Recent techniques in Question Answering (QA) have gained remarkable performance improvement with some QA models even surpassed human performance. However, the ability of these models in truly understanding the language still remains dubious and the models are revealing limitations when facing adversarial examples. To strengthen the robustness of QA models and their generalization ability, we propose a representation Enhancement via Semantic and Context constraints (ESC) approach to improve the robustness of lexical embeddings. Specifically, we insert perturbations with semantic constraints and train enhanced contextual representations via a context-constraint loss to better distinguish the context clues for the correct answer. Experimental results show that our approach gains significant robustness improvement on four adversarial test sets.
Universitat Politècnica de València（瓦伦西亚理工大学）；University of Houston（休斯顿大学）
In this work we describe the system built for the three English subtasks of the SemEval 2016 Task 3 by the Department of Computer Science of the University of Houston (UH) and the Pattern Recognition and Human Language Technology (PRHLT) research center - Universitat Polit`ecnica de Val`encia: UH-PRHLT. Our system represents instances by using both lexical and semantic-based similarity measures between text pairs. Our semantic features include the use of distributed representations of words, knowledge graphs generated with the BabelNet multilingual semantic network, and the FrameNet lexical da…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap. This hinders QA models from generalizing to under-represented samples such as questions with low lexical overlap. Question generation (QG), a method for augmenting QA datasets, can be a solution for such performance degradation if QG can properly debias QA datasets. However, we discover that recent neural QG models are biased towards generating questions with high lexical overlap, which can amplify the dataset bias. Moreover, our analysi…
Question answering-based summarization evaluation metrics must automatically determine whether the QA model's prediction is correct or not, a task known as answer verification. In this work, we benchmark the lexical answer verification methods which have been used by current QA-based metrics as well as two more sophisticated text comparison methods, BERTScore and LERC. We find that LERC out-performs the other methods in some settings while remaining statistically indistinguishable from lexical overlap in others. However, our experiments reveal that improved verification performance does not ne…
Indian Institute of Technology Roorkee（印度理工学院鲁尔基分校）
A major challenge to the problem of community question answering is the lexical and semantic gap between the sentence representations. Some solutions to minimize this gap includes the introduction of extra parameters to deep models or augmenting the external handcrafted features. In this paper, we propose a novel attentive recurrent tensor network for solving the lexical and semantic gap in community question answering. We introduce token-level and phrase-level attention strategy that maps input sequences to the output using trainable parameters. Further, we use the tensor parameters to introd…
Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution
Samsung Research Center Russia（三星俄罗斯研究中心）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；HSE University（俄罗斯国立高等经济大学）
This paper describes our system for The Microsoft AI Challenge India 2018: Ranking Passages for Web Question Answering. The system uses the biLSTM network with co-attention mechanism between query and passage representations. Additionally, we use self attention on embeddings to increase the lexical coverage by allowing the system to take union over different embeddings. We also incorporate hand-crafted features to improve the system performance. Our system achieved a Mean Reciprocal Rank (MRR) of 0.67 on eval-1 dataset.
