Retrospective Reader for Machine Reading Comprehension

By Zhuosheng Zhang, Junjie Yang, Hai Zhao. 2020

241 citations recorded by the source corpus.

Machine reading comprehension (MRC) is an AI challenge that requires machines to determine the correct answers to questions based on a given passage. MRC systems must not only answer questions when necessary but also tactfully abstain from answering when no answer is available according to the given passage. When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder, though the latest practice on MRC modeling still mostly benefits from adopting well pre-trained language models as the encoder block by only focusing on the "reading". This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions. Inspired by how humans solve reading comprehension questions, we proposed a retrospective reader (Retro-Reader) that integrates two stages of reading and verification strategies: 1) sketchy reading that briefly investigates the overall interactions of passage and question, and yields an initial judgment; 2) intensive reading that verifies the answer and gives the final prediction. The proposed reader is evaluated on two benchmark MRC challenge datasets SQuAD2.0 and NewsQA, achieving new state-of-the-art results. Significance tests show that our model is significantly better than strong baselines.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Question Answering & Reading Comprehension

Citations in the corpus

UnifiedQA: Crossing Format Boundaries With a Single QA System (2020, methodology): “For completeness, we include the highest previous scores for each dataset; one must be careful when reading these numbers as the best previous numbers follow the fully supervised protocol (for NewsQA (Zhang et al., 2020), Quoref (Segal et al.”
Pre-trained models for natural language processing: A survey (2020, background): “[208] proposed a retrospective reader architecture and initialize the encoder with PTM (e.”
Explanations for CommonsenseQA: New Dataset and Models (2021, background): “The ﬁeld of automated question answering (QA) has witnessed a rapid progress in the past few years, sometimes beating even human performance (Zhang et al., 2020).”
BioMRC: A Dataset for Biomedical Machine Reading Comprehension (2020, methodology): “We also plan to experiment with other MRC models that recently performed particularly well on opendomain MRC datasets (Zhang et al., 2020).”
From LSAT: The Progress and Challenges of Complex Reasoning (2021, background): “Recent pre-trained language models [63, 64] and diverse attention modules [96, 21] achieve state-of-the-art performance on them, and even exceed human performance.”
Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering (2021, background): “Regarding unanswerable questions, their importance in QA (and therefore their inclusion in benchmark datasets) has been argued by works such as Clark and Gardner (2018), Rajpurkar et al. (2018) and Zhu et al. (2019).”
ReasonBERT: Pre-trained to Reason with Distant Supervision (2021, methodology): “The conventional method to train an MRC model usually relies on large-scale supervised training data (Chen et al., 2017; Zhang et al., 2020).”
A large language model for electronic health records (2022, background): “0 31 .”