A Cross-Task Analysis of Text Span Representations
Shubham Toshniwal, Haoyue Shi, Bowen Shi, Lingyu Gao, Karen Livescu, Kevin Gimpel
Abstract
Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive research has focused on functional architectures for representing words and sentences, there is less work on representing arbitrary spans of text within sentences. In this paper, we conduct a comprehensive empirical evaluation of six span representation methods using eight pretrained language representation models across six tasks, including two tasks that we introduce. We find that, although some simple span representations are fairly reliable across tasks, in general the optimal span representation varies by task, and can also vary within different facets of individual tasks. We also find that the choice of span representation has a bigger impact with a fixed pretrained encoder than with a fine-tuned encoder.- Anthology ID:
- 2020.repl4nlp-1.20
- Volume:
- Proceedings of the 5th Workshop on Representation Learning for NLP
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Spandana Gella, Johannes Welbl, Marek Rei, Fabio Petroni, Patrick Lewis, Emma Strubell, Minjoon Seo, Hannaneh Hajishirzi
- Venue:
- RepL4NLP
- SIG:
- SIGREP
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 166–176
- Language:
- URL:
- https://aclanthology.org/2020.repl4nlp-1.20
- DOI:
- 10.18653/v1/2020.repl4nlp-1.20
- Cite (ACL):
- Shubham Toshniwal, Haoyue Shi, Bowen Shi, Lingyu Gao, Karen Livescu, and Kevin Gimpel. 2020. A Cross-Task Analysis of Text Span Representations. In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 166–176, Online. Association for Computational Linguistics.
- Cite (Informal):
- A Cross-Task Analysis of Text Span Representations (Toshniwal et al., RepL4NLP 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.repl4nlp-1.20.pdf
- Code
- shtoshni92/span-rep