Papers › Retrospective Reader for Machine Reading Comprehension
Retrospective Reader for Machine Reading Comprehension
Zhuosheng Zhang, Junjie Yang, Hai Zhao
Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. MRC systems must not only answer question when necessary but also distinguish when no answer is available according to the given passage and then tactfully abstain from answering. 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 most 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 yield 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 the strong ELECTRA and ALBERT baselines. A series of analysis is also conducted to interpret the effectiveness of the proposed reader.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | SQuAD2.0 | Retro-Reader (ensemble) | EM | 90.578 | #7 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader (ensemble) | F1 | 92.978 | #7 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader on ALBERT (ensemble) | EM | 90.115 | #19 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader on ALBERT (ensemble) | F1 | 92.580 | #19 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader on ELECTRA (single model) | EM | 89.562 | #29 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader on ELECTRA (single model) | F1 | 92.052 | #29 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader on ALBERT (single model) | EM | 88.107 | #65 of 286 | Archive leaderboard | report |
| Question Answering | SQuAD2.0 | Retro-Reader on ALBERT (single model) | F1 | 91.419 | #65 of 286 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections