained using UD parse trees for complex NLP tasks can characterize very different languages. We study two tasks of paraphrase identification and relation extraction as case studies. Based on UD parse trees, we develop several models using tree kernels and show that these models trained on the English dataset can correctly classify data of other languages, e.g., French, Farsi, and Arabic. The proposed approach opens up avenues for exploiting UD parsing in solving similar cross-lingual tasks, which is very useful for languages for which no labeled data is available.

Paraphrasing is a process to restate the meaning of a text or a passage using different words in the same language to give a clearer understanding of the original sentence to the readers. Paraphrasing is important in many natural language processing tasks such as plagiarism detection, information retrieval, and machine translation. In this article, we describe our work in paraphrasing Chinese idioms by using the definitions from dictionaries. The definitions of the idioms will be reworded and then scored to find the best paraphrase candidates to be used for the given context. With the proposed approach to paraphrase Chinse idioms in sentences, the BLEU was 75.69%, compared to the baseline approach that was 66.34%.

Advances in communication technologies have enabled peoples to deliver more. Due to this phenomenon, an increasing amount of data are easily disseminated and published on the internet, which encouraged the practice of paraphrasing. It allows the original sentence to be concealed by alternative expressions of the same meaning. Its detection consists in identifying the degree of semantic similarity between them. It is one of the complex tasks of automatic natural language processing and artificial intelligence. Despite the fact that Arabic language is spoken by a large population around the world, it is rich of grammars and semantics that made hard its sentences modeling and similarity computing. In this paper, an Arabic extrinsic paraphrase identification method is proposed. It is based on a Siamese recurrent neural networks architecture seeing its performance in processing variable size of textual sequences. Indeed, pertinent features are firstly extracted using global word vector that used a global co-occurrence matrix based on a local context window. Then, bidirectional long short-term memory is introduced that incorporated efficiently long-term dependent relationships and captured meaningful contextual semantics between words. For paraphrase identification, cosine measure is used as a merge function. It was useful for identifying semantic similarity between the obtained source and suspect vectors. To address the lack of free and publicly Arabic paraphrased datasets, word2vec algorithm and part-of-speech tagging are combined to generate suspect sentences. For its validation, its quality is compared to the SemEval benchmark. Experiments demonstrated the effectiveness of our proposal’s methods.

This paper is concerned withthe problem of paraphrase detection. For a number of applications, the ability to detect similar sentences, such as text mining, summary text, plagiarism detection, authorship authentication, and question answering, is important. Given two phrases, the goal is to detect whether they are identical semantically. This work involves a novel model namely, ParaCap, which uses capsule networks for the investigation of sentences. Capsule networks understand the spatial information (context, language, length of sentences and others) by using the instantiation parameters for the better results as compared to CNNs. For the objective, the Quora Question Pair dataset containing 404291 pairs of Quora Questions is being used. The ParaCap model outperforms many state-of-art methods, and also proves to be comparable to other techniques by achieving the accuracy of 89.19%.

El plagio o fraude académico es uno de los principales problemas que ha surgido junto a la mano de la emersión de las tecnologías y fuentes de internet, del mismo modo debido a la facilidad de encontrar la información en la red no siempre la información es verdadera y no son más que pseudo datos, por dicha razón se consideró conocer cuáles son las causas del plagio y la falta de uso de documentación de fuentes de manera adecuada para la realización de trabajos académicos, siendo como principales causas el hecho de el desconocimiento de las personas sobre como investigar de manera adecuada de fuentes confiables, el no saber cómo realizar un correcto parafraseo y como no se aplican consecuencias judiciales a los que incumplen con plagio. Dando como resultado la recopilación de datos que brindan información acerca de cuáles son las normas que se deben cumplir para no infringir con plagio, además de las consecuencias que conlleva hacer este delito.

