Language Interface Research Articles

Batched sparse and mixed-precision linear algebra interface for efficient use of GPU hardware accelerators in scientific applications

Batched Sparse Linear Algebra has become an emergent processing mode on modern hardware accelerators based on Graphics Processing Units (GPUs) developed over the years to serve as the main compute devices in the largest computing clusters and supercomputers. We propose a set solver interface designs for batched sparse numerical solvers on these hardware accelerators. We motivate our specific designs by both their use in scientific applications of national importance and also by the possibility of implementing them in an efficient and portable manner with multiple options for vendor-specific optimizations. We present the C language interface calls for the linker-agnostic interchange of functional entry points. We also show how using C++ for the batched solvers simplifies the interface design while giving the user much broader set of opportunities for customization, testing, and debugging. We also cover in our proposals the option of exploiting multiple floating-point arithmetic precisions to directly match the application needs in terms of accuracy. Finally, a selected sample of performance experiments show how our proposed interface can be efficiently implemented to outperform the available alternatives many times over. In the end, we plan for an ongoing evolution of our newly proposed interface standard to keep up with the updates in programming languages, accelerator hardware, and application needs.

A multilingual semantic search chatbot framework

Chatbots are conversational agents which interact with users and simulate a human interaction. Companies use chatbots on their customer-facing sites to enhance user experience by answering questions about their products and directing users to relevant pages on the site. Existing Chatbots which are used for this purpose give responses based on pre-defined FAQs only. In this paper, we propose a framework for a chatbot which combines two approaches - retrieval from a knowledge base consisting of question answer pairs, combined with a natural language search mechanism which can scan through the paragraphs of text information. A feedback-based knowledge base update is implemented which provides continuous improvement in user experience. The framework achieves a result of 81.73 percent answer matching on SQuAD 1.1 and 69.21 percent answer matching on SQuAD 2.0. The framework also performs well on languages such as Spanish (67.32 percent answer match), Russian (61.43 percent answer match), Arabic (51.63 percent answer match) etc. by means of zero shot learning.

Synergizing human expertise and AI efficiency with language model for microscopy operation and automated experiment design * *Notice: This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC0500OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up,

With the advent of large language models (LLMs), in both the open source and proprietary domains, attention is turning to how to exploit such artificial intelligence (AI) systems in assisting complex scientific tasks, such as material synthesis, characterization, analysis and discovery. Here, we explore the utility of LLMs, particularly ChatGPT4, in combination with application program interfaces (APIs) in tasks of experimental design, programming workflows, and data analysis in scanning probe microscopy, using both in-house developed APIs and APIs given by a commercial vendor for instrument control. We find that the LLM can be especially useful in converting ideations of experimental workflows to executable code on microscope APIs. Beyond code generation, we find that the GPT4 is capable of analyzing microscopy images in a generic sense. At the same time, we find that GPT4 suffers from an inability to extend beyond basic analyses for more in-depth technical experimental design. We argue that an LLM specifically fine-tuned for individual scientific domains can potentially be a better language interface for converting scientific ideations from human experts to executable workflows. Such a synergy between human expertise and LLM efficiency in experimentation can open new doors for accelerating scientific research, enabling effective experimental protocols sharing in the scientific community.

A FRAMEWORK FOR CONVERTING SQL QUERIES FROM NATURAL LANGUAGE

The database interface, called the "natural language interface", uses natural language to allow users to access data without the need for SQL queries. Using query language to interact with databases is always a sophisticated issue. Due to this complexity, the client must use the clear reports that are included in some pre-executed programming projects when using information that is already present in database points of confinement. But, users can make it possible for each nonprofessional user to ask questions and provide requirements in natural language, which the computer can then process to produce the appropriate data. This study introduces a system developed using the "Natural Language Interface to Database" (NLIDB). This approach has led to the emergence of "experts" who can detect compound sentences in English and use them in lessons. After parsing the input sentences, the natural language is converted to SQL.

