ASQA: Academia sinica question answering system for NTCIR-5 CLQA

In this paper we describe Tokyo Institute of Technology’s attempt at the TREC2007 question answering (QA) track. Keeping the same theoretical QA model as for the TREC2006 task, this year we once again focused on the factoid QA task, while investigating a new method for sentence retrieval. We deviated from our earlier approach of using web data, and instead relied solely on the supplied news wire and blog data. Our factoid and list score fell significantly from last year, while we achieved a higher other question score compared to TREC2006, using sentence retrieval rather than last year’s summarization method. 1.

In this paper we describe Tokyo Institute of Technology's attempt at the TREC2007 question answering (QA) track. Keeping the same theoretical QA model as for the TREC2006 task, this year we once again focused on the factoid QA task, while investigating a new method for sentence retrieval. We deviated from our earlier approach of using web data, and instead relied solely on the supplied news wire and blog data. Our factoid and list score fell significantly from last year, while we achieved a higher other question score compared to TREC2006, using sentence retrieval rather than last year's summarization method.

ACM Transactions on Information Systems, 2012

In this article, we present a factoid question-answering system, Sibyl, specifically tailored for question answering (QA) on spoken-word documents. This work explores, for the first time, which techniques can be robustly adapted from the usual QA on written documents to the more difficult spoken document scenario. More specifically, we study new information retrieval (IR) techniques designed or speech, and utilize several levels of linguistic information for the speech-based QA task. These include named-entity detection with phonetic information, syntactic parsing applied to speech transcripts, and the use of coreference resolution. Sibyl is largely based on supervised machine-learning techniques, with special focus on the answer extraction step, and makes little use of handcrafted knowledge. Consequently, it should be easily adaptable to other domains and languages. Sibyl and all its modules are extensively evaluated on the European Parliament Plenary Sessions English corpus, compa...

This paper describes an question answering system based on syntactic information. Our system extracts answer candidates by ranking of score which shows similarity of syntactic structure. Syntactic structure is estimated based on answer type, density of weighty words, distance between words and depth of parse tree. To analyze syntactic structure, morphological analysis, named entity extraction and parser are utilized.

Journal of Xidian University, 2021

The usage and amount of information available on the internet increase over the past decade. This digitization leads to the need for automated answering system to extract fruitful information from redundant and transitional knowledge sources. Such systems are designed to cater the most prominent answer from this giant knowledge source to the user's query using natural language understanding (NLU) and thus eminently depends on the Question-answering(QA) field. Question answering involves but not limited to the steps like mapping of user's question to pertinent query, retrieval of relevant information, finding the best suitable answer from the retrieved information etc. The current improvement of deep learning models evince compelling performance improvement in all these tasks. In this review work, the research directions of QA field are analyzed based on the type of question, answer type, source of evidence-answer, and modeling approach. This detailing followed by open challenges of the field like automatic question generation, similarity detection and, low resource availability for a language. In the end, a survey of available datasets and evaluation measures is presented.

arXiv (Cornell University), 2022

Question answering (QA) is a natural language understanding task within the fields of information retrieval and information extraction that has attracted much attention from the computational linguistics and artificial intelligence research community in recent years because of the strong development of machine reading comprehension-based models. A reader-based QA system is a high-level search engine that can find correct answers to queries or questions in open-domain or domain-specific texts using machine reading comprehension (MRC) techniques. The majority of advancements in data resources and machine-learning approaches in the MRC and QA systems especially are developed significantly in two resource-rich languages such as English and Chinese. A low-resource language like Vietnamese has witnessed a scarcity of research on QA systems. This paper presents XLMRQA, the first Vietnamese QA system using a supervised transformer-based reader on the Wikipedia-based textual knowledge source (using the UIT-ViQuAD corpus), outperforming the two robust QA systems using deep neural network models: DrQA and BERTserini with 24.46% and 6.28%, respectively. From the results obtained on the three systems, we analyze the influence of question types on the performance of the QA systems.

ACM Transactions on Asian Language Information Processing, 2008

Question Answering (QA) research has been conducted in many languages. Nearly all the top performing systems use heavy methods that require sophisticated techniques, such as parsers or logic provers. However, such techniques are usually unavailable or unaffordable for underresourced languages or in resource-limited situations. In this article, we describe how a topperforming Chinese QA system can be designed by using lightweight methods effectively. We propose two lightweight methods, namely the Sum of Co-occurrences of Question and Answer Terms (SCO-QAT) and Alignment-based Surface Patterns (ABSPs). SCO-QAT is a co-occurrencebased answer-ranking method that does not need extra knowledge, word-ignoring heuristic rules, or tools. It calculates co-occurrence scores based on the passage retrieval results. ABSPs are syntactic patterns trained from question-answer pairs with a multiple alignment algorithm. They are used to capture the relations between terms and then use the relations to filter answers. We attribute the success of the ABSPs and SCO-QAT methods to the effective use of local syntactic information and global co-occurrence information.

2015

This paper describes our participation in the NTCIR-5 CLQA task. Three runs were officially submitted for three subtasks: Chinese Question

2004

We describe an overview of Question Answering Challenge (QAC) 2 Subtask 3, a novel challenge for evaluating open-domain question answering technologies, at the NTCIR Workshop 4. In QAC2 Subtask 3, question answering systems are supposed to be used interactively to answer a series of related questions, whereas in the conventional setting, systems answer isolated questions one by one. Such an interaction occurs in the case of gathering information for a report on a specific topic, or when browsing information of interest to the user. In this paper, first, we explain the design of the challenge. Reporting the results of the run conducted and techniques employed there, we then show that existing technologies have the potential to address this challenge.

2004

In this paper we describe and evaluate a Question Answering system that goes beyond answering factoid questions. We focus on FAQlike questions and answers, and build our system around a noisy-channel architecture which exploits both a language model for answers and a transformation model for answer/question terms, trained on a corpus of 1 million question/answer pairs collected from the Web.