A Tri-Role Topic Model for Domain-Specific Question Answering

Question answering (QA) models use retriever and reader systems to answer questions. Reliance on training data by QA systems can amplify or reflect inequity through their responses. Many QA models, such as those for the SQuAD dataset, are trained and tested on a subset of Wikipedia articles which encode their own biases and also reproduce real-world inequality. Understanding how training data affects bias in QA systems can inform methods to mitigate inequity. We develop two sets of questions for closed and open domain questions respectively, which use ambiguous questions to probe QA models for bias. We feed three deep-learning-based QA systems with our question sets and evaluate responses for bias via the metrics. Using our metrics, we find that open-domain QA models amplify biases more than their closed-domain counterparts and propose that biases in the retriever surface more readily due to greater freedom of choice.

Datasets that boosted state-of-the-art solutions for Question Answering (QA) systems prove that it is possible to ask questions in natural language manner. However, users are still used to query-like systems where they type in keywords to search for answer. In this study we validate which parts of questions are essential for obtaining valid answer. In order to conclude that, we take advantage of LIME - a framework that explains prediction by local approximation. We find that grammar and natural language is disregarded by QA. State-of-the-art model can answer properly even if 'asked' only with a few words with high coefficients calculated with LIME. According to our knowledge, it is the first time that QA model is being explained by LIME.

Expert finding for question answering is a challenging problem in community-based question answering (CQA) systems, arising in many real applications such as question routing and identification of best answers. In order to provide high-quality experts, many existing approaches learn the user model from their past question-answering activities in CQA systems. However, the past activities of users in most CQA systems are rather few, and thus the user model may not be well inferred in practice. In this paper, we consider the problem of expert finding from the viewpoint of missing value estimation. We then employ users' social networks for inferring user model, and thus improve the performance of expert finding in CQA systems. In addition, we develop a novel graph-regularized matrix completion algorithm for inferring the user model. We further develop two efficient iterative procedures, GRMC-EGM and GRMC-AGM, to solve the optimization problem. GRMC-EGM utilizes the Extended Gradient Method (EGM), while GRMC-AGM applies the Accelerated proximal Gradient search Method (AGM), for the optimization. We evaluate our methods on the well-known question answering system Quora, and the popular social network Twitter. Our empirical study shows the effectiveness of the proposed algorithms in comparison to the state-of-the-art expert finding algorithms.

Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces. However, current benchmarks in QA research do not account for the errors that speech recognition models might introduce, nor do they consider the language variations (dialects) of the users. To address this gap, we augment an existing QA dataset to construct a multi-dialect, spoken QA benchmark on five languages (Arabic, Bengali, English, Kiswahili, Korean) with more than 68k audio prompts in 24 dialects from 255 speakers. We provide baseline results showcasing the real-world performance of QA systems and analyze the effect of language variety and other sensitive speaker attributes on downstream performance. Last, we study the fairness of the ASR and QA models with respect to the underlying user populations.

Open-domain question answering is an emerging field of natural language processing. Application areas of question answering (QA) systems are increasing with the availability of new datasets, more powerful machines and easy access to voice-enabled devices that interact with humans in their daily lives. Users can get into interactions with QA systems without the need to be limited by any domain. However, there is still need for QA systems that can answer questions in a specific field such as international criminal law, violence of human rights or bill of rights. The recent approaches on open-domain question answering made it possible to extend open-domain QA systems towards specific fields. This paper presents Quill-QA, the new feature of the Quill Platform. Quill Platform is a web platform providing set of tools that digitize and visualize negotiated texts, any text in the form of formal negotiations. Quill-QA is based on Facebook's DrQA system and as a result it adopts a flexible Ranker-Reader architecture. Quill-QA answers questions addressed on the samples of negotiated texts such as U.S. Constitutional Convention of 1787, Utah State Constitutional Convention of 1895 and European Union Act 2017. Without limiting the scope of the input questions to a finite set of templates, Quill-QA is the first QA system that focuses on negotiated texts.