The HR Insight Sidebar Extension for LinkedIn Profile

This paper explores the "HR Insights Sidebar Extension," which enhances LinkedIn profile evaluation through a chatbot, aiding informed decision-making with real-time analysis. AI-driven algorithms extract key information like skills, experience, and endorsements, generating concise summaries to streamline evaluations. Leveraging the OpenAI Assistant API's Information Retrieval and Natural Language Processing, the system extracts data from various file types. Users query the chatbot via a natural language interface, receiving direct answers and saving time. Tools like ChatGPT and Proxy curl improve profile evaluation efficiency and effectiveness for students, researchers, and professionals. Keywords- large language models, GPT-3 summarization, proxy curl, implementation, and integration.

I2R: Intra and inter-modal representation learning for code search

Code search, which locates code snippets in large code repositories based on natural language queries entered by developers, has become increasingly popular in the software development process. It has the potential to improve the efficiency of software developers. Recent studies have demonstrated the effectiveness of using deep learning techniques to represent queries and codes accurately for code search. In specific, pre-trained models of programming languages have recently achieved significant progress in code searching. However, we argue that aligning programming and natural languages are crucial as there are two different modalities. Existing pre-train models based approaches for code search do not effectively consider implicit alignments of representations across modalities (inter-modal representation). Moreover, the existing methods do not take into account the consistency constraint of intra-modal representations, making the model ineffective. As a result, we propose a novel code search method that optimizes both intra-modal and inter-modal representation learning. The alignment of the representation between the two modalities is achieved by introducing contrastive learning. Furthermore, the consistency of intra-modal feature representation is constrained by KL-divergence. Our experimental results confirm the model’s effectiveness on seven different test datasets. This paper proposes a code search method that significantly improves existing methods. Our source code is publicly available on GitHub.1

Investing of Chatbots to Enhance the Library Services

Artificial Intelligence (AI) has become an indispensable tool in our daily lives and is a concept that refers to complex tasks that usually require significant human effort. Chatbots stand out as one of the primary applications of artificial intelligence, aiming to foster an interactive dialogue environment between humans and machines to address inquiries through textual or voice interfaces that simulate human cognition. Libraries can serve as an ideal environment for implementing this technology, where it can deliver advanced information services and streamline repetitive routine tasks typically performed by library staff. The paper discusses the applications of chatbots in automating library services, including reference services, user recommendations, information retrieval, data analysis, and other related processes, and their mechanism of action in processing natural language queries and responding to them accurately. Through a web survey, the study identified eighteen chatbot models that could be implemented in libraries. This survey provided details about these bots, including their type (free or commercial), ownership, release date, operating platforms, and key features. This allows libraries to choose from them. Integrating chatbots into libraries will open new horizons for enhancing their services and improving the user experience. Despite the benefits offered by these chatbots, they face several challenges and concerns regarding their usage, notably data privacy and security, and bias in retrieval. It is expected that in the future, these chatbots will become a fundamental component of providing library services.

Scoring Multi-hop Question Decomposition Using Masked Language Models

Question answering (QA) is a sub-field of Natural Language Processing (NLP) that focuses on developing systems capable of answering natural language queries. Within this domain, multi-hop question answering represents an advanced QA task that requires gathering and reasoning over multiple pieces of information from diverse sources or passages. To handle the complexity of multi-hop questions, question decomposition has been proven to be a valuable approach. This technique involves breaking down complex questions into simpler sub-questions, reducing the complexity of the problem. However, it’s worth noting that existing question decomposition methods often rely on training data, which may not always be readily available for low-resource languages or specialized domains. To address this issue, we propose a novel approach that utilizes pre-trained masked language models to score decomposition candidates in a zero-shot manner. The method involves generating decomposition candidates, scoring them using a pseudo-log likelihood estimation, and ranking them based on their scores. To evaluate the efficacy of the decomposition process, we conducted experiments on two datasets annotated on decomposition in two different languages, Arabic and English. Subsequently, we integrated our approach into a complete QA system and conducted a reading comprehension performance evaluation on the HotpotQA dataset. The obtained results emphasize that while the system exhibited a small drop in performance, it still maintained a significant advance compared to the baseline model. The proposed approach highlights the efficiency of the language model scoring technique in complex reasoning tasks such as multi-hop question decomposition.

