Language Question Research Articles

RGISQL: Integrating Refined Grammatical Information into Relational Graph Neural Network for Text-to-SQL Task

The text-to-SQL task aims to convert natural language questions into corresponding SQL queries based on a given database schema. Previous models that rely on graph neural networks often struggle to accurately capture the complex grammatical relationships present in these questions, leading to poor performance when generating queries for longer requests. To address these challenges, we propose RGISQL, which integrates refined grammatical information extracted from the question and employs segmentation processing to effectively manage long queries. Additionally, RGISQL minimizes the complexity of edge embeddings by reducing the coupling within graph neural networks. By utilizing grammatical dependency trees, RGISQL is better equipped to capture the inherent structure and grammatical rules of questions. This refined grammatical information offers additional contextual and semantic cues for the model, thereby enhancing both its generalizability and interpretability. Furthermore, we dynamically assess the importance of different edges based on the graph structure, which helps reduce the coupling of edge embeddings and further improves the model’s performance. Multiple sets of experiments conducted on the Spider and Spider-Syn datasets demonstrate that RGISQL outperforms other baselines, achieving the best results in both datasets.

Investigating Open Source LLMs to Retrofit Competency Questions in Ontology Engineering

Competency Questions (CQs) are essential in ontology engineering; they express an ontology's functional requirements as natural language questions, offer crucial insights into an ontology's scope and are pivotal for various tasks, e.g. ontology reuse, testing, requirement specification, and pattern definition. Despite their importance, the practice of publishing CQs alongside ontological artefacts is not commonly adopted. We propose an approach based on Generative AI, specifically Large Language Models (LLMs) for retrofitting CQs from existing ontologies and we investigate how open LLMs (i.e. Llama-2-70b, Mistral 7B and Flan-T5-xl) perform in generating CQs for existing ontologies. We compare these results with our previous efforts using closed-source LLMs and we reflect on the results.

Dynamic multi teacher knowledge distillation for semantic parsing in KBQA

Knowledge base question answering (KBQA) is an important task of extracting answers from a knowledge base by analyzing natural language questions. Semantic parsing methods convert natural language questions into executable logical forms to obtain answers on the knowledge base. Conventional approaches often prioritize singular logical forms, overlooking the distinct strengths inherent in various logical frameworks for problem solving. Recognizing that different logical forms may excel in addressing specific types of questions, our aim is to harness these strengths. By integrating the strengths of different logical forms, we expect to achieve more comprehensive and effective semantic parsing solutions. In our paper, we propose a Dynamic Multi Teacher Knowledge Distillation for Semantic Parsing (DMTKD-SP). DMTKD-SP leverages a collection of teacher models, each mastering a unique logical form, to collaboratively guide a student model so that knowledge from different logical forms can be transferred into the student model. To achieve this, we employ a confidence-based weight assignment module to dynamically assign weights for each teacher model. Furthermore, we introduce a self-distillation mechanism to mitigate the confusion caused by simultaneous learning from multiple teachers. We evaluate DMTKD-SP across variants of the KQA Pro dataset, demonstrating an accuracy improvement of 0.35% on five types of questions, with a notable 0.75% improvement for Count questions.

Robust visual question answering via polarity enhancement and contrast

The Visual Question Answering (VQA) task is an important research direction in the field of artificial intelligence, which requires a model that can simultaneously understand visual images and natural language questions, and answer questions related to images. Recent studies have shown that many Visual Question Answering models rely on statistically regular correlations between questions and answers, which in turn weakens the correlation between visual content and textual information. In this work, we propose an unbiased Visual Question Answering method to solve language priors from the perspective of strengthening the contrast between the correct answer and the positive and negative predictions. We design a new model consisting of two modules with different roles. We input the image and the question corresponding to it into the Answer Visual Attention Modules to generate positive prediction output, and then use a Dual Channels Joint Module to generate negative prediction output with great linguistic prior knowledge. Finally, we input the positive and negative predictions together with the correct answer to our newly designed loss function for training. Our method achieves high performance (61.24%) on the VQA-CP v2 dataset. In addition, most existing debiasing methods improve performance on VQA-CP v2 dataset at the cost of reducing performance on VQA v2 dataset, while our method not only does not reduce the accuracy on VQA v2 dataset. Instead, it improves performance on both datasets mentioned above.

