Answer selection is a task to choose the positive answers from a pool of candidate answers for a given question. In this paper, we propose a novel strategy for answer selection, called hierarchical ranking. We introduce three levels of ranking: point-level ranking, pair-level ranking, and list-level ranking. They formulate their optimization objectives by employing supervisory information from different perspectives to achieve the same goal of ranking candidate answers. Therefore, the three levels of ranking are related and they can promote each other. We take the well-performed compare-aggregate model as the backbone and explore three schemes to implement the idea of applying the hierarchical rankings jointly: the scheme under the Multi-Task Learning (MTL) strategy, the Ranking Integration (RI) scheme, and the Progressive Ranking Integration (PRI) scheme. Experimental results on two public datasets, WikiQA and TREC-QA, demonstrate that the proposed hierarchical ranking is effective. Our method achieves state-of-the-art (non-BERT) performance on both TREC-QA and WikiQA.
With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the sentence-level answer, i.e., answer selection, or phrase-level answer, i.e., machine reading comprehension. How to produce compositional answers has not been throughout investigated. In compositional question answering, the systems should assemble several supporting evidence from the document to generate the final answer, which is more difficult than sentence-level or phrase-level QA. In this paper, we present a large-scale compositional question answering dataset containing more than 120k human-labeled questions. The answer in this dataset is composed of discontiguous sentences in the corresponding document. To tackle the ComQA problem, we proposed a hierarchical graph neural networks, which represents the document from the low-level word to the high-level sentence. We also devise a question selection and node selection task for pre-training. Our proposed model achieves a significant improvement over previous machine reading comprehension methods and pre-training methods. Codes and dataset can be found at \url{https://github.com/benywon/ComQA}.
This paper evaluates existing and newly proposed answer selection methods based on pre-trained word embeddings. Word embeddings are highly effective in various natural language processing tasks and their integration into traditional information retrieval (IR) systems allows for the capture of semantic relatedness between questions and answers. Empirical results on three publicly available data sets show significant gains over traditional term frequency based approaches in both supervised and unsupervised settings. We show that combining these word embedding features with traditional learning-to-rank techniques can achieve similar performance to state-of-the-art neural networks trained for the answer selection task.
Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is that they can effectively absorb the context of each word in a sentence. However, for tasks such as the answer selection task, the pre-trained language models have not been extensively used yet. To investigate their effectiveness in such tasks, in this paper, we adopt the pre-trained Bidirectional Encoder Representations from Transformer (BERT) language model and fine-tune it on two Question Answering (QA) datasets and three Community Question Answering (CQA) datasets for the answer selection task. We find that fine-tuning the BERT model for the answer selection task is very effective and observe a maximum improvement of 13.1% in the QA datasets and 18.7% in the CQA datasets compared to the previous state-of-the-art.
We propose a novel approach for answering and explaining multiple-choice science questions by reasoning on grounding and abstract inference chains. This paper frames question answering as an abductive reasoning problem, constructing plausible explanations for each choice and then selecting the candidate with the best explanation as the final answer. Our system, ExplanationLP, elicits explanations by constructing a weighted graph of relevant facts for each candidate answer and extracting the facts that satisfy certain structural and semantic constraints. To extract the explanations, we employ a linear programming formalism designed to select the optimal subgraph. The graphs' weighting function is composed of a set of parameters, which we fine-tune to optimize answer selection performance. We carry out our experiments on the WorldTree and ARC-Challenge corpus to empirically demonstrate the following conclusions: (1) Grounding-Abstract inference chains provides the semantic control to perform explainable abductive reasoning (2) Efficiency and robustness in learning with a fewer number of parameters by outperforming contemporary explainable and transformer-based approaches in a similar setting (3) Generalisability by outperforming SOTA explainable approaches on general science question sets.
