Search

Intelligent voice assistants, such as Apple Siri and Amazon Alexa, are widely used nowadays. These task-oriented dialogue systems require a semantic parsing module in order to process user utterances and understand the action to be performed. This semantic parsing component was initially implemented by rule-based or statistical slot-filling approaches for processing simple queries; however, the appearance of more complex utterances demanded the application of shift-reduce parsers or sequence-to-sequence models. Although shift-reduce approaches were initially considered the most promising option, the emergence of sequence-to-sequence neural systems has propelled them to the forefront as the highest-performing method for this particular task. In this article, we advance the research on shift-reduce semantic parsing for task-oriented dialogue. We implement novel shift-reduce parsers that rely on Stack-Transformers. This framework allows to adequately model transition systems on the transformer neural architecture, notably boosting shift-reduce parsing performance. Furthermore, our approach goes beyond the conventional top-down algorithm: we incorporate alternative bottom-up and in-order transition systems derived from constituency parsing into the realm of task-oriented parsing. We extensively test our approach on multiple domains from the Facebook TOP benchmark, improving over existing shift-reduce parsers and state-of-the-art sequence-to-sequence models in both high-resource and low-resource settings. We also empirically prove that the in-order algorithm substantially outperforms the commonly used top-down strategy. Through the creation of innovative transition systems and harnessing the capabilities of a robust neural architecture, our study showcases the superiority of shift-reduce parsers over leading sequence-to-sequence methods on the main benchmark. [ABSTRACT FROM AUTHOR]

In the information age, semantic parsing technology drives efficiency improvement and accelerates the process of intelligence. However, it faces complex understanding, data inflation, inappropriate evaluation, and difficult application of advanced large models. This study analyses the current challenges and looks forward to the development trend of the technology. Specific approaches include: this study adopts a systematic review method and strictly follows the PRISMA framework, deeply analyzes the key ideas, methods, problems, and solutions of traditional and neural network methods, and explores the model performance, API application, dataset, and evaluation mechanism. Through literature analysis, the technology is classified according to its application scenarios. Then, the practical application contributions are summarized, current limitations such as data size, model performance, and resource requirements are analyzed, and future directions such as dataset expansion, real-time performance enhancement, and industrial applications are envisioned. The results of the study show significant advances in semantic parsing technology with far-reaching impacts. Traditional and neural network methods complement each other to promote theoretical and practical innovation. In the future, with the continuous progress and in-depth application of machine learning technology, semantic parsing technology needs to further deepen the research on logical reasoning and evaluation, to better cope with technical challenges and lead the new development of natural language processing and AI. [ABSTRACT FROM AUTHOR]

Knowledge graph question answering (KGQA) is a technology that retrieves relevant answers from a knowledge graph by processing natural language questions posed by users. Early KGQA technologies were limited by the size of knowledge graphs, computational power, and natural language processing capabilities, resulting in lower accuracy. In recent years, with advancements in artificial intelligence, particularly the development of large language models (LLMs), KGQA technology has achieved significant improvements. LLMs such as GPT-3 have been widely applied to enhancing the performance of KGQA. To better study and learn the enhanced KGQA technologies, this paper summarizes various methods using LLMs for KGQA. Firstly, the relevant knowledge of LLMs and KGQA is summarized, including the technical principles and training methods of LLMs, as well as the basic concepts of knowledge graphs, question answering, and KGQA. Secondly, existing methods of enhancing KGQA with LLMs are reviewed from two dimensions: semantic parsing and information retrieval. The problems that these methods address and their limitations are analyzed. Additionally, related resources and evaluation methods for KGQA enhanced by LLMs are collected and organized, and the performance of existing methods is summarized. Finally, the limitations of current methods are analyzed, and future research directions are proposed.