The goal of sentence matching is to determine the semantic relation between two sentences, which is the basis of many downstream tasks in natural language processing, such as question answering and information retrieval. Recent studies using attention mechanism to align the elements of two sentences have shown promising results in capturing semantic similarity/relevance. Most existing methods mainly focus on the design of multi-layer attention network, however, some critical issues have not been dealt with well: 1) the higher attention layer is easily affected by error propagation because it relies on the alignment results of preceding attentions; 2) models have the risk of losing low-layer semantic features with the increase of network depth; and 3) the approach of capturing global matching information brings about large computing complexity for model training. To this end, we propose a Deep Bi-Directional Interaction Network (DBDIN) to solve these issues, which captures semantic relatedness from two directions and each direction employs multiple attention-based interaction units. To be specific, the attention of each interaction unit will repeatedly focus on the original sentence representation of another one for semantic alignment, which alleviates the error propagation problem by attending to a fixed semantic representation. Then we design deep fusion to aggregate and propagate attention information from low layers to high layers, which effectively retains low-layer semantic features for subsequential interactions. Moreover, we introduce a self-attention mechanism at last to enhance global matching information with smaller model complexity. We conduct experiments on natural language inference and paraphrase identification tasks with three benchmark datasets SNLI, SciTail and Quora. Experimental results demonstrate that our proposed method can achieve significant improvements over baseline systems without using any external knowledge. Additionally, we conduct interpretable study to disclose how our deep interaction network with attention can benefit sentence matching, which provides a reference for future model design. Ablation studies and visualization analyses further verify that our model can better capture interactive information between two sentences, and the proposed components are indeed able to help modeling semantic relation more precisely.

Respeaking is an effective way to make live and pre-recorded television, as well as live events, accessible to a wide audience. Respeakers use speech-recognition software to repeat or paraphrase wh...

The article is devoted to the review of conditional test generation, one of the most promising fields of natural language processing and artificial intelligence. Specifically, we explore monolingual local sequence transduction tasks: paraphrase generation, grammatical and spelling errors correction, text simplification. To give a better understanding of the considered tasks, we show examples of good rewrites. Then we take a deep look at such key aspects as publicly available datasets with the splits (training, validation, and testing), quality metrics for proper evaluation, and modern solutions based primarily on modern neural networks. For each task, we analyze its main characteristics and how they influence the state-of-the-art models. Eventually, we investigate the most significant shared features for the whole group of tasks in general and for approaches that provide solutions for them. Pages of the article in the issue: 102 - 107 Language of the article: Ukrainian

In this paper, we address the problem of uncertainty management in identification of paraphrase sentence pairs. Paraphrase sentences are simply sets/pairs of sentences that express the same facts and/or opinions using different words or order of words. We propose the use of certainty factor (CF) model in paraphrase detection. A set of succeeding paraphrase detection features (generic and distance based features) is built by filtering and this set is used as evidences in CF model. The CF model is evaluated by F1 and accuracy measures on Microsoft Research Paraphrase corpus. The results are compared to the well-known Bayesian reasoning. The experimental results showed that CF model is an alternating paraphrase detection method to Bayes model.

In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a simple method in the context of solving the paraphrase generation task. If we use a sequential encoder-decoder model for generating paraphrase, we would like the generated paraphrase to be semantically close to the original sentence. One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far. This is ensured by using a sequential pair-wise discriminator that shares weights with the encoder that is trained with a suitable loss function. Our loss function penalizes paraphrase sentence embedding distances from being too large. This loss is used in combination with a sequential encoder-decoder network. We also validated our method by evaluating the obtained embeddings for a sentiment analysis task. The proposed method results in semantic embeddings and outperforms the state-of-the-art on the paraphrase generation and sentiment analysis task on standard datasets. These results are also shown to be statistically significant., Comment: This work is an extension of our COLING-2018 paper arXiv:1806.00807

Paraphrase detection allows determining how original and suspect documents convey the same meaning. It has attracted attention from researchers in many Natural Language Processing (NLP) tasks such as plagiarism detection, question answering, information retrieval, etc., Traditional methods (e.g., Term Frequency-Inverse Document Frequency (TF-IDF), Latent Dirichlet Allocation (LDA), and Latent Semantic Analysis (LSA)) cannot capture efficiently hidden semantic relations when sentences may not contain any common words or the co-occurrence of words is rarely present. Therefore, we proposed a deep learning model based on Global Word embedding (GloVe) and Recurrent Convolutional Neural Network (RCNN). It was efficient for capturing more contextual dependencies between words vectors with precise semantic meanings. Seeing the lack of resources in Arabic language publicly available, we developed a paraphrased corpus automatically. It preserved syntactic and semantic structures of Arabic sentences using word2vec model and Part-Of-Speech (POS) annotation. Overall experiments shown that our proposed model outperformed the state-of-the-art methods in terms of precision and recall

These poems were written during the peak of the COVID-19 pandemic. ‘This' is a poetic paraphrase and development of a piece in The Guardian newspaper.