The dependency between an adequate question formulation and correct answer selection is a very intriguing but still underexplored area. In this paper, we show that question rewriting (QR) of the conversational context allows to shed more light on this phenomenon and also use it to evaluate robustness of different answer selection approaches. We introduce a simple framework that enables an automated analysis of the conversational question answering (QA) performance using question rewrites, and present the results of this analysis on the TREC CAsT and QuAC (CANARD) datasets. Our experiments uncover sensitivity to question formulation of the popular state-of-the-art models for reading comprehension and passage ranking. Our results demonstrate that the reading comprehension model is insensitive to question formulation, while the passage ranking changes dramatically with a little variation in the input question. The benefit of QR is that it allows us to pinpoint and group such cases automatically. We show how to use this methodology to verify whether QA models are really learning the task or just finding shortcuts in the dataset, and better understand the frequent types of error they make.
As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate. To address this problem, we propose a novel reinforcement learning (RL) based multi-step ranking model, named MS-Ranker, which accumulates information from potentially correct candidate answers as extra evidence for matching the question with a candidate. In specific, we explicitly consider the potential correctness of candidates and update the evidence with a gating mechanism. Moreover, as we use a listwise ranking reward, our model learns to pay more attention to the overall performance. Experiments on two benchmarks, namely WikiQA and SemEval-2016 CQA, show that our model significantly outperforms existing methods that do not rely on external resources.
Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past. However, with the advent of modern deep neural networks, attention has shifted to discriminative ranking functions that model the semantic similarity of documents and queries instead. Recently, deep generative models such as GPT2 and BART have been shown to be excellent text generators, but their effectiveness as rankers have not been demonstrated yet. In this work, we revisit the generative framework for information retrieval and show that our generative approaches are as effective as state-of-the-art semantic similarity-based discriminative models for the answer selection task. Additionally, we demonstrate the effectiveness of unlikelihood losses for IR.
We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially outperforms common IR baselines. We also demonstrate that considering a broad selection of source domains is crucial for obtaining the best zero-shot transfer performances, which contrasts the standard procedure that merely relies on the largest and most similar domains. In addition, we extensively study how to best combine multiple source domains. We propose to incorporate self-supervised with supervised multi-task learning on all available source domains. Our best zero-shot transfer model considerably outperforms in-domain BERT and the previous state of the art on six benchmarks. Fine-tuning of our model with in-domain data results in additional large gains and achieves the new state of the art on all nine benchmarks.
Multi-choice machine reading comprehension (MRC) requires models to choose the correct answer from candidate options given a passage and a question. Our research focuses dialogue-based MRC, where the passages are multi-turn dialogues. It suffers from two challenges, the answer selection decision is made without support of latently helpful commonsense, and the multi-turn context may hide considerable irrelevant information. This work thus makes the first attempt to tackle those two challenges by extracting substantially important turns and utilizing external knowledge to enhance the representation of context. In this paper, the relevance of each turn to the question are calculated to choose key turns. Besides, terms related to the context and the question in a knowledge graph are extracted as external knowledge. The original context, question and external knowledge are encoded with the pre-trained language model, then the language representation and key turns are combined together with a will-designed mechanism to predict the answer. Experimental results on a DREAM dataset show that our proposed model achieves great improvements on baselines.
Text matching is a core natural language processing research problem. How to retain sufficient information on both content and structure information is one important challenge. In this paper, we present a neural approach for general-purpose text matching with deep mutual information estimation incorporated. Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised learning of representations by maximizing the mutual information between text matching neural network's input and output. We use both global and local mutual information to learn text representations. We evaluate our text matching approach on several tasks including natural language inference, paraphrase identification, and answer selection. Compared to the state-of-the-art approaches, the experiments show that our method integrated with mutual information estimation learns better text representation and achieves better experimental results of text matching tasks without exploiting pretraining on external data.
