HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering

Pang, Liang; Lan, Yanyan; Guo, Jiafeng; Xu, Jun; Su, Lixin; Cheng, Xueqi

doi:10.1609/aaai.v33i01.33016875

Cited by 37 publications

(28 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) TriviaQA: TriviaQA unfiltered version (Joshi et al, 2017) are used. Following Pang et al (2019), we randomly hold out 5,000 QA pairs from the original training set as our validation set, and take the remaining pairs as our new training set. The original development set is used as our test set.…”

Section: Methodsmentioning

confidence: 99%

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

Wang

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

188

120

View full text Add to dashboard Cite

BERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training instances, which may cause incomparable scores for answers from different passages. To tackle this issue, we propose a multi-passage BERT model to globally normalize answer scores across all passages of the same question, and this change enables our QA model find better answers by utilizing more passages. In addition, we find that splitting articles into passages with the length of 100 words by sliding window improves performance by 4%. By leveraging a passage ranker to select high-quality passages, multipassage BERT gains additional 2%. Experiments on four standard benchmarks showed that our multi-passage BERT outperforms all state-of-the-art models on all benchmarks. In particular, on the OpenSQuAD dataset, our model gains 21.4% EM and 21.5% F 1 over all non-BERT models, and 5.8% EM and 6.5% F 1 over BERT-based models. 1

show abstract

Section: Methodsmentioning

confidence: 99%

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

Wang

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

188

120

View full text Add to dashboard Cite

show abstract

“…In multi-passage setting, there may be more than one possible answers among which some are not the right answers to the question. Instead of selecting the first match span as the right answer, Pang et al [55] propose three other heuristic methods. RAND operation treats all answer spans equally and chooses one randomly from them while MAX operation chooses the one with maximum probability and can be used if there are noisy paragraphs.…”

Section: -Evidence Aggregationmentioning

confidence: 99%

Neural Machine Reading Comprehension: Methods and Trends

et al. 2019

View full text Add to dashboard Cite

Machine Reading Comprehension (MRC), which requires the machine to answer questions based on the given context, has gained increasingly wide attention with the incorporation of various deep learning techniques over the past few years. Although the research of MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey to summarize existing approaches and recent trends, which motivates our work presented in this article. Specifically, we give a thorough review of this research field, covering different aspects including (1) typical MRC tasks: their definitions, differences and representative datasets; (2) general architecture of neural MRC: the main modules and prevalent approaches to each of them; and (3) new trends: some emerging focuses in neural MRC as well as the corresponding challenges. Last but not least, in retrospect of what has been achieved so far, the survey also envisages what the future may hold by discussing the open issues left to be addressed. * Work in progress.

show abstract

“…Wang et al (2018b) explore two kinds of answer rerankers in an existing retrieve-read pipeline system. There are some other works that handle this task in different perspectives, such as using hierarchical answer span representations (Pang et al, 2019), modeling the interaction between the retriever and the reader (Das et al, 2019), and so on.…”

Section: Related Workmentioning

confidence: 99%

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

Hu¹,

Peng²,

Huang³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

This 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 overall performance. However, the pipeline system is inefficient since the input is re-encoded within each module, and is unable to leverage upstream components to help downstream training. In this work, we present RE 3 QA, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. Unlike previous pipelined approaches, RE 3 QA shares contextualized text representation across different components, and is carefully designed to use high-quality upstream outputs (e.g., retrieved context or candidate answers) for directly supervising downstream modules (e.g., the reader or the reranker). As a result, the whole network can be trained end-to-end to avoid the context inconsistency problem. Experiments show that our model outperforms the pipelined baseline and achieves state-ofthe-art results on two versions of TriviaQA and two variants of SQuAD.

show abstract

HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering

Cited by 37 publications

References 10 publications

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

Neural Machine Reading Comprehension: Methods and Trends

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

Contact Info

Product

Resources

About