The context-dependent text-to-SQL task has profound real-world implications, as it facilitates users in extracting knowledge from vast databases, which allows users to acquire the information interactively for better accuracy. Unfortunately, current models struggle to address this task effectively due to the scarcity of data led by the high annotation overhead. The most straightforward method for addressing this problem is data augmentation, which aims at scaling up the parsing corpus. However, the naive methods suffer from the low diversity of the augmented data. To address this limitation, we propose the state-based CONtext-dependent text-to-SQL Data Augmentation (ConDA), which generate and filter augmented data based on the dialogue state, which has higher diversity. Experimental results show that ConDA yields performance improvement on all experimental datasets with an average boosting of 1.6 % , proving the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Referring image segmentation aims to segment object in an image based on a referring expression. Its difficulty lies in aligning expression semantics with visual instances. The existing methods based on semantic reasoning are limited by the performance of external syntax parser and do not explicitly explore the relationships between visual instances. This article proposes an end-to-end method for referring image segmentation by aligning ’linguistic relationship’ with ’visual relationships’. This method does not rely on external syntax parser for expression parsing. In this paper, the expression is adaptively and structurally parsed into three components: ’subject’, ’object’, and ’linguistic relationship’ by the Semantic Component Parser (SCP) in a learnable manner. Instances Activation Map Module (IAM) locates multiple visual instances based on the subject and object. In addition, the Relationship Based Visual Localization Module (RBVL) firstly enables each instance of the image to learn global knowledge, then decodes the visual relationships between these visual instances, and finally aligns the visual relationships with the linguistic relationships to further accurately locate the target object. The experimental results show that the proposed method improves performance by 4– 9% compared with baseline method on multiple referring image segmentation datasets. [ABSTRACT FROM AUTHOR]

In the modern world, structured and semi-structured knowledge bases hold a considerable amount of data. There-fore, people who are familiar with formal query languages should not be the only ones who can efficiently and clearly query them. Semantic Parsing (SP) is converting natural language utterances into formal meaning representations. The paper suggests a model for SP that uses a novel method of utilizing the Semi-Supervised Generative Adversarial Network (SS-GAN) to enhance the classifier performance. The proposed SS-GAN extends the fine-tuning of word embedding architectures using unlabeled examples in a generative adversarial environment. We provide a regularization strategy for addressing the mode missing problem and unstable training in SS-GAN. The main viewpoint is to use the extracted feature vectors from the discriminator. Hence, the generator produces outputs by aiding the discriminator's learned features. A reconstruction loss is added to the loss function of the SS-GAN to drive the genera-tor to reconstruct outputs from the discriminator's features, hence steering the generator toward actual data configurations. The proposed reconstruction loss improves the performance of SS-GAN, produces high-quality outputs, and may be combined with other regularization loss functions to improve the performance of diverse GANs. We employ BERT word embedding for our model, which can be included in a downstream task and fine-tuned as a model, while the pre-trained BERT model can capture various linguistic properties. We examine the suggested model using the WikiSQL and SparC datasets, and the analysis findings reveal our model outperforms its rivals. The findings from our experiments indicate that the need for labeled samples can be minimized, down to as few as 100 instances, while still achieving commendable classification outcomes. [ABSTRACT FROM AUTHOR]

Copyright of Journal of National University of Defense Technology / Guofang Keji Daxue Xuebao is the property of NUDT Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Existing multi-turn Text-to-SQL approaches, mainly use data in a randomized order when training the model, ignoring the rich structural information contained in the dialog and schema. In this paper, we propose to use curriculum learning (CL) to better leverage the curriculum structure of schema, query, and dialog for multi-turn question-query pairs. We design a model-agnostic framework named Schema Enhanced Hybrid Curriculum Learning (SE-HCL) for multi-turn Text-to-SQL to help the models gain a full contextual semantic understanding. Concretely, We measure the difficulty of the data from both a structural and model perspective. In terms of data structure, we mainly consider the turns of the question and the complexity of the schema and SQL query. Accordingly, we designed a data course module to dynamically adjust the difficulty of the data based on the convergence of the model and the schema enhancement method we designed. In terms of the model, we propose a scoring module that will judge the difficulty of a problem based on whether the model could solve the question effectively. Finally, we will consider both aspects and design a hybrid curriculum to determine the flow of model training. Our experiments show that our proposed method improves SQL-generated performance over previous state-of-the-art models on SparC and CoSQL, especially for hard and long-turn questions.

In the information age, semantic parsing technology drives efficiency improvement and accelerates the process of intelligence. However, it faces complex understanding, data inflation, inappropriate evaluation, and difficult application of advanced large models. This study analyses the current challenges and looks forward to the development trend of the technology. Specific approaches include: this study adopts a systematic review method and strictly follows the PRISMA framework, deeply analyzes the key ideas, methods, problems, and solutions of traditional and neural network methods, and explores the model performance, API application, dataset, and evaluation mechanism. Through literature analysis, the technology is classified according to its application scenarios. Then, the practical application contributions are summarized, current limitations such as data size, model performance, and resource requirements are analyzed, and future directions such as dataset expansion, real-time performance enhancement, and industrial applications are envisioned. The results of the study show significant advances in semantic parsing technology with far-reaching impacts. Traditional and neural network methods complement each other to promote theoretical and practical innovation. In the future, with the continuous progress and in-depth application of machine learning technology, semantic parsing technology needs to further deepen the research on logical reasoning and evaluation, to better cope with technical challenges and lead the new development of natural language processing and AI.