Product-specific community question answering platforms can greatly help address the concerns of potential customers. However, the user-provided answers on such platforms often vary a lot in their qualities. Helpfulness votes from the community can indicate the overall quality of the answer, but they are often missing. Accurately predicting the helpfulness of an answer to a given question and thus identifying helpful answers is becoming a demanding need. Since the helpfulness of an answer depends on multiple perspectives instead of only topical relevance investigated in typical QA tasks, common answer selection algorithms are insufficient for tackling this task. In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers. Moreover, we tackle the task of determining opinion coherence as a language inference problem and explore the utilization of pre-training strategy to transfer the textual inference knowledge obtained from a specifically designed trained network. Extensive experiments conducted on real-world data across seven product categories show that our proposed model achieves superior performance on the prediction task.
Deep learning methods that extract answers for non-factoid questions from QA sites are seen as critical since they can assist users in reaching their next decisions through conversations with AI systems. The current methods, however, have the following two problems: (1) They can not understand the ambiguous use of words in the questions as word usage can strongly depend on the context. As a result, the accuracies of their answer selections are not good enough. (2) The current methods can only select from among the answers held by QA sites and can not generate new ones. Thus, they can not answer the questions that are somewhat different with those stored in QA sites. Our solution, Neural Answer Construction Model, tackles these problems as it: (1) Incorporates the biases of semantics behind questions into word embeddings while also computing them regardless of the semantics. As a result, it can extract answers that suit the contexts of words used in the question as well as following the common usage of words across semantics. This improves the accuracy of answer selection. (2) Uses biLSTM to compute the embeddings of questions as well as those of the sentences often used to form answers. It then simultaneously learns the optimum combination of those sentences as well as the closeness between the question and those sentences. As a result, our model can construct an answer that corresponds to the situation that underlies the question; it fills the gap between answer selection and generation and is the first model to move beyond the current simple answer selection model for non-factoid QAs. Evaluations using datasets created for love advice stored in the Japanese QA site, Oshiete goo, indicate that our model achieves 20% higher accuracy in answer creation than the strong baselines. Our model is practical and has already been applied to the love advice service in Oshiete goo.
In the community question answering (CQA) system, the answer selection task aims to identify the best answer for a specific question, and thus is playing a key role in enhancing the service quality through recommending appropriate answers for new questions. Recent advances in CQA answer selection focus on enhancing the performance by incorporating the community information, particularly the expertise (previous answers) and authority (position in the social network) of an answerer. However, existing approaches for incorporating such information are limited in (a) only considering either the expertise or the authority, but not both; (b) ignoring the domain knowledge to differentiate topics of previous answers; and (c) simply using the authority information to adjust the similarity score, instead of fully utilizing it in the process of measuring the similarity between segments of the question and the answer. We propose the Knowledge-enhanced Attentive Answer Selection (KAAS) model, which enhances the performance through (a) considering both the expertise and the authority of the answerer; (b) utilizing the human-labeled tags, the taxonomy of the tags, and the votes as the domain knowledge to infer the expertise of the answer; (c) using matrix decomposition of the social network (formed by following-relationship) to infer the authority of the answerer and incorporating such information in the process of evaluating the similarity between segments. Besides, for vertical community, we incorporate an external knowledge graph to capture more professional information for vertical CQA systems. Then we adopt the attention mechanism to integrate the analysis of the text of questions and answers and the aforementioned community information. Experiments with both vertical and general CQA sites demonstrate the superior performance of the proposed KAAS model.
Community Question Answering (cQA) provides new interesting research directions to the traditional Question Answering (QA) field, e.g., the exploitation of the interaction between users and the structure of related posts. In this context, we organized SemEval-2015 Task 3 on "Answer Selection in cQA", which included two subtasks: (a) classifying answers as "good", "bad", or "potentially relevant" with respect to the question, and (b) answering a YES/NO question with "yes", "no", or "unsure", based on the list of all answers. We set subtask A for Arabic and English on two relatively different cQA domains, i.e., the Qatar Living website for English, and a Quran-related website for Arabic. We used crowdsourcing on Amazon Mechanical Turk to label a large English training dataset, which we released to the research community. Thirteen teams participated in the challenge with a total of 61 submissions: 24 primary and 37 contrastive. The best systems achieved an official score (macro-averaged F1) of 57.19 and 63.7 for the English subtasks A and B, and 78.55 for the Arabic subtask A.