Harnessing Representative Spatial-Temporal Information for Video Question Answering

Video question answering, aiming to answer a natural language question related to the given video, has become prevalent in the past few years. Although remarkable improvements have been obtained, it is still exposed to the challenge of insufficient comprehension of video content. To this end, we propose a spatial-temporal representative visual exploitation network for video question answering, which enhances the understanding of the video by merely summarizing representative visual information. In order to explore representative object information, we advance adaptive attention based on uncertainty estimation. At the same time, to capture representative frame-level and clip-level visual information, we structure a much more compact set of representations iteratively in an expectation-maximization manner to deprecate noisy information. Both the quantitative and qualitative results on NExT-QA, TGIF-QA, MSRVTT-QA, and MSVD-QA datasets demonstrate the superiority of our model over several state-of-the-art approaches.

Language matters: what can social workers learn from the transgender community?

ABSTRACT Questions of language and its contribution to constructing and preserving the social order have gradually entered social work research. This paper seeks to add to this professional scholarship by examining the concrete impact of language usage on real persons in everyday interactions. It is based on an interview study with eleven members of the transgender community in Israel and anchored in the feminist social work perspective. Transgender individuals challenge seemingly natural social conventions and do not necessarily conform to expected coherency between biology and gender. Since most Hebrew grammatical forms make clear distinctions based on gender, these individuals often lack adequate means for conducting a dialogue consistent with their sense of self. The interviewees’ descriptions highlight the pivotal role Hebrew plays in realizing their identity, thus providing a better opportunity for enhancing our understanding of the strategic power of language than the discourse of members of predominant social groups. These findings have potential implications for social work teaching and practice, especially in relation to undoing injustice.

Zero-Shot Prompting Strategies for Table Question Answering with a Low-Resource Language

This work explores the application of zero-shot prompting strategies for table question answering (TQA) in Portuguese, focusing specifically on the Text2SQL task. This task involves translating questions posed in natural language into Structured Query Language (SQL) queries, which can be executed against a database to answer the original question. Given the popularity of relational databases across various domains, advancements in this field can substantially impact the accessibility and democratization of data as simpler and more intuitive interfaces for database interaction are developed. Despite this significant potential, progress in developing Portuguese TQA solutions remains limited. The proposed approach leverages Large Language Models (LLMs)—specifically the GPT-3.5 and GPT-4 models—through zero-shot prompting. The primary objectives are to assess the effectiveness of such LLMs in this task and to identify the most suitable prompt styles. These are evaluated using a Portuguese translation of the popular Spider Text2SQL benchmark. Results reveal that the proposed approach can generate adequate SQL queries to answer Portuguese language questions about various databases, mainly when using GPT-4. The findings suggest that including schema information and database content in the prompts is critical for satisfactory outcomes. Doi: 10.28991/ESJ-2024-08-05-020 Full Text: PDF

AI in the L2 Classroom: Serving Language Educators through Professional Development

The spread of generative AI has been praised and criticized for engendering new possibilities and limitations for language education. While educators have praised AI’s ability to serve as a conversation partner, generate novel ideas for lesson plans, and offer tailored feedback, many instructors and scholars have voiced concerns related to AI’s biases and its impact on student learning and academic integrity. Responding to a need for further training and dialogue about AI, members of the Davis Language Center organized a professional development event in which instructors, students, and instructional technologists shared their perspectives and strategies for AI-mediated language education. The event also included guided practice on using these tools for pedagogical purposes, including writing effective prompts, interacting with AI tools, and engaging in an iterative, reflective process. Through our planning process, we discovered that balancing scheduled asynchronous tasks with focused synchronous check-ins was crucial for ensuring accountability, clear communication, and timely progress, ultimately helping us coordinate and achieve our event planning goals effectively. We report on insights from organizing and participating in the event, highlighting several advantages of using AI in language education, critical issues, and questions for further inquiry. Leveraging lessons learned at this event, we offer suggestions for coordinating trainings about AI-enhanced language education.