Generating SPARQL queries from natural language questions is challenging in Knowledge Base Question Answering (KBQA) systems. The current state-of-the-art models heavily rely on fine-tuning pretrained models such as T5. However, these methods still encounter critical issues such as triple-flip errors (e.g., (subject, relation, object) is predicted as (object, relation, subject)). To address this limitation, we introduce TSET (Triplet Structure Enhanced T5), a model with a novel pretraining stage positioned between the initial T5 pretraining and the fine-tuning for the Text-to-SPARQL task. In this intermediary stage, we introduce a new objective called Triplet Structure Correction (TSC) to train the model on a SPARQL corpus derived from Wikidata. This objective aims to deepen the model's understanding of the order of triplets. After this specialized pretraining, the model undergoes fine-tuning for SPARQL query generation, augmenting its query-generation capabilities. We also propose a method named "semantic transformation" to fortify the model's grasp of SPARQL syntax and semantics without compromising the pre-trained weights of T5. Experimental results demonstrate that our proposed TSET outperforms existing methods on three well-established KBQA datasets: LC-QuAD 2.0, QALD-9 plus, and QALD-10, establishing a new state-of-the-art performance (95.0% F1 and 93.1% QM on LC-QuAD 2.0, 75.85% F1 and 61.76% QM on QALD-9 plus, 51.37% F1 and 40.05% QM on QALD-10). [ABSTRACT FROM AUTHOR]

Information retrieval from databases is challenging for a non-SQL-domain expert. Some previous studies have provided solutions for translating the natural language to SQL instruction, aiming to access the information in the database directly. However, most solutions are in English Natural Language. In addition, the accuracies of the existing works still need to be improved. This work presents a mechanism called SV2-SQL, based on the pre-trained BERT. The proposed SV2-SQL mainly consists of multiple deep-learning models, including select-where slot filling model (SWSF-model), value extraction model (VE-model), and verification (V-model). The SWSF-model handles the classification tasks for those fields that appear in the “Select” and “Where” clauses, and the VE-model extracts the values for the “Where” clause from the input. The V-model sorts out the unwanted candidates from two previous models and leaves only the ones with the highest possibility. The proposed SV2-SQL also includes an algorithm for the inference process and allows the three models to be cooperative. Experimental results show that the proposed SV2-SQL outperforms the existing studies in terms of precision, accuracy, and recall. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Text-to-GraphQL (Text2GraphQL) is a task that converts the user's questions into Graph + QL (Query Language) when a graph database is given. That is a task of semantic parsing that transforms natural language problems into logical expressions, which will bring more efficient direct communication between humans and machines. The existing related work mainly focuses on Text-to-SQL tasks, and there is no available semantic parsing method and data set for the graph database. In order to fill the gaps in this field to serve the medical Human–Robot Interactions (HRI) better, we propose this task and a pipeline solution for the Text2GraphQL task. This solution uses the Adapter pre-trained by "the linking of GraphQL schemas and the corresponding utterances" as an external knowledge introduction plug-in. By inserting the Adapter into the language model, the mapping between logical language and natural language can be introduced faster and more directly to better realize the end-to-end human–machine language translation task. In the study, the proposed Text2GraphQL task model is mainly constructed based on an improved pipeline composed of a Language Model, Pre-trained Adapter plug-in, and Pointer Network. This enables the model to copy objects' tokens from utterances, generate corresponding GraphQL statements for graph database retrieval, and builds an adjustment mechanism to improve the final output. And the experiments have proved that our proposed method has certain competitiveness on the counterpart datasets (Spider, ATIS, GeoQuery, and 39.net) converted from the Text2SQL task, and the proposed method is also practical in medical scenarios. [ABSTRACT FROM AUTHOR]

