Decontextualization: Making Sentences Stand-Alone

Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, Michael Collins


Abstract
Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context. Taking excerpts of text can be problematic, as key pieces may not be explicit in a local window. We isolate and define the problem of sentence decontextualization: taking a sentence together with its context and rewriting it to be interpretable out of context, while preserving its meaning. We describe an annotation procedure, collect data on the Wikipedia corpus, and use the data to train models to automatically decontextualize sentences. We present preliminary studies that show the value of sentence decontextualization in a user-facing task, and as preprocessing for systems that perform document understanding. We argue that decontextualization is an important subtask in many downstream applications, and that the definitions and resources provided can benefit tasks that operate on sentences that occur in a richer context.
Anthology ID:
2021.tacl-1.27
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
447–461
Language:
URL:
https://aclanthology.org/2021.tacl-1.27
DOI:
10.1162/tacl_a_00377
Bibkey:
Cite (ACL):
Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, and Michael Collins. 2021. Decontextualization: Making Sentences Stand-Alone. Transactions of the Association for Computational Linguistics, 9:447–461.
Cite (Informal):
Decontextualization: Making Sentences Stand-Alone (Choi et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.27.pdf
Video:
 https://aclanthology.org/2021.tacl-1.27.mp4