Uniqorn: Unified question answering over RDF knowledge graphs and natural language text

Question answering over RDF data like knowledge graphs has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries. Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone. Conversely, the IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora, or individual sources, in a unified framework. Our method, called Uniqorn, builds a context graph on-the-fly, by retrieving question-relevant evidences from the RDF data and/or a text corpus, using fine-tuned BERT models. The resulting graph typically contains all question-relevant evidences but also a lot of noise. Uniqorn copes with this input by a graph algorithm for Group Steiner Trees, that identifies the best answer candidates in the context graph. Experimental results on several benchmarks of complex questions with multiple entities and relations, show that Uniqorn significantly outperforms state-of-the-art methods for heterogeneous QA – in a full training mode, as well as in zero-shot settings. The graph-based methodology provides user-interpretable evidence for the complete answering process.

Toward Subgraph-Guided Knowledge Graph Question Generation With Graph Neural Networks.

Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers. Previous works mostly focus on a simple setting that is to generate questions from a single KG triple. In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers. In addition, most previous works built on either RNN- or Transformer-based models to encode a linearized KG subgraph, which totally discards the explicit structure information of a KG subgraph. To address this issue, we propose to apply a bidirectional Graph2Seq model to encode the KG subgraph. Furthermore, we enhance our RNN decoder with a node-level copying mechanism to allow direct copying of node attributes from the KG subgraph to the output question. Both automatic and human evaluation results demonstrate that our model achieves new state-of-the-art scores, outperforming existing methods by a significant margin on two QG benchmarks. Experimental results also show that our QG model can consistently benefit the question-answering (QA) task as a means of data augmentation.

SciScribe: Automating and contextualizing literature reviews in cardiac surgery

BackgroundThe task of writing structured content reviews and guidelines has grown stronger and more complex. We propose to go beyond search tools and toward curation tools by automating time-consuming and repetitive steps of extracting and organizing information. MethodsSciScribe is built as an extension of IBM's Deep Search platform, which provides document processing and search capabilities. This platform was used to ingest and search full-content publications from PubMed Central (PMC) and official, structured records from the ClinicalTrials and OpenPayments databases. Author names and NCT numbers, mentioned within the publications, were used to link publications to these official records as context. Search strategies involve traditional keyword-based search as well as natural language question and answering via large language models (LLMs). ResultsSciScribe is a web-based tool that helps accelerate literature reviews through key features: (1) accumulating a personal collection from publication sources, such as PMC or other sources; (2) incorporating contextual information from external databases into the presented papers, promoting a more informed assessment by readers; (3) semantic questioning and answering of documents to quickly assess relevance and hierarchical organization; and (4) semantic question answering for each document within a collection, collated into tables. ConclusionsEmergent language processing techniques are opening new avenues to accelerate and enhance the literature review process, for which we have demonstrated a use case implementation in cardiac surgery. SciScribe automates and accelerates this process, mitigates errors associated with repetition and fatigue, and contextualizes results by linking relevant external data sources instantaneously.

Toward an Explainable Large Language Model for the Automatic Identification of the Drug-Induced Liver Injury Literature.

Drug-induced liver injury (DILI) stands as a significant concern in drug safety, representing the primary cause of acute liver failure. Identifying the scientific literature related to DILI is crucial for monitoring, investigating, and conducting meta-analyses of drug safety issues. Given the intricate and often obscure nature of drug interactions, simple keyword searching can be insufficient for the exhaustive retrieval of the DILI-relevant literature. Manual curation of DILI-related publications demands pharmaceutical expertise and is susceptible to errors, severely limiting throughput. Despite numerous efforts utilizing cutting-edge natural language processing and deep learning techniques to automatically identify the DILI-related literature, their performance remains suboptimal for real-world applications in clinical research and regulatory contexts. In the past year, large language models (LLMs) such as ChatGPT and its open-source counterpart LLaMA have achieved groundbreaking progress in natural language understanding and question answering, paving the way for the automated, high-throughput identification of the DILI-related literature and subsequent analysis. Leveraging a large-scale public dataset comprising 14 203 training publications from the CAMDA 2022 literature AI challenge, we have developed what we believe to be the first LLM specialized in DILI analysis based on LLaMA-2. In comparison with other smaller language models such as BERT, GPT, and their variants, LLaMA-2 exhibits an enhanced out-of-fold accuracy of 97.19% and area under the ROC curve of 0.9947 using 3-fold cross-validation on the training set. Despite LLMs' initial design for dialogue systems, our study illustrates their successful adaptation into accurate classifiers for automated identification of the DILI-related literature from vast collections of documents. This work is a step toward unleashing the potential of LLMs in the context of regulatory science and facilitating the regulatory review process.

