Haichao Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haichao Zhu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Furu Wei
Microsoft Research Asia, Beijing, China
2 shared publicationsLi Dong
Microsoft Research Asia, Beijing, China
2 shared publicationsTing Liu
Faculty of Computing, Harbin Institute of Technology, Harbin, China
2 shared publicationsBing Qin
1 shared publication- Bing Qin
Harbin Institute of Technology, Harbin, China
1 shared publication Wenhui Wang
1 shared publication
Latest Publications
- 3 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 30 (23299290) , 2357-2367
Transforming Wikipedia Into Augmented Data for Query-Focused Summarization
The limited size of existing query-focused summarization datasets renders training data-driven summarization models challenging. Meanwhile, the manual construction of a query-focused summarization corpus is costly and time-consuming. In this paper, we use Wikipedia to automatically collect a large query-focused summarization dataset (named W iki R ef ) of more than 280,000 examples, which can serve as a means of data augmentation. We also develop a BERT-based query-focused summarization model (Q-BERT) to extract sentences from the documents as summaries. To better adapt a huge model containing millions of parameters to tiny benchmarks, we identify and fine-tune only a sparse subnetwork, which corresponds to a small fraction of the whole model parameters. Experimental results on three DUC benchmarks show that the model pre-trained on W iki R ef has already achieved reasonable performance. After fine-tuning on the specific benchmark datasets, the model with data augmentation outperforms strong comparison systems. Moreover, both our proposed Q-BERT model and subnetwork fine-tuning further improve the model performance.
- 3 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 30 (23299290) , 2357-2367
Transforming Wikipedia Into Augmented Data for Query-Focused Summarization
The limited size of existing query-focused summarization datasets renders training data-driven summarization models challenging. Meanwhile, the manual construction of a query-focused summarization corpus is costly and time-consuming. In this paper, we use Wikipedia to automatically collect a large query-focused summarization dataset (named W iki R ef ) of more than 280,000 examples, which can serve as a means of data augmentation. We also develop a BERT-based query-focused summarization model (Q-BERT) to extract sentences from the documents as summaries. To better adapt a huge model containing millions of parameters to tiny benchmarks, we identify and fine-tune only a sparse subnetwork, which corresponds to a small fraction of the whole model parameters. Experimental results on three DUC benchmarks show that the model pre-trained on W iki R ef has already achieved reasonable performance. After fine-tuning on the specific benchmark datasets, the model with data augmentation outperforms strong comparison systems. Moreover, both our proposed Q-BERT model and subnetwork fine-tuning further improve the model performance.
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 4238-4248
Learning to Ask Unanswerable Questions for Machine Reading Comprehension
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 4238-4248
Open AccessLearning to Ask Unanswerable Questions for Machine Reading Comprehension