Alignment by agreement
We present an unsupervised approach to symmetric word alignment in which two simple asymmetric models are trained jointly to maximize a combination of data likelihood and agreem...
Publications
3 shownKnow What You Don’t Know: Unanswerable Questions for SQuAD
Extractive reading comprehension systems can often locate the correct answer to a question in a context document, but they also tend to make unreliable guesses on questions for ...
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Xiang Lisa Li, Percy Liang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Langua...
Frequent Co-Authors
Researcher Info
- h-index
- 3
- Publications
- 3
- Citations
- 4,460
- Institution
- Berkeley College
External Links
Identifiers
- ORCID
- 0000-0002-0458-6139
Impact Metrics
h-index
3
h-index: Number of publications with at least h citations each.