For a significant number of questions at Stack Overflow, none of the posted answers were accepted as solutions. Acceptance of an answer indicates that the answer actually solves the discussed problem in the question, and the question is answered sufficiently. In this paper, we investigate 3,956 such unresolved questions using an exploratory study where we analyze four important aspects of those questions, their answers and the corresponding users that partially explain the observed scenario. We then propose a prediction model by employing five metrics related to user behaviour, topics and popularity of question, which predicts if the best answer for a question at Stack Overflow might remain unaccepted or not. Experiments using 8,057 questions show that the model can predict unresolved questions with 78.70% precision and 76.10% recall.

Given a user question, the goal of a Question Answering (QA) system is to retrieve answers rather than full documents or even best-matching passages, as most Information Retrieval systems currently do. In this paper, we present BRUJA, a QA system for the management of multilingual collections. BRUJ rkstions (English, Spanish and French). The BRUJA architecture is not formed with three monolingual QA systems but instead uses English as Interlingua to make usual QA tasks such as question classifications and answer extractions. In addition, BRUJA uses Cross Language Information Retrieval (CLIR) techniques to retrieve relevant documents from a multilingual collection. On the one hand, we have more documents to find answers from but on the other hand, we are introducing noise into the system because of translations to the Interlingua (English) and the CLIR module. The question is whether the difficulty of managing three languages is worth it or whether a monolingual QA system delivers better results. We report on in-depth experimentation and demonstrate that our multilingual QA system gets better results than its monolingual counterpart whenever it uses good translation resources and, especially, CLIR techniques that are state-of-the-art.

Machine Reading Comprehension (MRC) is a challenging Question - Answering (QA) task that helps the user in providing the answer to the given question. There is a lot of progress in this area due to the availability of large datasets and large pre-trained language models based on transformer architecture (BERT). Named Entity Recognition (NER) was used for neural QA systems to improve performance. However, whether NER plays a vital role in a QA system built using contextual embeddings obtained through BERT variants is not explored. To fill this gap, we investigate whether NER is helpful in improving the performance of QA systems built using BERT variants. We experimented with Squad 2.0 using SpanBERT. The Squad 2.0 dataset has both answerable and unanswerable questions. The proposed model finds the answer span if the question is answerable and, provides justification for the unanswerable questions. We perform question analysis to find the expected answer tag and then use that information to find the relevant parts of the passage in order to retrieve the answer span.

Number of people having expertise in a certain domain is less than people who need information in that domain. In this situation, an automatic question answering (QA) system is necessary. Observing available manual QA sites on internet, the real world question that people usually ask have different expected answer type (EAT) compared to a common automatic QA. Addressing a case study of a religion domain which makes it a closed domain QA, we proposed the EAT into 6 types: LAW, DEFINITION, COMPARISON, METHOD, TIME and PERSON. Different with common QA approach, we built the QA system using case based approach which consists of two main components: Question Analyzer and Case Retriever. Related with the case based reasoning (CBR) framework, these two main components act as the Retrieve and Reuse process while the Revise and Retain process is handle by Case Retainer component. The QA system was built using available Indonesian Natural Language Processing (NLP) tools and FreeCBR as the CBR library. The experiments were done to calculate the accuracy and testing the system with unknown case. By using 77 cases collected from internet with assumption that all answers are available, the experiments achieved 97% accuracy. And by using 10 test cases for the unknown case, the similarity score calculated by the system showed that the test questions have no answer in the available case base.

Question-answering (QA) models find answers to a given question. The necessity of automatically finding answers is increasing because it is very important and challenging from the large-scale QA data sets. In this paper, we deal with the QA pair matching approach in QA models, which finds the most relevant question and its recommended answer for a given question. Existing studies for the approach performed on the entire dataset or datasets within a category that the question writer manually specifies. In contrast, we aim to automatically find the category to which the question belongs by employing the text classification model and to find the answer corresponding to the question within the category. Due to the text classification model, we can effectively reduce the search space for finding the answers to a given question. Therefore, the proposed model improves the accuracy of the QA matching model and significantly reduces the model inference time. Furthermore, to improve the performance of finding similar sentences in each category, we present an ensemble embedding model for sentences, improving the performance compared to the individual embedding models. Using real-world QA data sets, we evaluate the performance of the proposed QA matching model. As a result, the accuracy of our final ensemble embedding model based on the text classification model is 81.18%, which outperforms the existing models by 9.81%∼14.16% point. Moreover, in terms of the model inference speed, our model is faster than the existing models by 2.61∼5.07 times due to the effective reduction of search spaces by the text classification model.

