SQuAD

AbstractKnowing the quality of reading comprehension (RC) datasets is important for the development of natural-language understanding systems. In this study, two classes of metrics were adopted for evaluating RC datasets: …...

AbstractIn this paper, we present the gated self-matching networks for reading comprehension style question answering, which aims to answer questions from a given passage. We first match the question and …...

AbstractA first step in the task of automatically generating questions for testing reading comprehension is to identify question-worthy sentences, i.e. sentences in a text passage that humans find it worthwhile …...

AbstractFactoid question answering (QA) has recently benefited from the development of deep learning (DL) systems. Neural network models outperform traditional approaches in domains where large datasets exist, such as SQuAD …...

AbstractThis paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training …...

AbstractDeep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this …...

AbstractWe develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network. Given a high performing MC model in one domain, our technique aims to …...

AbstractReading Comprehension (RC) of text is one of the fundamental tasks in natural language processing. In recent years, several end-to-end neural network models have been proposed to solve RC tasks. …...

AbstractIn this paper we present the results of an investigation of the importance of verbs in a deep learning QA system trained on SQuAD dataset. We show that main verbs …...

AbstractAnswer selection is an important but challenging task. Significant progresses have been made in domains where a large amount of labeled training data is available. However, obtaining rich annotated data …...

AbstractIn this paper, we propose a new linguistically-based approach to answering non-factoid open-domain questions from unstructured data. First, we elaborate on an architecture for textual encoding based on which we …...

AbstractTo answer the question in machine comprehension (MC) task, the models need to establish the interaction between the question and the context. To tackle the problem that the single-pass model …...

AbstractBuilding curious machines that can answer as well as ask questions is an important challenge for AI. The two tasks of question answering and question generation are usually tackled separately …...

AbstractExisting research on question answering (QA) and comprehension reading (RC) are mainly focused on the resource-rich language like English. In recent times, the rapid growth of multi-lingual web content has …...

AbstractAlthough current evaluation of question-answering systems treats predictions in isolation, we need to consider the relationship between predictions to measure true understanding. A model should be penalized for answering “no” …...

AbstractDespite the advancement of question answering (QA) systems and rapid improvements on held-out test sets, their generalizability is a topic of concern. We explore the robustness of QA models to …...

AbstractThis paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation …...

AbstractThis paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i.e., previous turns of question-answer …...

AbstractThis paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the …...

AbstractNeural architectures based on self-attention, such as Transformers, recently attracted interest from the research community, and obtained significant improvements over the state of the art in several tasks. We explore …...

AbstractWith social media becoming increasingly popular on which lots of news and real-time events are reported, developing automated question answering systems is critical to the effective-ness of many applications that …...

AbstractObtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what …...

AbstractWe present a voice-based conversational agent which combines the robustness of chatbots and the utility of question answering (QA) systems. Indeed, while data-driven chatbots are typically user-friendly but not goal-oriented, …...

AbstractExtractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text …...

AbstractAnswer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and …...

AbstractArtificial General Intelligence (AGI) is showing growing performance in numerous applications - beating human performance in Chess and Go, using knowledge bases and text sources to answer questions (SQuAD) and …...

AbstractMany extractive question answering models are trained to predict start and end positions of answers. The choice of predicting answers as positions is mainly due to its simplicity and effectiveness. …...

AbstractNatural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high …...

AbstractSelf-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. Existing pre-training techniques employ autoencoding and/or autoregressive objectives to train …...

AbstractTo avoid giving wrong answers, question answering (QA) models need to know when to abstain from answering. Moreover, users often ask questions that diverge from the model’s training data, making …...

AbstractWe introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom …...

AbstractAdvances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able …...

AbstractQuestion Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has …...

AbstractTransformer-based pre-training models like BERT have achieved remarkable performance in many natural language processing tasks. However, these models are both computation and memory expensive, hindering their deployment to resource-constrained devices. …...

AbstractQuestion generation (QG) has recently attracted considerable attention. Most of the current neural models take as input only one or two sentences, and perform poorly when multiple sentences or complete …...

AbstractHumans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore …...

AbstractPre-trained language models (PLMs) have achieved great success in natural language processing. Most of PLMs follow the default setting of architecture hyper-parameters (e.g., the hidden dimension is a quarter of …...

AbstractRecent work has investigated the interesting question using pre-trained language models (PLMs) as knowledge bases for answering open questions. However, existing work is limited in using small benchmarks with high …...

Disfluencies is an under-studied topic in NLP, even though it is ubiquitous in human con- versation. This is largely due to the lack of datasets containing disfluencies. In this paper, …...

AbstractHeavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long …...

AbstractIn several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where …...

AbstractMasked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input …...

AbstractNatural question generation (QG) aims to generate questions from a passage, and generated questions are answered from the passage. Most models with state-of-the-art performance model the previously generated text at …...

AbstractA common approach in many machine learning algorithms involves self-supervised learning on large unlabeled data before fine-tuning on downstream tasks to further improve performance. A new approach for language modelling, …...

AbstractTo fully model human-like ability to ask questions, automatic question generation (QG) models must be able to produce multiple expressions of the same question with different levels of detail. Unfortunately, …...

Transformer is the backbone of modern NLP models. In this paper, we propose Real- Former, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform …...

AbstractSystems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much …...

AbstractMachine reading comprehension (MRC) is one of the most challenging tasks in natural language processing domain. Recent state-of-the-art results for MRC have been achieved with the pre-trained language models, such …...

Pre-trained language models (PTLMs) ac- quire domain-independent linguistic knowl- edge through pre-training with massive textual resources. Additional pre-training is effective in adapting PTLMs to domains that are not well covered …...

AbstractA flaw in QA evaluation is that annotations often only provide one gold answer. Thus, model predictions semantically equivalent to the answer but superficially different are considered incorrect. This work …...

AbstractWe propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed …...

AbstractPowerful generative models have led to recent progress in question generation (QG). However, it is difficult to measure advances in QG research since there are no standardized resources that allow …...

AbstractThe development of over-parameterized pre-trained language models has made a significant contribution toward the success of natural language processing. While over-parameterization of these models is the key to their generalization …...

AbstractAutomatic question generation (AQG) is the task of generating a question from a given passage and an answer. Most existing AQG methods aim at encoding the passage and the answer …...

AbstractThe growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and …...

AbstractData Augmentation (DA) is known to improve the generalizability of deep neural networks. Most existing DA techniques naively add a certain number of augmented samples without considering the quality and …...

AbstractPre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we …...

AbstractMasked language models (MLMs) conventionally mask 15% of tokens due to the belief that more masking would leave insufficient context to learn good representations; this masking rate has been widely …...

AbstractIn the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and …...