The evaluation of question answering models compares ground-truth annotations with model predictions. However, as of today, this comparison is mostly lexical-based and therefore misses out on answers that have no lexical overlap but are still semantically similar, thus treating correct answers as false. This underestimation of the true performance of models hinders user acceptance in applications and complicates a fair comparison of different models. Therefore, there is a need for an evaluation metric that is based on semantics instead of pure string similarity. In this short paper, we present…
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering
Pulchowk Campus, IoE（伊奥学院普尔乔克校区）；Cohere For AI Community（Cohere AI社区）；IIT Roorkee（鲁基印度理工学院）；NUST（巴基斯坦国家科技大学）；University of Wisconsin（威斯康星大学）；University of Maryland（马里兰大学）
Seoul National University（首尔大学）；University of Washington（华盛顿大学）
We show that the task of question answering (QA) can significantly benefit from the transfer learning of models trained on a different large, fine-grained QA dataset. We achieve the state of the art in two well-studied QA datasets, WikiQA and SemEval-2016 (Task 3A), through a basic transfer learning technique from SQuAD. For WikiQA, our model outperforms the previous best model by more than 8%. We demonstrate that finer supervision provides better guidance for learning lexical and syntactic information than coarser supervision, through quantitative results and visual analysis. We also show tha…
University of Washington（华盛顿大学）；Google AI Language（谷歌人工智能语言部门）
We study approaches to improve fine-grained short answer Question Answering models by integrating coarse-grained data annotated for paragraph-level relevance and show that coarsely annotated data can bring significant performance gains. Experiments demonstrate that the standard multi-task learning approach of sharing representations is not the most effective way to leverage coarse-grained annotations. Instead, we can explicitly model the latent fine-grained short answer variables and optimize the marginal log-likelihood directly or use a newly proposed \emph{posterior distillation} learning ob…
In this paper, we propose a novel word-alignment-based method to solve the FAQ-based question answering task. First, we employ a neural network model to calculate question similarity, where the word alignment between two questions is used for extracting features. Second, we design a bootstrap-based feature extraction method to extract a small set of effective lexical features. Third, we propose a learning-to-rank algorithm to train parameters more suitable for the ranking tasks. Experimental results, conducted on three languages (English, Spanish and Japanese), demonstrate that the question si…
University of Information Technology（信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）
Although Vietnamese is the 17th most popular native-speaker language in the world, there are not many research studies on Vietnamese machine reading comprehension (MRC), the task of understanding a text and answering questions about it. One of the reasons is because of the lack of high-quality benchmark datasets for this task. In this work, we construct a dataset which consists of 2,783 pairs of multiple-choice questions and answers based on 417 Vietnamese texts which are commonly used for teaching reading comprehension for elementary school pupils. In addition, we propose a lexical-based MRC …
Classic lexical-matching-based QA metrics are slowly being phased out because they punish succinct or informative outputs just because those answers were not provided as ground truth. Recently proposed neural metrics can evaluate semantic similarity but were trained on small textual similarity datasets grafted from foreign domains. We introduce the Wiki Entity Similarity (WES) dataset, an 11M example, domain targeted, semantic entity similarity dataset that is generated from link texts in Wikipedia. WES is tailored to QA evaluation: the examples are entities and phrases and grouped into semant…
Islamic Science University of Malaysia（马来西亚伊斯兰科学大学）；Zarqa University（扎尔卡大学）
Question processing is a fundamental step in a question answering (QA) application, and its quality impacts the performance of QA application. The major challenging issue in processing question is how to extract semantic of natural language questions (NLQs). A human language is ambiguous. Ambiguity may occur at two levels; lexical and syntactic. In this paper, we propose a new approach for resolving lexical ambiguity problem by integrating context knowledge and concepts knowledge of a domain, into shallow natural language processing (SNLP) techniques. Concepts knowledge is modeled using ontolo…
Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Institute for Intelligent Computing, Alibaba Group（阿里巴巴集团智能计算研究院）
Microsoft Research Asia（微软亚洲研究院）；Sun Yat-Sen University（中山大学）
Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge. We believe the main reason is the lack of commonsense \mbox{connections} between concepts. To remedy this, we provide a simple and effective method that leverages external commonsense knowledge base such as ConceptNet. We pre-train direct and indirect relational functions between concepts, and show that these pre-trained functions could be easily added to existing neural network models. Results show that incorporating commonsense…
Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about complex science questions which require some form of inference to determine the correct answer. In this paper, we present a two-step method that combines information retrieval techniques optimized for question answering with deep learning models for natural language inference in order to tackle the multi-choice question answering in the science domain. For each question-answer pair, we use standard retrieval-based model…
South China University of Technology（华南理工大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Tencent AI Lab（腾讯人工智能实验室）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Neural network models usually suffer from the challenge of incorporating commonsense knowledge into the open-domain dialogue systems. In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. In addition, we propose a response guiding attention and a multi-step decoding strategy to steer our model to focus on relevant features for response…
The first step of processing a question in Question Answering(QA) Systems is to carry out a detailed analysis of the question for the purpose of determining what it is asking for and how to perfectly approach answering it. Our Question analysis uses several techniques to analyze any question given in natural language: a Stanford POS Tagger & parser for Arabic language, a named entity recognizer, tokenizer,Stop-word removal, Question expansion, Question classification and Question focus extraction components. We employ numerous detection rules and trained classifier using features from this ana…
Redfin Inc.（Redfin公司）；University of Pennsylvania（宾夕法尼亚大学）
Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with is content-dense. Here we empirically test this assumption on news articles from the business, U.S. international relations, sports and science journalism domains. Our findings clearly indicate that about half of the news texts in our study are in fact not content-dense and motivate the development of a supervised content-density detector. We heuristically …
Improving Vietnamese Legal Question--Answering System based on Automatic Data Enrichment
VNU University of Engineering and Technology（越南国立大学工程技术大学）；National Institute of Informatics（国立信息学研究所）；Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）
University of Maryland, College Park（马里兰大学帕克分校）；IIT Kharagpur（印度理工学院克勒格布尔分校）；University of Minnesota（明尼苏达大学）
Question Answering (QA) systems require a large amount of annotated data which is costly and time-consuming to gather. Converting datasets of existing QA benchmarks are challenging due to different formats and complexities. To address these issues, we propose an algorithm to automatically generate shorter questions resembling day-to-day human communication in the Natural Questions (NQ) dataset from longer trivia questions in Quizbowl (QB) dataset by leveraging conversion in style among the datasets. This provides an automated way to generate more data for our QA systems. To ensure quality as w…
University of the Basque Country (UPV/EHU)（巴斯克地区大学（UPV/EHU））；New York University (NYU)（纽约大学（NYU））
The interaction of conversational systems with users poses an exciting opportunity for improving them after deployment, but little evidence has been provided of its feasibility. In most applications, users are not able to provide the correct answer to the system, but they are able to provide binary (correct, incorrect) feedback. In this paper we propose feedback-weighted learning based on importance sampling to improve upon an initial supervised system using binary user feedback. We perform simulated experiments on document classification (for development) and Conversational Question Answering…
University of Washington（华盛顿大学）；Salesforce Research（Salesforce研究院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究院）
Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question. This paper introduces a new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions. Our retriever model trains a recurrent neural network that learns to sequentially retrieve evidence paragraphs in the reasoning path by conditioning on the previously retrieved documents. Our reader model ranks the reasoning…
Shenzhen Graduate School, Harbin Institute of Technology（哈尔滨工业大学深圳研究生院）；College of Mathematics and Computer Science, Fuzhou University（福州大学数学与计算机科学学院）；School of Engineering and Applied Science, Aston University（阿斯顿大学工程与应用科学学院）；Guangdong Provincial Engineering Technology Research Center for Data Science（广东省数据科学工程技术研究中心）；Department of Computing, the Hong Kong Polytechnic University（香港理工大学计算学系）
Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by recent advances in using deep memory networks for question answering (QA), we propose a new approach which considers emotion cause identification as a reading comprehension task in QA. Inspired by convolutional neural networks, we propose a new mechanism to store relevant context in different memory slots to model context information. Our proposed approach can extract both word level sequence features and lexical feat…
Knowledge graph simple question answering (KGSQA), in its standard form, does not take into account that human-curated question answering training data only cover a small subset of the relations that exist in a Knowledge Graph (KG), or even worse, that new domains covering unseen and rather different to existing domains relations are added to the KG. In this work, we study KGSQA in a previously unstudied setting where new, unseen domains are added during test time. In this setting, question-answer pairs of the new domain do not appear during training, thus making the task more challenging. We …
School of Information, University of Arizona（亚利桑那大学信息学院）
Question Answering for complex questions is often modeled as a graph construction or traversal task, where a solver must build or traverse a graph of facts that answer and explain a given question. This "multi-hop" inference has been shown to be extremely challenging, with few models able to aggregate more than two facts before being overwhelmed by "semantic drift", or the tendency for long chains of facts to quickly drift off topic. This is a major barrier to current inference models, as even elementary science questions require an average of 4 to 6 facts to answer and explain. In this work w…
Generative question answering (QA) models generate answers to questions either solely based on the parameters of the model (the closed-book setting) or additionally retrieving relevant evidence (the open-book setting). Generative QA models can answer some relatively complex questions, but the mechanism through which they do so is still poorly understood. We perform several studies aimed at better understanding the multi-hop reasoning capabilities of generative QA models. First, we decompose multi-hop questions into multiple corresponding single-hop questions, and find marked inconsistency in Q…
Japan Advanced Institute of Science and Technology (JAIST)（日本先端科学技术大学院大学）；Hung Yen University of Education and Technology (UTEHY)（兴安教育技术大学）
In the context of the Competition on Legal Information Extraction/Entailment (COLIEE), we propose a method comprising the necessary steps for finding relevant documents to a legal question and deciding on textual entailment evidence to provide a correct answer. The proposed method is based on the combination of several lexical and morphological characteristics, to build a language model and a set of features for Machine Learning algorithms. We provide a detailed study on the proposed method performance and failure cases, indicating that it is competitive with state-of-the-art approaches on Leg…
University of Washington（华盛顿大学）；Google Research（谷歌研究院）；Allen Institute for AI（艾伦人工智能研究所）；Clova AI；NAVER；Korea University（高丽大学）
Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query. In this paper, we introduce the query-agnostic indexable representation of document phrases that can drastically speed up open-domain QA and also allows us to reach long-tail targets. In particular, our dense-sparse phrase encoding effectively captures syntactic, semantic, and lexical information of the phrases and eliminates the pipeline filtering of context documents. Leveraging optimization strategies, our model can be …
University of Pennsylvania（宾夕法尼亚大学）；Google Research（谷歌研究院）
A desirable property of a reference-based evaluation metric that measures the content quality of a summary is that it should estimate how much information that summary has in common with a reference. Traditional text overlap based metrics such as ROUGE fail to achieve this because they are limited to matching tokens, either lexically or via embeddings. In this work, we propose a metric to evaluate the content quality of a summary using question-answering (QA). QA-based methods directly measure a summary's information overlap with a reference, making them fundamentally different than text overl…
Tsinghua University（清华大学）；Institute for Artificial Intelligence（人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Beijing University of Posts and Telecommunications（北京邮电大学）
Unsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language models to score candidate choices directly conditioned on the question or context. However, such scores from language models can be easily affected by irrelevant factors, such as word frequencies, sentence structures, etc. These distracting factors may not only mislead the model to choose a wrong answer but also make it oversensitive to lexical perturbations in candidate answers. In this paper, we present a novel SEmant…
Sun Yat-sen University（中山大学）；University of California（加利福尼亚大学）；Duke University（杜克大学）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
Commonsense question answering requires reasoning about everyday situations and causes and effects implicit in context. Typically, existing approaches first retrieve external evidence and then perform commonsense reasoning using these evidence. In this paper, we propose a Self-supervised Bidirectional Encoder Representation Learning of Commonsense (elBERto) framework, which is compatible with off-the-shelf QA model architectures. The framework comprises five self-supervised tasks to force the model to fully exploit the additional training signals from contexts containing rich commonsense. The …
Shanghai University（上海大学）；Beijing University of Technology（北京工业大学）；Engineering Research Center of Intelligence Perception and Autonomous Control, Ministry of Education（教育部智能感知与自主控制工程研究中心）
Knowledge Graph Question Answering (KGQA) aims to answer user-questions from a knowledge graph (KG) by identifying the reasoning relations between topic entity and answer. As a complex branch task of KGQA, multi-hop KGQA requires reasoning over the multi-hop relational chain preserved in KG to arrive at the right answer. Despite recent successes, the existing works on answering multi-hop complex questions still face the following challenges: i) The absence of an explicit relational chain order reflected in user-question stems from a misunderstanding of a user's intentions. ii) Incorrectly capt…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Cornell University（康奈尔大学）；Tencent AI Lab（腾讯人工智能实验室）
