Generalizing Question Answering System with Pre-trained Language Model Fine-tuning
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
With a large number of datasets being released and new techniques being proposed, Question answering (QA) systems have witnessed great breakthroughs in reading comprehension (RC)tasks. However, most existing methods focus on improving in-domain performance, leaving open the research question of how these mod-els and techniques can generalize to out-of-domain and unseen RC tasks. To enhance the generalization ability, we propose a multi-task learning framework that learns the shared representation across different tasks. Our model is built on top of a large pre-trained language model, such as XLNet, and then fine-tuned on multiple RC datasets. Experimental results show the effectiveness of our methods, with an average Exact Match score of 56.59 and an average F1 score of 68.98, which significantly improves the BERT-Large baseline by8.39 and 7.22, respectively
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.
Integrity signals
Registry
Cites
Statistics
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.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
Graph drawing by force‐directed placement
Fruchterman, T. M. J., & Reingold, E. M. (1991) · Software: Practice and Experience · doi:10.1002/spe.4380211102 · Cited by 6,352
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“The second method is similar to curriculum learning (Bengio et al., 2009), but because of the sparse relation among the datasets, it’s not practical to evaluate the difficulty and the degree of learning.”
MethodTransformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169 · cited 2×
“Model XLNet (Yang et al., 2019) is a recently proposed generalized autoregressive pre-training model for language understanding which naively follows the Transformer(-XL) (Dai et al., 2019) architecture.”
BackgroundNatural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1259 · Cited by 1,804 · cited 3×
“…such as SQuAD (Rajpurkar et al., 2016), NewsQA (Trischler et al., 2017), Trivi-aQA (Joshi et al., 2017), SearchQA (Dunn et al., 2017), HotpotQA (Yang et al., 2018), NaturalQuestions (Kwiatkowski et al., 2019), DROP (Dua et al., 2019), RACE (Lai et al., 2017), DueRC (Saha et al., 2018), BioASQ…”
BackgroundTriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D., & Zettlemoyer, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1147 · Cited by 1,690
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D. S., & Zettlemoyer, L. (2017) · arXiv · doi:10.48550/arxiv.1705.03551 · Cited by 1,650
RACE: Large-scale ReAding Comprehension Dataset From Examinations
Lai, G., Xie, Q., Liu, H., Yang, Y., & Hovy, E. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1082 · Cited by 1,044 · cited 6×
“The fact that the single-task model achieves better performance on RACE than that using the multi-task learning method is related to the higher similarity between RACE and NaturalQuestions, which we can figure out from Figure 2.”
BackgroundInfluential
Cited by
Unifying Large Language Models and Knowledge Graphs: A Roadmap
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3352100 · Cited by 1,376
On the Evolution of Knowledge Graphs: A Survey and Perspective
Jiang, X., Xu, C., Shen, Y., Sun, X., Tang, L., Wang, S., Chen, Z., Wang, Y., & Guo, J. (2023) · arXiv · doi:10.48550/arxiv.2310.04835 · Cited by 42
“Some literature shows that such LLMs can further improve their performances on open-domain QA after fine-tuning [199].”
Read before Generate! Faithful Long Form Question Answering with Machine Reading
Su, D., Li, X., Zhang, J., Shang, L., Jiang, X., Liu, Q., & Fung, P. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.61 · Cited by 37
Self-citationRead before Generate! Faithful Long Form Question Answering with Machine Reading
Su, D., Li, X., Zhang, J., Shang, L., Jiang, X., Liu, Q., & Fung, P. (2022) · arXiv · doi:10.48550/arxiv.2203.00343 · Cited by 37
Self-citationKnowledge Graph-Enhanced Large Language Models via Path Selection
Liu, H., Wang, S., Zhu, Y., Dong, Y., & Li, J. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.376 · Cited by 28
Metadata
- Authors
- Su, D., Xu, Y., Winata, G. I., Xu, P., Kim, H., Liu, Z., & Fung, P.
- Venue
- Proceedings of the 2nd Workshop on Machine Reading for Question Answering
- Published
- 2019
- Pages
- 203-211
- OpenAlex
- W2986836624
- Cited by
- 69
- References
- 17
- FWCI
- 2.90
- Type
- conference paper
- Language
- en
- Open access
- gold
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: Generalizing Question Answering System with Pre-trained Language Model Fine-tuning. https://app.cochat.ai/papers/10.18653/v1/d19-5827
- The paper
- Su, D., Xu, Y., Winata, G. I., Xu, P., Kim, H., Liu, Z., & Fung, P. (2019). Generalizing Question Answering System with Pre-trained Language Model Fine-tuning. Proceedings of the 2nd Workshop on Machine Reading for Question Answering. https://doi.org/10.18653/v1/d19-5827
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.