To paraphrase Lewis Carroll’s poem “The Walrus and the Carpenter” from his Through the Looking Glass, “The time has come to talk of many things.” Not as the Walrus did in the nursery rhyme, “of sho...

The article argues in favour of bringing back the original full title of Gogol's epic poem in prose, namely The Adventures/Wanderings of Chichikov, or Dead Souls [Pokhozhdeniya Chichikova, ili Myortvye dushi]. Once reduced, the title emphasizes stagnancy and rigidity, but loses what is essential for the novel's plot: the potential eidos of movement, road, and wandering. The scholar examines the semantics of the cover of the separate edition of Dead Souls and its connection with the full name of this Gogol masterpiece. Compared in the new context are the book's beginning and ending, with a new interpretation offered for ‘the bird-troika' as well as for the wheel: it is shown how the latter represents a sacred circle prototype in addition to familiar secular connotations. The author follows the poem's paraphrastic context which connects it with Dante's Divina Commedia and is not limited to motifs, reminiscences, and identic plotlines, but highlights the general Christian meaning of the paschal conclusion of a mortal life, interpreted differently by the Catholic and Eastern Orthodox cultural traditions, represented by Dante and Gogol, respectively.

Paraphrase detection is one of the fundamental tasks in the area of natural language processing. Paraphrase refers to those sentences or phrases that convey the same meaning but use different wording. It has a lot of applications such as machine translation, text summarization, QA systems, and plagiarism detection. In this research, we propose a new deep-learning based model which can generalize well despite the lack of training data for deep models. After preprocessing, our model can be divided into two separate modules. In the first one, we train a single Bi-LSTM neural network to encode the whole input by leveraging its pretrained GloVe word vectors. In the second module, three sets of handcrafted features are used to measure the similarity between each pair of sentences, some of which are introduced in this research for the first time. Our final model is formed by incorporating the handcrafted features with the output of the Bi-LSTM network. Evaluation results on MSRP and Quora datasets show that it outperforms almost all the previous works in terms of f-measure and accuracy on MSRP and achieves comparable results on Quora. On the Quora-question pair competition launched by Kaggle, our model ranked among the top 24% solutions between more than 3000 teams.

The translation of speech acts on product packaging labels was the object of this research. This study aimed to analyze the types of speech acts, translation techniques used by translators to translate label text, and to identify how these techniques affected changing speech acts on product packaging labels. A qualitative descriptive approach was used in this study. The data was presented in the form of utterances on packaging labels that included speech acts and their translations. Document analysis and focus group discussion were used to gather the data. According to the findings, the researcher discovered 94 different forms of speech acts. The translator used 14 different translation techniques in translating the label. Several translation techniques used in this study affect the changing of speech acts in the target language. Deletion, reduction, modulation, paraphrase, and compensation techniques were found to induce a change in speech acts. There were 12 data of the speech acts shifting. The cumulative score for the quality of the translation on the product packaging label was 2.75.

In recent years, deep neural network has achieved great success in solving many natural language processing tasks. Particularly, substantial progress has been made on neural text generation, which takes the linguistic and non-linguistic input, and generates natural language text. This survey aims to provide an up-to-date synthesis of core tasks in neural text generation and the architectures adopted to handle these tasks, and draw attention to the challenges in neural text generation. We first outline the mainstream neural text generation frameworks, and then introduce datasets, advanced models and challenges of four core text generation tasks in detail, including AMR-to-text generation, data-to-text generation, and two text-to-text generation tasks (i.e., text summarization and paraphrase generation). Finally, we present future research directions for neural text generation. This survey can be used as a guide and reference for researchers and practitioners in this area.

Plagiarism detection deals with detecting plagiarized fragments among textual documents. The availability of digital documents in online libraries makes plagiarism easier and on the other hand, to be easily detected by automatic plagiarism detection systems. Large scale plagiarism corpora with a wide variety of plagiarism cases are needed to evaluate different detection methods in different languages. Plagiarism detection corpora play an important role in evaluating and tuning plagiarism detection systems. Despite of their importance, few corpora have been developed for low resource languages. In this paper, we propose HAMTA, a Persian plagiarism detection corpus. To simulate real cases of plagiarism, manually paraphrased text are used to compile the corpus. For obtaining the manual plagiarism cases, a crowdsourcing platform is developed and crowd workers are asked to paraphrase fragments of text in order to simulate real cases of plagiarism. Moreover, artificial methods are used to scale-up the proposed corpus by automatically generating cases of text re-use. The evaluation results indicate a high correlation between the proposed corpus and the PAN state-of-the-art English plagiarism detection corpus.