Community-based question answering sites such as Yahoo! Answers, Quora, and Stack Overflow have emerged as an effective means of information seeking on the Web. Anyone can obtain answers to their questions by posting them for other participants on these sites. However, not all questions get immediate answers from other users. Questions which are not interesting enough for the community may suffer from “starvation”. Such questions may take days/months to get satisfactory answers. This delay in response can be avoided by searching similar questions in an archive of previously answered questions or by forwarding to users who might potentially answer. Another approach would be to combine multiple valid answers into one and then generate a well-summarized answer. The proposed framework reduces starvation of new questions in Stack Overflow by profiling users based on interests and forwarding the questions to the right users to obtain trustful, complete, and relevant answers.

This paper presents a study of the negative effect of Machine Translation (MT) on the precision of Cross---Lingual Question Answering (CL---QA). For this research, a English---Spanish Question Answering (QA) system is used. Also, the sets of 200 official questions from CLEF 2004 and 2006 are used. The CL experimental evaluation using MT reveals that the precision of the system drops around 30% with regard to the monolingual Spanish task. Our main contribution consists on a taxonomy of the identified errors caused by using MT and how the errors can be overcome by using our proposals. An experimental evaluation proves that our approach performs better than MT tools, at the same time contributing to this CL---QA system being ranked first at English---Spanish QA CLEF 2006.

As readers of scientific articles often read to answer specific questions, the task of Question-Answering (QA) in academic papers was proposed to evaluate the ability of intelligent systems to answer questions in long scientific documents. Due to the large contexts in the questions, this task poses many challenges to state-of-the-art QA models. This paper explores the retriever-reader approaches widely used in open-domain QA and their impact when adapting to QA on long scientific documents. By treating one scientific article as the corpus for retrieval, we propose a retriever-reader method to extract the answer from the relevant parts of the document and an effective sliding window technique that improves the pipeline by splitting the articles into disjoint text blocks of fixed size. Experiments on QASPER, a dataset for QA in Natural Language Processing papers, showed that our method outperforms all state-of-the-art models and establishes a new state-of-the-art in the extractive questions subset with 30.43% F1\(^{1}\)The code and processed data are available at https://github.com/lekhang4497/qasper-retriever-reader.KeywordsQuestion-answeringRetriever-readerLong sequences

While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects. First, we lack QA datasets covering complex questions that involve answers as well as the reasoning processes to get them. As a result, the state-of-the-art QA research on numerical reasoning still focuses on simple calculations and does not provide the mathematical expressions or evidence justifying the answers. Second, the QA community has contributed a lot of effort to improve the interpretability of QA models. However, they fail to explicitly show the reasoning process, such as the evidence order for reasoning and the interactions between different pieces of evidence. To address the above shortcoming, we introduce NOAHQA, a conversational and bilingual QA dataset with questions requiring numerical reasoning with compound mathematical expressions. With NOAHQA, we develop an interpretable reasoning graph as well as the appropriate evaluation metric to measure the answer quality. We evaluate the state-of-the-art QA models trained using existing QA datasets on NOAHQA and show that the best among them can only achieve 55.5 exact match scores, while the human performance is 89.7. We also present a new QA model for generating a reasoning graph where the reasoning graph metric still has a large gap compared with that of humans, eg, 28 scores.

Community question answering (CQA) services accumulate large amount of knowledge through the voluntary services of the community across the globe. In fact, CQA services gained much popularity recently compared to other Internet services in obtaining and exchanging information. Stack Overflow is an example of such a service that targets programmers and software developers. In general, most questions in Stack Overflow are usually ended up with an answer accepted by the askers. However, it is found that the number of unanswered or ignored questions has increased significantly in the past few years. Understanding the factors that contribute to questions being answered as well as questions remain ignored can help information seekers to improve the quality of their questions and increase their chances of getting answers from the community in Stack Overflow. In this study, we attempt to identify by data mining techniques the relevant features that will help predict the quality of questions, and validate the reliability of the features using some of the state-of-the-art classification algorithms. The features to be obtained have to be significant in the sense that they can help Stack Overflow to improve their existing CQA service in terms of user satisfaction in obtaining quality answers from their questions.