Mohandas Gandhi and the uses of Esperanto

Abstract In the vast literature that deals with Mohandas Gandhi, very little attention has been paid to his opinions on questions of language. This essay studies Gandhi’s use of the international auxiliary language, Esperanto, as a negative example of a way to find a common language. Gandhi was willing and able to collaborate with Esperantists. And yet, Esperanto was repeatedly invoked by Gandhi in order to attack it as an utopian ideal irrelevant in Indian contexts. Gandhi’s arguments against Esperanto established the rejection of an internationalism of which he perceived Esperanto to be a part. His rejection of Esperanto as an artificially constructed language is integral to his failure to acknowledge Hindi’s artificial construction and imposition in South Indian contexts. The Gandhi-led All Indian Education Conference at Wardha (1937) is situated in this essay, therefore, within a wider context of linguistic parochialisms.

GS-CBR-KBQA: Graph-structured case-based reasoning for knowledge base question answering

Knowledge Base Question Answering (KBQA) task is an important research direction in natural language processing. Due to the flexibility and ambiguity of natural language, users’ questions often have more complex query types and richer semantic information. To address this issue, this paper proposes the GS-CBR-KBQA model, a Case-Based Reasoning model tailored for KBQA to improve the semantic parsing accuracy and interpretability of natural language questions. The model integrates Knowledge-oriented Programming Language (KoPL) reasoning graphs with query information, employing a Graph Auto-Encoder and the RoBERTa pretrained language model for a highly effective case retrieval. This integration leads to a more robust knowledge retrieval and application approach, particularly innovative in capturing the relationships within KoPL graphs. The model addresses explicitly complex questions such as multi-hop reasoning and questions involving intricate entity relationships. Finally, our extensive experiments show that the model performs excellently in accuracy and F1 metrics on benchmark datasets such as WebQSP and ComplexWebQuestions, particularly in complex question-answering. The code of our model is available at https://anonymous.4open.science/r/GS-CBR-KBQA.

Natural Language Processing Pretraining Language Model for Computer Intelligent Recognition Technology

Computer intelligent recognition technology refers to the use of computer vision, Natural Language Processing (NLP), machine learning and other technologies to enable computers to recognize, analyze, understand and answer human language and behavior. The common applications of computer intelligent recognition technology include image recognition, NLP, face recognition, target tracking, and other fields. NLP is a field of computer science, which involves the interaction between computers and natural languages. NLP technology can be used to process, analyze and generate natural language data, such as text, voice and image. Common NLP technology applications include language translation, emotion analysis, text classification, speech recognition and question answering system. Language model is a machine learning model, which uses a large number of text data for training to learn language patterns and relationships in text data. Although the language model has made great progress in the past few years, it still faces some challenges, including: poor semantic understanding, confusion in multilingual processing, slow language processing and other shortcomings. Therefore, in order to optimize these shortcomings, this article would study the pre-training language model based on NLP technology, which aimed at using NLP technology to optimize and improve the performance of the language model, thus optimizing the computer intelligent recognition technology. The model had a higher language understanding ability and more accurate prediction ability. In addition, the model could learn language rules and structures by using a large number of corpus, so as to better understand natural language. Through experiments, it could be known that the data size and total computing time of the traditional Generative Pretrained Transformer-2 (GPT-2) language model were 10 GB and 97 hours respectively. The data size and total computing time of BERT (Bidirectional Encoder Representations from Transformer) were 12 GB and 86 hours respectively. The data size and total computing time of the pre-training language model based on NLP were 18 GB and 71 hours respectively. Obviously, the pre-training language model based on NLP had a larger data size and shorter computing time. The experimental results showed that the NLP technology could better optimize the language model and effectively improve its various capabilities. This article opened up a new development direction for computer intelligent recognition technology and provided excellent technical support for the development of language models.

AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models

With the growing significance of data analysis, several studies aim to provide precise answers to users' natural language questions from tables, a task referred to as tabular question answering (TQA). The state-of-the-art TQA approaches are limited to handling only single-table questions. However, real-world TQA problems are inherently complex and frequently involve multiple tables, which poses challenges in directly extending single-table TQA designs to handle multiple tables, primarily due to the limited extensibility of the majority of single-table TQA methods. This paper proposes AutoTQA, a novel Auto nomous T abular Q uestion A nswering framework that employs multi-agent large language models (LLMs) across multiple tables from various systems (e.g., TiDB, BigQuery). AutoTQA comprises five agents: the User , responsible for receiving the user's natural language inquiry; the Planner , tasked with creating an execution plan for the user's inquiry; the Engineer , responsible for executing the plan step-by-step; the Executor , provides various execution environments (e.g., text-to-SQL) to fulfill specific tasks assigned by the Engineer ; and the Critic , responsible for judging whether to complete the user's natural language inquiry and identifying gaps between the current results and initial tasks. To facilitate the interaction between different agents, we have also devised agent scheduling algorithms. Furthermore, we have developed LinguFlow, an open-source, low-code visual programming tool, to quickly build and debug LLM-based applications, and to accelerate the creation of various external tools and execution environments. We also implemented a series of data connectors, which allows AutoTQA to access various tables from multiple systems. Extensive experiments show that AutoTQA delivers outstanding performance on four representative datasets.

Robust Visual Question Answering: Datasets, Methods, and Future Challenges.

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often tend to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Third, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints.

English and/in Africa: reflections on the language question, Afropolitanism, and linguistic orientation six decades after the ‘African Writers Conference’

English and/in Africa: reflections on the language question, Afropolitanism, and linguistic orientation six decades after the ‘African Writers Conference’

A crossword solving system based on Monte Carlo tree search

Although the development of AI in games is remarkable, intelligent machines still lag behind humans in games that require the ability of language understanding. In this paper, we focus on the crossword puzzle resolution task. Solving crossword puzzles is a challenging task since it requires the ability to answer natural language questions with knowledge and the ability to execute a search over possible answers to find an optimal set of solutions for the grid. Previous solutions are devoted to exploiting heuristic strategies in search to find solutions while having limited ability to explore the search space. We build a comprehensive system for crossword puzzle resolution based on Monte Carlo Tree Search (MCTS). As far as we know, we are the first to model the crossword puzzle resolution problem as a Markov Decision Process and apply the MCTS to solve it. We construct a dataset for crossword puzzle resolution based on daily puzzles from The New York Times with detailed specifications of both the puzzle and clue database selection. Our method achieves state-of-the-art performance on the dataset. The code of the system and experiments in this paper is publicly available: https://www.github.com/lhlclhl/CP.

NLP-based smart decision making for business and academics

Natural Language Processing (NLP) systems enable machines to understand, interpret, and generate human-like language, bridging the gap between human communication and computer understanding. Natural Language Interface to Databases (NLIDB) and Natural Language Interface to Visualization (NLIV) systems are designed to enable non-technical users to retrieve and visualize data through natural language queries. However, these systems often face challenges in handling complex correlation and analytical questions, limiting their effectiveness for comprehensive data analysis. Additionally, current Business Intelligence (BI) tools also struggle with understanding the context and semantics of complex questions, further hindering their usability for strategic decision-making. Also, when building these models for generating the queries from natural language, the system handles only the semantic parsing issues as each column header is being changed manually to their normal names by all existing models which is time-consuming, tedious, and subjective.Recent studies reflect the need for attention to context, semantics, and especially ambiguities in dealing with natural language questions. To address this problem, the proposed architecture focuses on understanding the context, correlation-based semantic analysis, and removal of ambiguities using a novel approach. An Enhanced Longest Common Subsequence (ELCS) is suggested where existing LCS is modified with a memorization component for mapping the natural language question tokens with ambiguous table column headers. This can speed up the overall process as human intervention is not required to manually change the column headers. The same is evidenced by carrying out thorough experimentation and comparative study in terms of precision, recall, and F1 score. By synthesizing the latest advancements and addressing challenges, this paper has proved how NLP can significantly enhance the accuracy and efficiency of information retrieval and visualization, broadening the inclusivity and usability of NLIDB, NLIV, and BI systems.