Visually grounded paraphrases (VGPs) describe the same visual concept but in different wording. Previous studies have developed models to identify VGPs from language and visual features. In these existing methods, language and visual features are simply fused. However, our detailed analysis indicates that VGPs with different lexical similarities require different weights on language and visual features to maximize identification performance. This motivates us to propose a gated neural network model to adaptively control the weights. In addition, because VGP identification is closely related to phrase localization, we also propose a way to explicitly incorporate phrase-object correspondences. From our evaluation in detail, we confirmed our model outperforms the state-of-the-art model.

Kṛṣṇadevarāya’s sixteenth-century Telugu poem, the Āmuktamālyada (Giver of the Worn Garland), includes the stories of two āḻvārs, Viṣṇucitta and his foster daughter, Āṇṭāḷ. Though the text does not quote from or paraphrase the historical āḻvārs’ poems, it presents two stutis of Viṣṇu’s incarnations—the first a celebratory praise poem sung by Viṣṇucitta, the second a blame-praise (nindā-stuti) uttered by Āṇṭāḷ. Comparing the two stutis in the Āmuktamālyada to the āḻvārs’ poetry in the Tamil Nālāyiradivyaprabandham (Divine Book of Four Thousand), this article explores the ways in which the Āmuktamālyada marks various shifts in understanding the respective roles of the āḻvārs and of Viṣṇu’s avatāras. A central claim of the article is that the poem tells the story of an ascendant Śrīvaiṣṇava community navigating the emotional relationship between the human and the divine and that the two stutis are set up to help negotiate emotional experiences of all those involved in a loving relationship with god—god himself, his consort, and his devotees.

Natural language inference (NLI) is the basic task of many applications such as question answering and paraphrase recognition. Existing methods have solved the key issue of how the NLI model can benefit from external knowledge. Inspired by this, we attempt to further explore the following two problems: (1) how to make better use of external knowledge when the total amount of such knowledge is constant and (2) how to bring external knowledge to the NLI model more conveniently in the application scenario. In this paper, we propose a novel joint training framework that consists of a modified graph attention network, called the knowledge graph attention network, and an NLI model. We demonstrate that the proposed method outperforms the existing method which introduces external knowledge, and we improve the performance of multiple NLI models without additional external knowledge.

Paraphrase, i.e., differing textual realizations of the same meaning, has proven useful for many natural language processing (NLP) applications. Collecting paraphrase for predicates in knowledge bases (KBs) is the key to comprehend the RDF triples in KBs. Existing works have published some paraphrase datasets automatically extracted from large corpora, but have too many redundant pairs or don't cover enough predicates, which cannot be improved by computer only and need the help of human beings. This paper shows a full process of collecting large-scale and high-quality paraphrase dictionaries for predicates in knowledge bases, which takes advantage of existing datasets and combines the technologies of machine mining and crowdsourcing. Our dataset comprises 2284 distinct predicates in DBpedia and 31130 paraphrase pairs in total, the quality of which is a great leap over previous works. Then it is demonstrated that such good paraphrase dictionaries can do great help to natural language processing tasks such as question answering and language generation. We also publish our own dictionary for further research.

Black-box machine translation systems have proven incredibly useful for a variety of applications yet by design are hard to adapt, tune to a specific domain, or build on top of. In this work, we introduce a method to improve such systems via automatic pre-processing (APP) using sentence simplification. We first propose a method to automatically generate a large in-domain paraphrase corpus through back-translation with a black-box MT system, which is used to train a paraphrase model that “simplifies” the original sentence to be more conducive for translation. The model is used to preprocess source sentences of multiple low-resource language pairs. We show that this preprocessing leads to better translation performance as compared to non-preprocessed source sentences. We further perform side-by-side human evaluation to verify that translations of the simplified sentences are better than the original ones. Finally, we provide some guidance on recommended language pairs for generating the simplification model corpora by investigating the relationship between ease of translation of a language pair (as measured by BLEU) and quality of the resulting simplification model from back-translations of this language pair (as measured by SARI), and tie this into the downstream task of low-resource translation.

