Supertagging with CCG primitives

Aditya Bhargava, Gerald Penn


Abstract
In CCG and other highly lexicalized grammars, supertagging a sentence’s words with their lexical categories is a critical step for efficient parsing. Because of the high degree of lexicalization in these grammars, the lexical categories can be very complex. Existing approaches to supervised CCG supertagging treat the categories as atomic units, even when the categories are not simple; when they encounter words with categories unseen during training, their guesses are accordingly unsophisticated. In this paper, we make use of the primitives and operators that constitute the lexical categories of categorial grammars. Instead of opaque labels, we treat lexical categories themselves as linear sequences. We present an LSTM-based model that replaces standard word-level classification with prediction of a sequence of primitives, similarly to LSTM decoders. Our model obtains state-of-the-art word accuracy for single-task English CCG supertagging, increases parser coverage and F1, and is able to produce novel categories. Analysis shows a synergistic effect between this decomposed view and incorporation of prediction history.
Anthology ID:
2020.repl4nlp-1.23
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:
194–204
Language:
URL:
https://aclanthology.org/2020.repl4nlp-1.23
DOI:
10.18653/v1/2020.repl4nlp-1.23
Bibkey:
Cite (ACL):
Aditya Bhargava and Gerald Penn. 2020. Supertagging with CCG primitives. In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 194–204, Online. Association for Computational Linguistics.
Cite (Informal):
Supertagging with CCG primitives (Bhargava & Penn, RepL4NLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.repl4nlp-1.23.pdf
Video:
 http://slideslive.com/38929789