Search

Choice overload describes a situation in which a person has difficulty in making decisions due to too many options. We examine choice overload when displaying related-article recommendations in digital libraries, and examine the effectiveness of recommendation algorithms in this domain. We first analyzed existing digital libraries, and found that only 30% of digital libraries show related-article recommendations to their users. Of these libraries, the majority (74%) displays 3–5 related articles; 28% of them display 6–10 related articles; and no digital library displayed more than ten related-article recommendations. We then conducted our experimental evaluation through GESIS' digital library Sowiport, with recommendations delivered by recommendations-as-a-service provider Mr. DLib. We use four metrics to analyze 41.3 million delivered recommendations: click-through rate (CTR), percentage of clicked recommendation sets (clicked set rate, CSR), average clicks per clicked recommendation set (ACCS), and time to first click (TTFC), which is the time between delivery of a set of recommendations to the first click. These metrics help us to analyze choice overload and can yield evidence for finding the ideal number of recommendations to display. We found that with increasing recommendation set size, i.e., the numbers of displayed recommendations, CTR decreases from 0.41% for one recommendation to 0.09% for 15 recommendations. Most recommendation sets only receive one click. ACCS increases with set size, but increases more slowly for six recommendations and more. When displaying 15 recommendations, the average clicks per set is at a maximum (1.15). Similarly, TTFC increases with larger recommendation set size, but increases more slowly for sets of more than five recommendations. While CTR and CSR do not indicate choice overload, ACCS and TTFC point toward 5–6 recommendations as being optimal for Sowiport. Content-based filtering yields the highest CTR with 0.118%, while stereotype recommendations yield the highest ACCS (1.28). Stereotype recommendations also yield the highest TTFC. This means that users take more time before clicking stereotype recommendations when compared to recommendations based on other algorithms. [ABSTRACT FROM AUTHOR]

Scientific documents generally contain multiple mathematical expressions in them. Detecting inline mathematical expressions are one of the most important and challenging tasks in scientific text mining. Recent works that detect inline mathematical expressions in scientific documents have looked at the problem from an image processing perspective. There is little work that has targeted the problem from NLP perspective. Towards this, we define a few features and applied Conditional Random Fields (CRF) to detect inline mathematical expressions in scientific documents. Apart from this feature based approach, we also propose a hybrid algorithm that combines Bidirectional Long Short Term Memory networks (Bi‐LSTM) and feature‐based approach for this task. Experimental results suggest that this proposed hybrid method outperforms several baselines in the literature and also individual methods in the hybrid approach. [ABSTRACT FROM AUTHOR]

• Unsupervised word sense disambiguation technique for diverse NLP tasks. • Word embeddings combining sense disambiguation, improving its vector representation. • Synset embedding models can help to leverage the disambiguation of polysemous words. • Multi-sense embedding models provide better representation than single-sense ones. • Recurrent synset-embedding models can improve the quality of word representations. Natural Language Understanding has seen an increasing number of publications in the last few years, especially after robust word embeddings models became prominent, when they proved themselves able to capture and represent semantic relationships from massive amounts of data. Nevertheless, traditional models often fall short in intrinsic issues of linguistics, such as polysemy and homonymy. Any expert system that makes use of natural language in its core, can be affected by a weak semantic representation of text, resulting in inaccurate outcomes based on poor decisions. To mitigate such issues, we propose a novel approach called Most Suitable Sense Annotation (MSSA) , that disambiguates and annotates each word by its specific sense, considering the semantic effects of its context. Our approach brings three main contributions to the semantic representation scenario: (i) an unsupervised technique that disambiguates and annotates words by their senses, (ii) a multi-sense embeddings model that can be extended to any traditional word embeddings algorithm, and (iii) a recurrent methodology that allows our models to be re-used and their representations refined. We test our approach on six different benchmarks for the word similarity task, showing that our approach can produce state-of-the-art results and outperforms several more complex state-of-the-art systems. [ABSTRACT FROM AUTHOR]

Current mathematical search systems allow math expressions within a document to be queried using math expressions and keywords. To accept such queries, math search systems must index both math expressions and textual information in documents. Each indexed math expression is usually associated with all the words in its surrounding context within a given window size. However, we found that this context is often ineffective for explaining math expressions in scientific papers. The meaning of an expression is usually defined in the early part of a document, and the meaning of each symbol contained in the expression can be useful for explaining the entire expression. This explanation may not be captured within the context of a math expression, unless we set the context to have a very wide window size. However, widening the window size also increases the proportion of words that are unrelated to the expression. This paper proposes the use of dependency relationships between math expressions to enrich the textual information of each expression. We examine the influence of this enrichment in a math search system. The experimental results show that significantly better precision can be obtained using the enriched textual information rather than the math expressions' own textual information. This indicates that the enrichment of textual information for each math expression using dependency relationships enhances the math search system. [ABSTRACT FROM AUTHOR]