Learning sentence representation is a fundamental task in Natural Language Processing. Most of the existing sentence pair modelling architectures focus only on extracting and using the rich sentence pair features. The drawback of utilizing all of these features makes the learning process much harder. In this study, we propose a reinforcement learning (RL) method to learn a sentence pair representation when performing tasks like semantic similarity, paraphrase identification, and question-answer pair modelling. We formulate this learning problem as a sequential decision making task where the decision made in the current state will have a strong impact on the following decisions. We address this decision making with a policy gradient RL method which chooses the irrelevant words to delete by looking at the sub-optimal representation of the sentences being compared. With this policy, extensive experiments show that our model achieves on par performance when learning task-specific representations of sentence pairs without needing any further knowledge like parse trees. We suggest that the simplicity of each task inference provided by our RL model makes it easier to explain.

Semantic matching is a basic problem in natural language processing, but it is far from solved because of the differences between the pairs for matching. In question answering (QA), answer selection (AS) is a popular semantic matching task, usually reformulated as a paraphrase identification (PI) problem. However, QA is different from PI because the question and the answer are not synonymous sentences and not strictly comparable. In this work, a novel knowledge and cross-pair pattern guided semantic matching system (KCG) is proposed, which considers both knowledge and pattern conditions for QA. We apply explicit cross-pair matching based on Graph Convolutional Network (GCN) to help KCG recognize general domain-independent Q-to-A patterns better. And with the incorporation of domain-specific information from knowledge bases (KB), KCG is able to capture and explore various relations within Q-A pairs. Experiments show that KCG is robust against the diversity of Q-A pairs and outperforms the state-of-the-art systems on different answer selection tasks.

We tackle the low-resource problem in style transfer by employing transfer learning that utilizes abundantly available raw corpora. Our method consists of two steps: pre-training learns to generate a semantically equivalent sentence with an input assured grammaticality, and fine-tuning learns to add a desired style. Pre-training has two options, auto-encoding and machine translation based methods. Pre-training based on AutoEncoder is a simple way to learn these from a raw corpus. If machine translators are available, the model can learn more diverse paraphrasing via roundtrip translation. After these, fine-tuning achieves high-quality paraphrase generation even in situations where only 1k sentence pairs of the parallel corpus for style transfer is available. Experimental results of formality style transfer indicated the effectiveness of both pre-training methods and the method based on roundtrip translation achieves state-of-the-art performance.

In this Letter, the authors introduce a novel approach to learn representations for sentence-level paraphrase identification (PI) using BERT and ten natural language processing tasks. Their method trains an unsupervised model called BERT with two different tasks to detect whether two sentences are in paraphrase relation or not. Unlike conventional BERT, which fine tunes the target task such as PI to pre-trained BERT, twice fine-tuning deep neural networks first fine tune each task (e.g. general language understanding evaluation tasks, question answering, and paraphrase adversaries from word scrambling task) and second fine tune target PI task. As a result, the multi-fine-tuned BERT model outperformed the fine-tuned model only with Microsoft Research Paraphrase Corpus (MRPC), which is paraphrase data, except for one case of Stanford Sentiment Treebank - 2 (SST-2). Multi-task fine-tuning is a simple idea but experimentally powerful. Experiments show that fine-tuning just PI tasks to the BERT already gives enough performance, but additionally, fine-tuning similar tasks can affect performance (3.4% point absolute improvement) and be competitive with the state-of-the-art systems.

Purpose The purpose of this study is to assess information literacy skills of undergraduates in Nigerian universities. Design/methodology/approach A self-assessed questionnaire was developed to collect data from the final year undergraduates in 15 universities. A total of 1,350 final year Library and Information Science (LIS) students responded to the questionnaire which was used for analysis. Findings The study revealed that the majority of the LIS final year undergraduates mostly consult journal articles, followed by internet information and online databases during their research process. The undergraduates rated well-known author(s), current information, credible information, accurate and relevant information as very important when evaluating online information resources. It was found that the students rated their ability to organize information and integrate ideas from consulted information as high. While they were deficient in ability to correctly paraphrase ideas to avoid plagiarism and use citation and referencing styles correctly. On the whole, almost half of the final year undergraduates of LIS rated their level of information literacy skills to be moderate. Practical implications The findings of the study will inform librarians and faculty in universities in developing countries like Nigeria to develop an information literacy instruction policy. Originality/value Assessing information literacy skills will provide the foundation and knowledge to improve the development of information literacy training programmes.