APPLICATION OF HYBRID APPROACH FOR WOLAITA LANGUAGE PART OF SPEECH TAGGING

The main purpose of this study is to develop part-of-speech tagger for Wolaita Language using hybrid approach. Part of speech tagger is one of the subtasks in NLP application which is important for other Natural Language Processing (NLP) applications, like parser, machine translator, speech recognizer and search engines. PoST is a process of tagging a corresponding part of speech tag for a word that tag defines how the word is used in a sentence. The PoST for Wolaita language is not enough yet to be used as one vital module in other natural language processing applications. In this study, the development of PoS tagger using hybrid approach that combines HMM and rule based approaches was conducted for Wolaita language. In general HMM model need large data to increase the performance and the rule based model learner rule based on the language features. The HMM tagger, tags the words based on the optimal path for a given sequence of words and transformation based learning (TBL) is a rule based approaches that learns rule directly from the training corpus without expert knowledge. The developed hybrid approach of Wolaita language PoS tagger uses HMM tagger as initial annotators and rule based tagger as a corrector based on fixed threshold values. For implementation and experiment purpose the researcher used python programming and NLTK. For training and testing the models, 1256 sentences or 15,268 words are collected from three different categories (Bible, Social media in Wolaita language (Wogetta FM 96.6 ) and Wolaita language department) and annotated data manually. For tagging purpose 26 PoS tag are identified. From entire corpus, 90% for training and the remaining of entire corpus for testing purpose. The performance of the taggers, are tested by using different experiments. After experiment the researcher found that the performance of HMM, rule based and hybrid taggers shows 88.14%, 93.19% and 94.82% respectively. Generally, hybrid approach showed the better performance to assigning part of speech tag for Wolaita language.

G-VOILA: Gaze-Facilitated Information Querying in Daily Scenarios

Modern information querying systems are progressively incorporating multimodal inputs like vision and audio. However, the integration of gaze --- a modality deeply linked to user intent and increasingly accessible via gaze-tracking wearables --- remains underexplored. This paper introduces a novel gaze-facilitated information querying paradigm, named G-VOILA, which synergizes users' gaze, visual field, and voice-based natural language queries to facilitate a more intuitive querying process. In a user-enactment study involving 21 participants in 3 daily scenarios (p = 21, scene = 3), we revealed the ambiguity in users' query language and a gaze-voice coordination pattern in users' natural query behaviors with G-VOILA. Based on the quantitative and qualitative findings, we developed a design framework for the G-VOILA paradigm, which effectively integrates the gaze data with the in-situ querying context. Then we implemented a G-VOILA proof-of-concept using cutting-edge deep learning techniques. A follow-up user study (p = 16, scene = 2) demonstrates its effectiveness by achieving both higher objective score and subjective score, compared to a baseline without gaze data. We further conducted interviews and provided insights for future gaze-facilitated information querying systems.

Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding

Grounding temporal video segments described in natural language queries effectively and efficiently is a crucial capability needed in vision-and-language fields. In this paper, we deal with the fast video temporal grounding (FVTG) task, aiming at localizing the target segment with high speed and favorable accuracy. Most existing approaches adopt elaborately designed cross-modal interaction modules to improve the grounding performance, which suffer from the test-time bottleneck. Although several common space-based methods enjoy the high-speed merit during inference, they can hardly capture the comprehensive and explicit relations between visual and textual modalities. In this paper, to tackle the dilemma of speed-accuracy tradeoff, we propose a commonsense-aware cross-modal alignment network (C 2 AN), which incorporates commonsense-guided visual and text representations into a complementary common space for fast video temporal grounding. Specifically, the commonsense concepts are explored and exploited by extracting the structural semantic information from a language corpus. Then, a commonsense-aware interaction module is designed to obtain bridged visual and text features by utilizing the learned commonsense concepts. Finally, to maintain the original semantic information of textual queries, a cross-modal complementary common space is optimized to obtain matching scores for performing FVTG. Extensive results on two challenging benchmarks show that our C 2 AN method performs favorably against state-of-the-arts while running at high speed. Our code is available at https://github.com/ZiyueWu59/CCA.