In recent years, question answering on knowledge bases (KBQA) has emerged as a promising approach for providing unified, user-friendly access to knowledge bases. Nevertheless, existing KBQA systems struggle to answer spatial-related questions, prompting the introduction of geographic knowledge ba se question answering (GeoKBQA) to address such challenges. Current GeoKBQA systems face three primary issues: (1) the limited scale of questions, restricting the effective application of neural networks; (2) reliance on rule-based approaches dependent on predefined templates, resulting in coverage and scalability challenges; and (3) the assumption of the availability of a golden entity, limiting the practicality of GeoKBQA systems. In this work, we aim to address these three critical issues to develop a practical GeoKBQA system. We construct a large-scale, high-quality GeoKBQA dataset and link mentions in the questions to entities in OpenStreetMap using an end-to-end entity-linking method. Additionally, we develop a query generator that translates natural language questions, along with the entities predicted by entity linking into corresponding GeoSPARQL queries. To the best of our knowledge, this work presents the first purely neural-based GeoKBQA system with potential for real-world application. [ABSTRACT FROM AUTHOR]

Existing text-to-SQL semantic parsers are typically designed for particular settings such as handling queries that span multiple tables, domains, or turns which makes them ineffective when applied to different settings. We present UniSAr (Unified Structure-Aware Autoregressive Language Model), which benefits from directly using an off-the-shelf language model architecture and demonstrates consistently high performance under different settings. Specifically, UniSAr extends existing autoregressive language models to incorporate two non-invasive extensions to make them structure-aware: (1) adding structure mark to encode database schema, conversation context, and their relationships; (2) constrained decoding to decode well-structured SQL for a given database schema. On seven well-known text-to-SQL datasets covering multi-domain, multi-table, and multi-turn, UniSAr demonstrates highly comparable or better performance to the most advanced specifically-designed text-to-SQL models. [ABSTRACT FROM AUTHOR]

This paper aims to introduce the innovative work carried out in the Horizon 2020 DECODER project – acronym for “DEveloper COmpanion for Documented and annotatEd code Reference” – (Grant Agreement no. 824231) by linking the fields of natural language processing (NLP) and software engineering. The project as a whole addresses the development of a framework, namely the Persistent Knowledge Monitor (PKM), that acts as a central infrastructure to store, access, and trace all the data, information and knowledge related to a given software or ecosystem. This meta-model defines the knowledge base that can be queried and analysed by all the tools integrated and developed in DECODER. Besides, the DECODER project offers a friendly user interface where each of the predefined three roles (i.e., developers, maintainers and reviewers) can access and query the PKM with their personal accounts. The paper focuses on the NLP tools developed and integrated in the PKM, namely the deep learning models developed to perform variable misuse, code summarisation and semantic parsing. These were developed under a common work package – “Activities for the developer” – intended to precisely target developers, who can perform tasks such as detection of bugs, automatic generation of documentation for source code and generation of code snippets from natural languages instructions, among the multiple functionalities that DECODER offers. These tools assist and help the developers in the daily work, by increasing their productivity and avoiding loss of time in tedious tasks such as manual bug detection. Training and validation were conducted for four use cases in Java, C and C++ programming languages in order to evaluate the performance, suitability, usability, etc. of the developed tools.

Featured Application: Hierarchical clause annotation could be applied in many downstream tasks of natural language processing, including abstract meaning representation parsing, semantic dependency parsing, text summarization, argument mining, information extraction, question answering, machine translation, etc. Most natural-language-processing (NLP) tasks suffer performance degradation when encountering long complex sentences, such as semantic parsing, syntactic parsing, machine translation, and text summarization. Previous works addressed the issue with the intuition of decomposing complex sentences and linking simple ones, such as rhetorical-structure-theory (RST)-style discourse parsing, split-and-rephrase (SPRP), text simplification (TS), simple sentence decomposition (SSD), etc. However, these works are not applicable for semantic parsing such as abstract meaning representation (AMR) parsing and semantic dependency parsing due to misalignments with semantic relations and unavailabilities to preserve the original semantics. Following the same intuition and avoiding the deficiencies of previous works, we propose a novel framework, hierarchical clause annotation (HCA), for capturing clausal structures of complex sentences, based on the linguistic research of clause hierarchy. With the HCA framework, we annotated a large HCA corpus to explore the potentialities of integrating HCA structural features into semantic parsing with complex sentences. Moreover, we decomposed HCA into two subtasks, i.e., clause segmentation and clause parsing, and provide neural baseline models for more-silver annotations. In evaluating the proposed models on our manually annotated HCA dataset, the performances of clause segmentation and parsing resulted in 91.3% F1-scores and 88.5% Parseval scores, respectively. Due to the same model architectures employed, the performance differences of the clause/discourse segmentation and parsing subtasks was reflected in our HCA corpus and compared discourse corpora, where our sentences contained more segment units and fewer interrelations than those in the compared corpora. [ABSTRACT FROM AUTHOR]

