Linguistic representations in multi-task neural networks for ellipsis resolution

Ola Rønning, Daniel Hardt, Anders Søgaard


Abstract
Sluicing resolution is the task of identifying the antecedent to a question ellipsis. Antecedents are often sentential constituents, and previous work has therefore relied on syntactic parsing, together with complex linguistic features. A recent model instead used partial parsing as an auxiliary task in sequential neural network architectures to inject syntactic information. We explore the linguistic information being brought to bear by such networks, both by defining subsets of the data exhibiting relevant linguistic characteristics, and by examining the internal representations of the network. Both perspectives provide evidence for substantial linguistic knowledge being deployed by the neural networks.
Anthology ID:
W18-5409
Volume:
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Tal Linzen, Grzegorz Chrupała, Afra Alishahi
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
66–73
Language:
URL:
https://aclanthology.org/W18-5409
DOI:
10.18653/v1/W18-5409
Bibkey:
Cite (ACL):
Ola Rønning, Daniel Hardt, and Anders Søgaard. 2018. Linguistic representations in multi-task neural networks for ellipsis resolution. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 66–73, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Linguistic representations in multi-task neural networks for ellipsis resolution (Rønning et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/W18-5409.pdf