We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus. In this work, we explore simple yet effective methods for exploiting two sources of external knowledge for subject-area QA. The first enriches the original subject-area reference corpus with relevant text snippets extracted from an open-domain resource (i.e., Wikipedia) that cover potentially ambiguous concepts in the question and answer options. As in other QA research, the second method simply …
Numerical reasoning skills are essential for complex question answering (CQA) over text. It requires opertaions including counting, comparison, addition and subtraction. A successful approach to CQA on text, Neural Module Networks (NMNs), follows the programmer-interpreter paradigm and leverages specialised modules to perform compositional reasoning. However, the NMNs framework does not consider the relationship between numbers and entities in both questions and paragraphs. We propose effective techniques to improve NMNs' numerical reasoning capabilities by making the interpreter question-awar…
University of Arizona（亚利桑那大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究院）
A common model for question answering (QA) is that a good answer is one that is closely related to the question, where relatedness is often determined using general-purpose lexical models such as word embeddings. We argue that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings. With causality as a use case, we implement this insight in three steps. First, we generate causal embeddings cost-effectively by bootstrapping cause-effect pairs extracted…
Yale University（耶鲁大学）；Allen Institute for AI（艾伦人工智能研究所）
Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information for reasoning. The retrieval model is typically trained to maximize the likelihood of the labeled supporting evidence. However, when retrieving from large text corpora such as Wikipedia, the correct answer can often be obtained from multiple evidence candidates. Moreover, not all such candidates are labeled as positive during annotation, rendering the training signal weak and noisy. This problem is exacerbated when the questions are unanswerable or when t…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；IBM Research（IBM研究院）
We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the w…
SOKENDAI（综合研究大学院大学）；Database Center for Life Science（生命科学数据库中心）；National Bioscience Database Center（国家生物科学数据库中心）；The University of Tokyo（东京大学）
Systematic benchmark evaluation plays an important role in the process of improving technologies for Question Answering (QA) systems. While currently there are a number of existing evaluation methods for natural language (NL) QA systems, most of them consider only the final answers, limiting their utility within a black box style evaluation. Herein, we propose a subdivided evaluation approach to enable finer-grained evaluation of QA systems, and present an evaluation tool which targets the NL question (NLQ) interpretation step, an initial step of a QA pipeline. The results of experiments using…
University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
To extract answers from a large corpus, open-domain question answering (QA) systems usually rely on information retrieval (IR) techniques to narrow the search space. Standard inverted index methods such as TF-IDF are commonly used as thanks to their efficiency. However, their retrieval performance is limited as they simply use shallow and sparse lexical features. To break the IR bottleneck, recent studies show that stronger retrieval performance can be achieved by pretraining a effective paragraph encoder that index paragraphs into dense vectors. Once trained, the corpus can be pre-encoded int…
Ontology-based approach to the Natural Language Understanding (NLU) processing allows to improve questions answering quality in dialogue systems. We describe our NLU engine architecture and evaluate its implementation. The engine transforms user input into the SPARQL SELECT, ASK or INSERT query to the knowledge graph provided by the ontology-based data virtualization platform. The transformation is based on the lexical level of the knowledge graph built according to the Ontolex ontology. The described approach can be applied for graph data population tasks and to the question answering systems…
We study calibration in question answering, estimating whether model correctly predicts answer for each question. Unlike prior work which mainly rely on the model's confidence score, our calibrator incorporates information about the input example (e.g., question and the evidence context). Together with data augmentation via back translation, our simple approach achieves 5-10% gains in calibration accuracy on reading comprehension benchmarks. Furthermore, we present the first calibration study in the open retrieval setting, comparing the calibration accuracy of retrieval-based span prediction m…
Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of neural networks to match a question with all predefined relations. In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is sele…