Community question answering (CQA) gains increasing popularity in both academy and industry recently. However, the redundancy and lengthiness issues of crowdsourced answers limit the performance of answer selection and lead to reading difficulties and misunderstandings for community users. To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model. Specifically, we design a question-driven pointer-generator network, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating answer summaries. Meanwhile, we leverage the answer summaries to alleviate noise in original lengthy answers when ranking the relevancy degrees of question-answer pairs. In addition, we construct a new large-scale CQA corpus, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization. The experimental results show that the joint learning method can effectively address the answer redundancy issue in CQA and achieves state-of-the-art results on both answer selection and text summarization tasks. Furthermore, the proposed model is shown to be of great transferring ability and applicability for resource-poor CQA tasks, which lack of reference answer summaries.
This paper addresses the question of identifying the best candidate answer to a question on Community Question Answer (CQA) forums. The problem is important because Individuals often visit CQA forums to seek answers to nuanced questions. We develop a novel induced relational graph convolutional network (IR-GCN) framework to address the question. We make three contributions. First, we introduce a modular framework that separates the construction of the graph with the label selection mechanism. We use equivalence relations to induce a graph comprising cliques and identify two label assignment mechanisms---label contrast, label sharing. Then, we show how to encode these assignment mechanisms in GCNs. Second, we show that encoding contrast creates discriminative magnification---enhancing the separation between nodes in the embedding space. Third, we show a surprising result---boosting techniques improve learning over familiar stacking, fusion, or aggregation approaches for neural architectures. We show strong results over the state-of-the-art neural baselines in extensive experiments on 50 StackExchange communities.
Supervised training of neural models to duplicate question detection in community Question Answering (cQA) requires large amounts of labeled question pairs, which are costly to obtain. To minimize this cost, recent works thus often used alternative methods, e.g., adversarial domain adaptation. In this work, we propose two novel methods: (1) the automatic generation of duplicate questions, and (2) weak supervision using the title and body of a question. We show that both can achieve improved performances even though they do not require any labeled data. We provide comprehensive comparisons of popular training strategies, which provides important insights on how to best train models in different scenarios. We show that our proposed approaches are more effective in many cases because they can utilize larger amounts of unlabeled data from cQA forums. Finally, we also show that our proposed approach for weak supervision with question title and body information is also an effective method to train cQA answer selection models without direct answer supervision.
In recent years, Question Answering systems have become more popular and widely used by users. Despite the increasing popularity of these systems, the their performance is not even sufficient for textual data and requires further research. These systems consist of several parts that one of them is the Answer Selection component. This component detects the most relevant answer from a list of candidate answers. The methods presented in previous researches have attempted to provide an independent model to undertake the answer-selection task. An independent model cannot comprehend the syntactic and semantic features of questions and answers with a small training dataset. To fill this gap, language models can be employed in implementing the answer selection part. This action enables the model to have a better understanding of the language in order to understand questions and answers better than previous works. In this research, we will present the "BAS" (BERT Answer Selection) that uses the BERT language model to comprehend language. The empirical results of applying the model on the TrecQA Raw, TrecQA Clean, and WikiQA datasets demonstrate that using a robust language model such as BERT can enhance the performance. Using a more robust classifier also enhances the effect of the language model on the answer selection component. The results demonstrate that language comprehension is an essential requirement in natural language processing tasks such as answer-selection.
Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our hypothesis is that question-answer pairs are often in analogical relation to each other. Using analogical inference as our use case, we propose a framework and a neural network architecture for learning dedicated sentence embeddings that preserve analogical properties in the semantic space. We evaluate the proposed method on benchmark datasets for answer selection and demonstrate that our sentence embeddings indeed capture analogical properties better than conventional embeddings, and that analogy-based question answering outperforms a comparable similarity-based technique.