МАТЕМАТИЧЕСКИЕ МОДЕЛИ И ЧИСЛЕННЫЕ МЕТОДЫ В КАРДИОЛОГИИ: СОБСТВЕННЫЙ ОПЫТ

Вackground. In the era of digital transformation in medicine, which is radically changing the way patient information is stored, processed and used, medical professionals need new tools and approaches that can efficiently process and interpret data for fast and accurate decision making. These methods also enable the creation of personalized treatment approaches, taking into account individual patient characteristics and risks. In this article, the authors share their own experience in applying numerical methods in cardiology. Purpose of the study. To develop methods of effective risk assessment of cardiovascular outcomes in different categories of patients. Characteristics of patients and methods of the study. Three variants of outcome prediction were included in the study. The 1st - assessment of the total risk of one-year cardiovascular outcomes after myocardial infarction with ST-segment elevation, the 2nd - assessment of the risk of postinfarction chronic heart failure, the 3rd – assessment of the risk of progressive course of atherosclerosis. Statistical analysis methods included the free cross-platform visual programming system Orange, the SPSS 22.0 package, and the C programming language console. Results and Conclusion. The conducted study has shown that the application of different approaches: regression analysis, machine learning, Excel programming capabilities, C programming language and console interface allows to develop models of cardiovascular outcomes prediction with high accuracy.

Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap

Abstract We present Text-to-OverpassQL, a task designed to facilitate a natural language interface for querying geodata from OpenStreetMap (OSM). The Overpass Query Language (OverpassQL) allows users to formulate complex database queries and is widely adopted in the OSM ecosystem. Generating Overpass queries from natural language input serves multiple use-cases. It enables novice users to utilize OverpassQL without prior knowledge, assists experienced users with crafting advanced queries, and enables tool-augmented large language models to access information stored in the OSM database. In order to assess the performance of current sequence generation models on this task, we propose OverpassNL,1 a dataset of 8,352 queries with corresponding natural language inputs. We further introduce task specific evaluation metrics and ground the evaluation of the Text-to-OverpassQL task by executing the queries against the OSM database. We establish strong baselines by finetuning sequence-to-sequence models and adapting large language models with in-context examples. The detailed evaluation reveals strengths and weaknesses of the considered learning strategies, laying the foundations for further research into the Text-to-OverpassQL task.

Talk2Data: A Natural Language Interface for Exploratory Visual Analysis via Question Decomposition

Through a natural language interface (NLI) for exploratory visual analysis, users can directly “ask” analytical questions about the given tabular data. This process greatly improves user experience and lowers the technical barriers of data analysis. Existing techniques focus on generating a visualization from a concrete question. However, complex questions, requiring multiple data queries and visualizations to answer, are frequently asked in data exploration and analysis, which cannot be easily solved with the existing techniques. To address this issue, in this article, we introduce Talk2Data, a natural language interface for exploratory visual analysis that supports answering complex questions. It leverages an advanced deep-learning model to resolve complex questions into a series of simple questions that could gradually elaborate on the users’ requirements. To present answers, we design a set of annotated and captioned visualizations to represent the answers in a form that supports interpretation and narration. We conducted an ablation study and a controlled user study to evaluate the Talk2Data’s effectiveness and usefulness.

Measuring and Clustering Heterogeneous Chatbot Designs

Conversational agents, or chatbots, have become popular to access all kind of software services. They provide an intuitive natural language interface for interaction, available from a wide range of channels including social networks, web pages, intelligent speakers or cars. In response to this demand, many chatbot development platforms and tools have emerged. However, they typically lack support to statically measure properties of the chatbots being built, as indicators of their size, complexity, quality or usability. Similarly, there are hardly any mechanisms to compare and cluster chatbots developed with heterogeneous technologies. To overcome this limitation, we propose a suite of 21 metrics for chatbot designs, as well as two clustering methods that help in grouping chatbots along their conversation topics and design features. Both the metrics and the clustering methods are defined on a neutral chatbot design language, becoming independent of the implementation platform. We provide automatic translations of chatbots defined on some major platforms into this neutral notation to perform the measurement and clustering. The approach is supported by our tool Asymob , which we have used to evaluate the metrics and the clustering methods over a set of 259 Dialogflow and Rasa chatbots from open-source repositories. The results open the door to incorporating the metrics within chatbot development processes for the early detection of quality issues, and to exploit clustering to organise large collections of chatbots into significant groups to ease chatbot comprehension, search and comparison.