In this paper, A shorter version of the paper appeared in German in the final report of the Digital Plato project which was funded by the Volkswagen Foundation from 2016 to 2019. [35], [28]. we present a method for paraphrase extraction in Ancient Greek that can be applied to huge text corpora in interactive humanities applications. Since lexical databases and POS tagging are either unavailable or do not achieve sufficient accuracy for ancient languages, our approach is based on pure word embeddings and the word mover’s distance (WMD) [20]. We show how to adapt the WMD approach to paraphrase searching such that the expensive WMD computation has to be computed for a small fraction of the text segments contained in the corpus, only. Formally, the time complexity will be reduced from O ( N · K 3 · log K ) \mathcal{O}(N\cdot {K^{3}}\cdot \log K) to O ( N + K 3 · log K ) \mathcal{O}(N+{K^{3}}\cdot \log K) , compared to the brute-force approach which computes the WMD between each text segment of the corpus and the search query. N is the length of the corpus and K the size of its vocabulary. The method, which searches not only for paraphrases of the same length as the search query but also for paraphrases of varying lengths, was evaluated on the Thesaurus Linguae Graecae® (TLG®) [25]. The TLG consists of about 75 · 10 6 75\cdot {10^{6}} Greek words. We searched the whole TLG for paraphrases for given passages of Plato. The experimental results show that our method and the brute-force approach, with only very few exceptions, propose the same text passages in the TLG as possible paraphrases. The computation times of our method are in a range that allows its application in interactive systems and let the humanities scholars work productively and smoothly.

Paraphrase Generation is one of the most important and challenging tasks in the field of Natural Language Generation. The paraphrasing techniques help to identify or to extract/generate phrases/sentences conveying the similar meaning. The paraphrasing task can be bifurcated into two sub-tasks namely, Paraphrase Identification (PI) and Paraphrase Generation (PG). Most of the existing proposed state-of-the-art systems have the potential to solve only one problem at a time. This paper proposes a light-weight unified model that can simultaneously classify whether given pair of sentences are paraphrases of each other and the model can also generate multiple paraphrases given an input sentence. Paraphrase Generation module aims to generate fluent and semantically similar paraphrases and the Paraphrase Identification system aims to classify whether sentences pair are paraphrases of each other or not. The proposed approach uses an amalgamation of data sampling or data variety with a granular fine-tuned Text-To-Text Transfer Transformer (T5) model. This paper proposes a unified approach which aims to solve the problems of Paraphrase Identification and generation by using carefully selected data-points and a fine-tuned T5 model. The highlight of this study is that the same light-weight model trained by keeping the objective of Paraphrase Generation can also be used for solving the Paraphrase Identification task. Hence, the proposed system is light-weight in terms of the model’s size along with the data used to train the model which facilitates the quick learning of the model without having to compromise with the results. The proposed system is then evaluated against the popular evaluation metrics like BLEU (BiLingual Evaluation Understudy):, ROUGE (Recall-Oriented Understudy for Gisting Evaluation), METEOR, WER (Word Error Rate), and GLEU (Google-BLEU) for Paraphrase Generation and classification metrics like accuracy, precision, recall and F1-score for Paraphrase Identification system. The proposed model achieves state-of-the-art results on both the tasks of Paraphrase Identification and paraphrase Generation.

Everything is online. We exist in the age of internet. It has become an important part of our life that we cannot imagine our life without it. We use internet for various different needs from sending messages, calling, sharing pictures to acquire skills online. It is serving as a source of information, entertainment and has made online shopping easy. It has made our life very convenient. But people now tend to spend more and more time on it without doing any actual work. And it saves our time too. Besides every big or small detail is available on the internet. In this age of internet, one tends to use easy methods to do his work, assignments, projects, speeches, presentations instead of putting in efforts from their side. Technology has been developing from letters to mails, books to pdfs and blackboards to screens. Since everything is online, there is a high chance of stealing or copying someone else’s work and this is called plagiarism. Plagiarism is the practice of copying other’s work or ideas. Plagiarism has become disseminated in online. It happens due to laziness, last minute panic, desire to get good grades, fear of failing, lack of confidence. Plagiarism is popular in computer language coding programs, projects and documentation/research papers. Plagiarism is being done with or without knowledge. Sometimes it is very difficult to check if you are plagiarizing when you paraphrase someone’s ideas as your own. Plagiarism does not allow an individual to develop their writing skills, nor does it serve the purpose of the assignments. Plagiarism prevents you from shaping your own ideas and opinions on a topic.

