作者:孙嘉伟
单位:燕山大学
就在5月23号,NAACL终于放出接收论文目录啦。
论文列表:https://www.aclweb.org/anthology/events/naacl-2021/
NAACL作为NLP的顶会之一,接收的论文质量也非常之高,其中有不少关于阅读理解&问答领域相关的文章以供大家研究参考。作为一个从事该研究领域的研究生(小学生),在这里整理了2021年NAACL阅读理解和问答领域的相关文章并对阅读理解领域的发展进行了一个小结。笔者根据自己的研究方向对部分文章做了简短的注释,下边按照论文的研究详细方向进行逐一介绍。
阅读理解和问答领域相关论文共计29篇,其中:
开放域问答(5篇):
Open Domain Question Answering over Tables via Dense Retrieval | https://www.aclweb.org/anthology/2021.naacl-main.43/ |
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering | https://www.aclweb.org/anthology/2021.naacl-main.466/ |
Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering | https://www.aclweb.org/anthology/2021.naacl-main.468/ |
SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval | https://www.aclweb.org/anthology/2021.naacl-main.47/ |
RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering | https://www.aclweb.org/anthology/2021.naacl-main.100/ |
1.
标题:Open Domain Question Answering over Tables via Dense Retrieval
链接:https://www.aclweb.org/anthology/2021.naacl-main.43.pdf
摘要:Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context. We present an effective pre-training procedure for our retriever and improve retrieval quality with mined hard negatives. As relevant datasets are missing, we extract a subset of NATURAL QUESTIONS (Kwiatkowski et al., 2019) into a Table QA dataset. We find that our retriever improves retrieval results from 72.0 to 81.1 recall@10 and end-to-end QA results from 33.8 to 37.7 exact match, over a BERT based retriever.
在TableQA上的开放域问答
2.
标题:RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
链接:https://www.aclweb.org/anthology/2021.naacl-main.466.pdf
摘要:In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and passages for semantic matching. However, it is difficult to effectively train a dual-encoder due to the challenges including the discrepancy between training and inference, the existence of unlabeled positives and limited training data. To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. We make three major technical contributions in RocketQA, namely crossbatch negatives, denoised hard negatives and data augmentation. The experiment results show that RocketQA significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions. We also conduct extensive experiments to examine the effectiveness of the three strategies in RocketQA.
Besides, we demonstrate that the performance of end-to-end QA can be improved based on our RocketQA retriever
提出了3种优化用于检索候选答案段落的DPR(Dense Passage Retrieval)算法的方法:跨批次负采样、去噪强负例采样、数据增强。在MARCO 和 Natural Questions数据集上做到了SOTA
3.
标题:Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering
链接:https://www.aclweb.org/anthology/2021.naacl-main.468.pdf
摘要:In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closedbook QA models. However, it is also known to suffer from its large storage footprint due to its document corpus and index. Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-andread open-domain QA system by up to 160x.Our results indicate that retrieve-and-read can be a viable option even in a highly constrained serving environment such as edge devices, as we show that it can achieve better accuracy than a purely parametric model with comparable docker-level system size.
基于retrieve-and-read方式的问答系统往往需要一个很大的知识、语料检索库,作者提出了用于减小该检索库存储空间大小的方法。实验中结果表明原系统的内存占用大小变为原来的1/160,在dev和test集上准确率下降了2.45%和4%。
4.
标题:SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
链接:https://www.aclweb.org/anthology/2021.naacl-main.47.pdf
摘要:Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context. We present an effective pre-training procedure for our retriever and improve retrieval quality with mined hard negatives. As relevant datasets are missing, we extract a subset of NATURAL QUESTIONS (Kwiatkowski et al., 2019) into a Table QA dataset. We find that our retriever improves retrieval results from 72.0 to 81.1 recall@10 and end-to-end QA results from 33.8 to 37.7 exact match, over a BERT based retriever.
提出了一种用于检索答案候选段落的方法:使用token级别的表示替换原有句子级别的表示来进行query与answer的交互。在多个数据集上效果优秀。
5.
标题:RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering
链接:https://www.aclweb.org/anthology/2021.naacl-main.100.pdf
摘要:State-of-the-art Machine Reading Comprehension (MRC) models for Open-domain Question Answering (QA) are typically trained for span selection using distantly supervised positive examples and heuristically retrieved negative examples. This training scheme possibly explains empirical observations that these models achieve a high recall amongst their top few predictions, but a low overall accuracy, motivating the need for answer re-ranking.
We develop a successful re-ranking approach (RECONSIDER) for span-extraction tasks that improves upon the performance of MRC models, even beyond large-scale pre-training. RECONSIDER is trained on positive and negative examples extracted from high confidence MRC model predictions, and uses in-passage span annotations to perform span-focused reranking over a smaller candidate set. As a result, RECONSIDER learns to eliminate close false positives, achieving a new extractive state of the art on four QA tasks, with 45.5% Exact Match accuracy on Natural Questions with real user questions, and 61.7% on TriviaQA.We will release all related data, models, and code
解决开放域问答中由于MRC模块无法区分语义相似的错误答案而出错的问题,提出一种对答案重新排序的方法,该方法进一步提高了四个数据集上SOTA算法的准确性。
QA数据集(3篇):
A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers | https://www.aclweb.org/anthology/2021.naacl-main.365/ |
Open-Domain Question Answering Goes Conversational via Question Rewriting | https://www.aclweb.org/anthology/2021.naacl-main.44/ |
SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning | https://www.aclweb.org/anthology/2021.naacl-main.364/ |
1.
标题:A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
链接:https://www.aclweb.org/anthology/2021.naacl-main.365.pdf
摘要:Readers of academic research papers often read with the goal of answering specific questions. Question Answering systems that can answer those questions can make consump