Nanjing Yunjin intelligent question-answering system based on knowledge graphs and retrieval augmented generation technology

Nanjing Yunjin, a traditional Chinese silk weaving craft, is celebrated globally for its unique local characteristics and exquisite workmanship, forming an integral part of the world's intangible cultural heritage. However, with the advancement of information technology, the experiential knowledge of the Nanjing Yunjin production process is predominantly stored in text format. As a highly specialized and vertical domain, this information is not readily convert into usable data. Previous studies on a knowledge graph-based Nanjing Yunjin Question-Answering System have partially addressed this issue. However, knowledge graphs need to be constantly updated and rely on predefined entities and relationship types. Faced with ambiguous or complex natural language problems, knowledge graph information retrieval faces some challenges. Therefore, this study proposes a Nanjing Yunjin Question-Answering System that integrates Knowledge Graphs and Retrieval Augmented Generation techniques. In this system, the ROBERTA model is first utilized to vectorize Nanjing Yunjin textual information, delving deep into textual semantics to unveil its profound cultural connotations. Additionally, the FAISS vector database is employed for efficient storage and retrieval of Nanjing Yunjin information, achieving a deep semantic match between questions and answers. Ultimately, related retrieval results are fed into the Large Language Model for enhanced generation, aiming for more accurate text generation outcomes and improving the interpretability and logic of the Question-Answering System. This research merges technologies like text embedding, vectorized retrieval, and natural language generation, aiming to overcome the limitations of knowledge graphs-based Question-Answering System in terms of graph updating, dependency on predefined types, and semantic understanding. System implementation and testing have shown that the Nanjing Yunjin Intelligent Question-Answering System, constructed on the basis of Knowledge Graphs and Retrieval Augmented Generation, possesses a broader knowledge base that considers context, resolving issues of polysemy, vague language, and sentence ambiguity, and efficiently and accurately generates answers to natural language queries. This significantly facilitates the retrieval and utilization of Yunjin knowledge, providing a paradigm for constructing Question-Answering System for other intangible cultural heritages, and holds substantial theoretical and practical significance for the deep exploration and discovery of the knowledge structure of human intangible heritage, promoting cultural inheritance and protection.

The Intelligent System for Low Recourses Languages for Expanding Language Recourses

This research, funded under the BR11765535 “Development of Scientific and Linguistic Foundations and IT Resources to Expand the Functions and Improve the Culture of the Kazakh Language” project, is aimed at the need to develop the scientific and linguistic foundations of the Kazakh language with a special focus on anthroponymy. The "Akhmettanu" intelligent system, which includes digitized materials based on the scientific heritage of Akhmet Baitursynuly, consists of an ontological model of knowledge on the structural layers of the language, a Kazakh language user interface with the function of adding and correcting new digitized materials. Digitized materials based on the scientist's work "Language-Tool" include a new system of knowledge about the sound, word and sentence system of the language. The main aim of this system is to promote the scientific heritage of Akhmet Baitursynuly by promoting the further development of digitalized knowledge and information tools that affect the development of the Kazakh language.

Boolean interpretation, matching, and ranking of natural language queries in product selection systems

E-commerce is a massive sector in the US economy, generating $767.7 billion in revenue in 2021. E-commerce sites maximize their revenue by helping customers find, examine, and purchase products. To help users easily find the most relevant products in the database for their individual needs, e-commerce sites are equipped with a product retrieval system. Many of these modern retrieval systems parse user-specified constraints or keywords embedded in a simple natural language query, which is generally easier and faster for the customer to specify their needs than navigating a product specification form, and does not require the seller to design or develop such a form. These natural language product retrieval systems, however, suffer from low relevance in retrieved products, especially for complex constraints specified on products. The reduced accuracy is in part due to under-utilizing the rich semantics of natural language, specifically queries that include Boolean operators, and lacking of the ranking on partially-matched relevant results that could be of interest to the customers. This undesirable effect costs e-commerce vendors to lose sales on their merchandise. In solving this problem, we propose a novel product retrieval system, called QuePR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ extit{QuePR}}$$\\end{document}, that parses arbitrarily simple and complex natural language queries with(out) Boolean operators, utilizes combinatorial numeric and content-based matching to extract relevant products from a database, and ranks retrieved resultant products by relevance before presenting them to the end-user. The advantages of QuePR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ extit{QuePR}}$$\\end{document} are its ability to process explicit and implicit Boolean operators in queries, handle natural language queries using similarity measures on partially-matched records, and perform best guess or match on ambiguous or incomplete queries. QuePR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ extit{QuePR}}$$\\end{document} is unique, easy to use, and scalable to all product categories. To verify the accuracy of QuePR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ extit{QuePR}}$$\\end{document} in retrieving relevant products on different product domains, we have conducted different performance analyses and compared QuePR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ extit{QuePR}}$$\\end{document} with other ranking and retrieval systems. The empirical results verify that QuePR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ extit{QuePR}}$$\\end{document} outperforms others while maintaining an optimal runtime speed.

