Contextualized Word Representations for Reading Comprehension

Shimi Salant, Jonathan Berant


Abstract
Reading a document and extracting an answer to a question about its content has attracted substantial attention recently. While most work has focused on the interaction between the question and the document, in this work we evaluate the importance of context when the question and document are processed independently. We take a standard neural architecture for this task, and show that by providing rich contextualized word representations from a large pre-trained language model as well as allowing the model to choose between context-dependent and context-independent word representations, we can obtain dramatic improvements and reach performance comparable to state-of-the-art on the competitive SQuAD dataset.
Anthology ID:
N18-2088
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
554–559
Language:
URL:
https://aclanthology.org/N18-2088
DOI:
10.18653/v1/N18-2088
Bibkey:
Cite (ACL):
Shimi Salant and Jonathan Berant. 2018. Contextualized Word Representations for Reading Comprehension. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 554–559, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Contextualized Word Representations for Reading Comprehension (Salant & Berant, NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2088.pdf
Code
 shimisalant/CWR
Data
SQuAD