Natural Language Processing is an active area of research where new challenges and issues such as text similarity, semantic analysis, paraphrase identification, citation matching, and language translation, etc. foster the need to further exploit this area. Among the above issues, text similarity is one of the key operative challenges which is being explored by many researchers. In text similarity, extracting the meaningful word, phrase, and sentence patterns from texts requires an effective way that can be evaluated based on various standardized metrics. Therefore, we propose a model based on Convolutional Neural Networks (CNN) and Convolutional Neural Networks- Long Short Term Memory (CNN-LSTM) to find the text similarity as image recognition. Our results show that we achieved better classification results with the precision of 61.3% and recall of 57.9% with MatchGridTower as compared to the earlier MatchPyramid model having a precision of 54.0% and recall of 53.1%.

The brackish politics and the criticism of the university are played out, then, in a context in which the university has pretty much disappeared as an independent and unitary institution. The liberal arts have become professionalized also because those disciplines are driven by doctoral programs, and the curriculum increasingly reflects not the needs of students but the research needs and professional interests of faculty. With the spread of professional education through undergraduate life and the professional spirit throughout all education, the central issue, to steal and paraphrase some lines from Ernest J. Weinrib, is whether education is to be understood in instrumental or noninstrumental terms. Student services has been one of the sites of the principal force in the erosion of education, namely credit inflation.

In recent years, neural paraphrase generation based on Seq2Seq has achieved superior performance, however, the generated paraphrase still has the problem of lack of diversity. In this paper, we focus on improving the diversity between the generated paraphrase and the original sentence, i.e., making generated paraphrase different from the original sentence as much as possible. We propose BTmPG (Back-Translation guided multi-round Paraphrase Generation), which leverages multi-round paraphrase generation to improve diversity and employs back-translation to preserve semantic information. We evaluate BTmPG on two benchmark datasets. Both automatic and human evaluation show BTmPG can improve the diversity of paraphrase while preserving the semantics of the original sentence., Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

In this paper, we propose Semantically Smooth Bilingual Recursive Autoencoders to learn bilingual phrase embeddings. The intuition behind our work is to exploit the intrinsic geometric structure of the embedding space and enforce the learned phrase embeddings to be semantically smooth. Specifically, we extend the conventional bilingual recursive autoencoders by preserving the translation and paraphrase probability distributions via regularization terms to simultaneously exploit richer explicit and implicit similarity constraints for bilingual phrase embeddings. To examine the effectiveness of our model, we incorporate two phrase-level similarity features based on the proposed model into a state-of-the-art phrase-based statistical machine translation system. Experiments on NIST Chinese–English test sets show that our model achieves substantial improvements over the baseline.

Paraphrase is an expression of a text with alternative words and orders to achieve a better clarity. Paraphrases have been found vital for augmenting training dataset, which aid to enhance performance of machine learning models that intended for various natural language processing (NLP) tasks. Thus, recently, automatic paraphrase generation has received increasing attention. However, evaluating quality of generated paraphrases is technically challenging. In the literature, the importance of generated paraphrases is tended to be determined by their impact on the performance of other NLP tasks. This kind of evaluation is referred as extrinsic evaluation, which requires high computational resources to train and test the models. So far, very little attention has been paid to the role of intrinsic evaluation in which quality of generated paraphrase is judged against predefined ground truth (reference paraphrases). In fact, it is also very challenging to find ideal and complete reference paraphrases. Therefore, in this study, we propose semantic or meaning oriented automatic evaluation metric that helps to evaluate quality of generated paraphrases against the original text, which is an intrinsic evaluation approach. Further, we evaluate quality of the paraphrases by assessing their impact on other NLP tasks, which is an extrinsic evaluation method. The goal is to explore the relationship between intrinsic and extrinsic evaluation methods. To ensure the effectiveness of proposed evaluation methods, extensive experiments are done on different publicly available datasets. The experimental results demonstrate that our proposed intrinsic and extrinsic evaluation strategies are promising. The results further reveal that there is a significant correlation between intrinsic and extrinsic evaluation approaches.