Medical nearest-word embedding technique implemented using an unsupervised machine learning approach for Bengali language

Abstract The rapid growth of natural language processing (NLP) applications, such as text summarization, speech recognition, information extraction, and machine translation, has led to the development of structured query language (SQL) for extracting information from structured data. However, due to limited resources, converting Natural Language (NL) queries to SQL in Bengali is challenging. This article proposes an unsupervised machine learning model to find semantically Bengali closed words that can generate SQL from NL queries in Bengali. The main objective of the proposed system is to provide support in the creation of patient-oriented explanations and educational resources by simplifying intricate medical terminology. The major findings of the proposed system are as follows: The use of machine translation in the field of medicine facilitates the dissemination of healthcare information to a diverse international audience and improves the performance of entity recognition tasks, including the identification of medical conditions, drugs, or procedures within clinical notes or electronic health data. This system allows a naive user to extract health-related information from a healthcare-structured database without any knowledge of SQL. The system accepts a query and generates a response according to the query in Bengali language. Query tokenization and stop word removal are carried out in the preprocessing stage, and unsupervised machine learning techniques are implemented to process the input query sentence. Tokenized words are converted into vectors using the skip-gram model, with noise-contrastive estimation (NCE) applied to discriminate between actual and irrelevant words. Stochastic gradient descent (SGD) optimizes the model by randomly choosing a small amount of data from the dataset and using cosine similarity to measure closer words. The semantically closer words are found using an unsupervised learning method to generate the SQL.

Multilingual Question Answering for Malaysia History with Transformer-based Language Model

In natural language processing (NLP), a Question Answering System (QAS) refers to a system or model that is designed to understand and respond to user queries in natural language. As we navigate through the recent advancements in QAS, it can be observed that there is a paradigm shift of the methods used from traditional machine learning and deep learning approaches towards transformer-based language models. While significant progress has been made, the utilization of these models for historical QAS and the development of QAS for Malay language remain largely unexplored. This research aims to bridge the gaps, focusing on developing a Multilingual QAS for history of Malaysia by utilizing a transformer-based language model. The system development process encompasses various stages, including data collection, knowledge representation, data loading and pre-processing, document indexing and storing, and the establishment of a querying pipeline with the retriever and reader. A dataset with a collection of 100 articles, including web blogs related to the history of Malaysia, has been constructed, serving as the knowledge base for the proposed QAS. A significant aspect of this research is the use of the translated dataset in English instead of the raw dataset in Malay. This decision was made to leverage the effectiveness of well-established retriever and reader models that were trained on English data. Moreover, an evaluation dataset comprising 100 question-answer pairs has been created to evaluate the performance of the models. A comparative analysis of six different transformer-based language models, namely DeBERTaV3, BERT, ALBERT, ELECTRA, MiniLM, and RoBERTa, has been conducted, where the effectiveness of the models was examined through a series of experiments to determine the best reader model for the proposed QAS. The experimental results reveal that the proposed QAS achieved the best performance when employing RoBERTa as the reader model. Finally, the proposed QAS was deployed on Discord and equipped with multilingual support through the incorporation of language detection and translation modules, enabling it to handle queries in both Malay and English. Doi: 10.28991/ESJ-2024-08-02-019 Full Text: PDF