CoChat

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension

Open access
Yang, An, Wang, Quan, Liu, Jing, Liu, Kai, Lyu, Yajuan, Wu, Hua, She, Qiaoqiao, Li, Sujian · 2019 · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.

Abstract

Machine reading comprehension (MRC) is a crucial and challenging task in NLP.Recently, pre-trained language models (LMs), especially BERT, have achieved remarkable success, presenting new state-of-the-art results in MRC.In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC.We introduce KT-NET, which employs an attention mechanism to adaptively select desired knowledge from KBs, and then fuses selected knowledge with BERT to enable context-and knowledgeaware predictions.We believe this would combine the merits of both deep LMs and curated KBs towards better MRC.Experimental results indicate that KT-NET offers significant and consistent improvements over BERT, outperforming competitive baselines on ReCoRD and SQuAD1.1 benchmarks.Notably, it ranks the 1st place on the ReCoRD leaderboard, and is also the best single model on the SQuAD1.1 leaderboard at the time of submission (March 4th, 2019). 1

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/p19-1226

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 2 Overall architecture of KT-NET (left), with the knowledge integration module illustrated (right).
Figure 2 Overall architecture of KT-NET (left), with the knowledge integration module illustrated (right).CC-BY · From the PDF
Figure 3 Case study. Heat maps present similarities between question (row) and passage (column) words. Line charts show probabilities of answer boundaries. In KT-NET, top 3 most relevant KB concepts are further given.
Figure 3 Case study. Heat maps present similarities between question (row) and passage (column) words. Line charts show probabilities of answer boundaries. In KT-NET, top 3 most relevant KB concepts are further given.CC-BY · From the PDF
Figure 5 Case study. Heat maps present similarities between question (row) and passage (column) words. Line charts show probabilities of answer boundaries. In KT-NET, top 3 most relevant KB concepts are further given.
Figure 5 Case study. Heat maps present similarities between question (row) and passage (column) words. Line charts show probabilities of answer boundaries. In KT-NET, top 3 most relevant KB concepts are further given.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 47 references

Research works printed but not linked: 1

  1. Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018a. Deep contextualized word rep- resentations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227- 2237. Association for Computational Linguistics.

Cited by

See all 156

Metadata

Authors
Yang, A., Wang, Q., Liu, J., Liu, K., Lyu, Y., Wu, H., She, Q., & Li, S.
Affiliations
  • Baidu (China) (CN)
  • Peking University (CN)
Venue
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Published
2019
Pages
2346-2357
ISSN
0736-587X (ISSN-L)
OpenAlex
W2951561177
Cited by
155
References
45
Citations by year
2026: 3 · 2025: 5 · 2024: 16 · 2023: 22 · 2022: 24 · 2021: 47 · 2020: 29 · 2019: 9
FWCI
10.43
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
Funders
  • Baidu
  • National Natural Science Foundation of China (61876009, 61533018, 61876223)
  • Peking University
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
machine reading comprehension, pre-trained language models, BERT, knowledge base, external knowledge integration, knowledge fusion, records

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension. https://app.cochat.ai/papers/10.18653/v1/p19-1226
The paper
Yang, A., Wang, Q., Liu, J., Liu, K., Lyu, Y., Wu, H., She, Q., & Li, S. (2019). Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1226

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.