Text-to-SQL is the task of translating a natural language query into a structured query language. Existing text-to-SQL approaches focus on improving the model' s architecture while ignoring the relationship between queries and table schemas and the differences in difficulty between examples in the dataset. To tackle these challenges, a twostage curriculum learning framework for text-to-SQL (TSCL-SQL) is proposed in this paper. To exploit the relationship between the queries and the table schemas, a schema identification pre-training task is proposed to make the model choose the correct table schema from a set of candidates for a specific query. To leverage the differences in difficulty between examples, curriculum learning is applied to the text-to-SQL task, accompanied by an automatic curriculum learning solution, including a difficulty scorer and a training scheduler. Experiments show that the framework proposed in this paper is effective. [ABSTRACT FROM AUTHOR]

Moving objects databases (MODs) have been extensively studied due to their wide variety of applications including traffic management, tourist service and mobile commerce. However, queries in natural languages are still not supported in MODs. Since most users are not familiar with structured query languages, it is essentially important to bridge the gap between natural languages and the underlying MODs system commands. Motivated by this, we design a natural language interface for moving objects, named NALMO. In general, we use semantic parsing in combination with a location knowledge base and domain-specific rules to interpret natural language queries. We design a corpus of moving objects queries for model training, which is later used to determine the query type. Extracted entities from parsing are mapped through deterministic rules to perform query composition. NALMO is able to well translate moving objects queries into structured (executable) languages. We support five kinds of queries including time interval queries, range queries, nearest neighbor queries, trajectory similarity queries and join queries. We develop the system in a prototype system SECONDO and evaluate our approach using 280 natural language queries extracted from popular conference and journal papers in the domain of moving objects. Four volunteers give the system satisfaction and related suggestions through three rounds of independent tests. Experimental results show that (i) NALMO achieves accuracy and precision 96.8% and 81.1%, respectively, (ii) the average time cost of translating a query is 1.49s, and (iii) the average satisfaction is 95.5%. [ABSTRACT FROM AUTHOR]

Semantic parsing is a challenging task mapping a natural language utterance to machine-understandable information representation. Recently, approaches using neural machine translation (NMT) have achieved many promising results, especially the Transformer. However, the typical drawback of adapting the vanilla Transformer to semantic parsing is that it does not consider the phrase in expressing the information of sentences while phrases play an important role in constructing the sentence meaning. Therefore, we propose an architecture, PhraseTransformer, that is capable of a more detailed meaning representation by learning the phrase dependencies in the sentence. The main idea is to incorporate Long Short-Term Memory into the Self-Attention mechanism of the original Transformer to capture the local context of a word. Experimental results show that our proposed model performs better than the original Transformer in terms of understanding sentences structure as well as logical representation and raises the model local context-awareness without any support from external tree information. Besides, although the recurrent architecture is integrated, the number of sequential operations of the PhraseTransformer is still O (1) similar to the original Transformer. Our proposed model achieves strong competitive performance on Geo and MSParS datasets, and leads to SOTA performance on the Atis dataset for methods using neural networks. In addition, to prove the generalization of our proposed model, we also conduct extensive experiments on three translation datasets IWLST14 German-English, IWSLT15 Vietnamese-English, WMT14 English-German, and show significant improvement. Our code is available at https://github.com/phuongnm94/PhraseTransformer.git. [ABSTRACT FROM AUTHOR]

Text-to-graphics systems encompass three types of tools: text-to-picture, text-to-scene and text-to-animation. They are an artificial intelligence application wherein users can create 2D and 3D scenes or animations and recently immersive environments from natural language. These complex tasks require the collaboration of various fields, such as natural language processing, computational linguistics and computer graphics. Text-to-animation systems have received more interest than their counterparts, and have been developed for various domains, including theatrical pre-production, education or training. In this survey we focus on text-to-animation systems, discussing their requirements, challenges and proposing solutions, and investigate the natural language understanding approaches adopted in previous research works to solve the challenge of animation generation. We review text-to-animation systems developed over the period 2001-2021, and investigate their recent trends in order to paint the current landscape of the field.