Formulaic expressions, such as ' in this paper we propose ', are helpful for authors of scholarly papers because they convey communicative functions; in the above, it is ' showing the aim of this paper '. Thus, resources of formulaic expressions, such as a dictionary, that could be looked up easily would be useful. However, forms of formulaic expressions can often vary to a great extent. For example, ' in this paper we propose ', ' in this study we propose ' and ' in this paper we propose a new method to ' are all regarded as formulaic expressions. Such a diversity of spans and forms causes problems in both extraction and evaluation of formulaic expressions. In this paper, we propose a new approach that is robust to variation of spans and forms of formulaic expressions. Our approach regards a sentence as consisting of a formulaic part and non-formulaic part. Then, instead of trying to extract formulaic expressions from a whole corpus, by extracting them from each sentence, different forms can be dealt with at once. Based on this formulation, to avoid the diversity problem, we propose evaluating extraction methods by how much they convey specific communicative functions rather than by comparing extracted expressions to an existing lexicon. We also propose a new extraction method that utilises named entities and dependency structures to remove the non-formulaic part from a sentence. Experimental results show that the proposed extraction method achieved the best performance compared to other existing methods. • Formulaic expression extraction using named entities and dependency structure. • Sentence retrieval task as an extrinsic evaluation for formulaic expressions. • Changing weights on word embeddings captures characteristics of extraction methods. [ABSTRACT FROM AUTHOR]

This study is a mixed method, i.e. qualitative as well as quantitative, analysis of the stylistic characteristics of texts submitted to Japanese Q & A communities. Along with the development of social media, Q & A communities are attracting much scholarly attention as important resources for analysing online communication. In Q & A communities, people freely submit questions and answers; questions are classified into subject categories; and the best answers are selected. In this study, we analyse the stylistic characteristics of three types of submission, i.e. questions, best answers, and normal answers, in two different subject categories, i.e. "personal computers and related devices" and "love and human relations advice". The results show that the textual styles clearly distinguished these six classes of texts and clarified their respective characters. Our findings provide useful knowledge about how people differ in their communication styles regarding subject categories and on how people select communication styles. This study will contribute to research into discovering current online communication styles. [ABSTRACT FROM AUTHOR]

Abstract Sentence compression aims to shorten a sentence into a compression while remaining grammatical and preserving the underlying meaning of the original sentence. Previous works have recognized that linguistic features such as parts-of-speech tags and dependency labels are helpful to compression generation. In this work, we introduce a gating mechanism and propose a gated neural network that selectively exploits linguistic knowledge for deletion-based sentence compression. An extensive experiment was conducted on four downstream datasets, showing that the proposed gated neural network method leads to better compression upon both automatic metrics and human evaluation, compared to previous competitive compression methods. We also observed that the generated compression by the proposed gated neural network share more grammatical relations in common with the ground-truth compression than the baseline method, indicating that important grammatical relations, such as subject or object of a sentence, are more likely to be kept in the compression by the proposed method. Furthermore, visualization analysis is conducted to explore the selective use of linguistic features, suggesting that the gate mechanism could condition the predicted compression on different linguistic features. [ABSTRACT FROM AUTHOR]

We built a researcher identifier management system called the Researcher Name Resolver (RNR) to assist with the name disambiguation of authors in digital libraries on the Web. RNR, which is designed to cover all researchers in Japan, is a Web-oriented service that can be openly connected with external scholastic systems. We expect it to be widely used for enriched scholarly communications. In this paper, we first outline the conceptual framework of RNR, which is jointly focused on researcher identifier management and Web resource linking. We based our researcher identifier scheme on the reuse of multiple sets of existing researcher identifiers belonging to the Japanese grant database KAKEN and the researcher directory ReaD & Researchmap. Researcher identifiers are associated by direct links to related resources on the Web through a combination of methods, including descriptive mapping, focused crawling on campus directories and researcher identification by matching names and affiliations. Second, we discuss our implementation of RNR based on this framework. Researcher identifiers construct uniform resource identifiers to show Web pages that describe researcher profiles and provide links to related external resources. We have adapted Web-friendly technologies-e.g., OpenSearch and the RDFs of Linked Data technology-in this implementation to provide Web-friendly services. Third, we discuss our application of RNR to a name disambiguation task for the search portal of the Japanese Institutional Repositories Online to determine how well the researcher identifier management system cooperates with external systems. Finally, we discuss lessons learned from the entire project as well as the future development directions we intend to take. [ABSTRACT FROM AUTHOR]

Along with its methodological development, authorship analysis has expanded in scope to new application areas like authorship profiling and computational sociolinguistics as well as conventional ones like authorship attribution. For these new applications, providing a new interpretation of text through the textual characteristics is as important as improving the classification performance between the authors, which was the aim in conventional applications. Lexical indicators were one of the most frequently used characteristics in conventional applications as they were effective at discriminating between authors, but most of the previously used indicators were based on the frequencies of morphemes, and reflected only limited aspects of the writing styles of the authors. In order to use these types of characteristics for new applications, we need to develop indicators reflecting other various aspects of the authors writing styles that are useful for interpretation as well as classification. As such, we propose the use of two types of co-occurrence-based indicators, namely network indicators and a co-occurrence-based concentration indicator in this field. Experimental results using the Aozora Bunko corpora, along with qualitative analyses, showed that our indicators were very effective at capturing aspects of the styles of the authors as well as for improving the classification performance. We concluded that our indicators successfully supplement previously used indicators and are useful for various new applications in authorship analysis. [ABSTRACT FROM AUTHOR]