Sökning: WFRF:(de Lhoneux Miryam 1990 ) >
Nightmare at test t...
Nightmare at test time : How punctuation prevents parsers from generalizing
-
- Søgaard, Anders (författare)
- University of Copenhagen
-
- de Lhoneux, Miryam, 1990- (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics
-
- Augenstein, Isabelle (författare)
- University of Copenhagen
-
(creator_code:org_t)
- Brussels : Association for Computational Linguistics, 2018
- 2018
- Engelska.
-
Ingår i: Proceedings of the 2018 EMNLP Workshop BlackboxNLP. - Brussels : Association for Computational Linguistics. ; , s. 25-29
- Relaterad länk:
-
http://aclweb.org/an...
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Punctuation is a strong indicator of syntactic structure, and parsers trained on text with punctuation often rely heavily on this signal. Punctuation is a diversion, however, since human language processing does not rely on punctuation to the same extent, and in informal texts, we therefore often leave out punctuation. We also use punctuation ungrammatically for emphatic or creative purposes, or simply by mistake. We show that (a) dependency parsers are sensitive to both absence of punctuation and to alternative uses; (b) neural parsers tend to be more sensitive than vintage parsers; (c) training neural parsers without punctuation outperforms all out-of-the-box parsers across all scenarios where punctuation departs from standard punctuation. Our main experiments are on synthetically corrupted data to study the effect of punctuation in isolation and avoid potential confounds, but we also show effects on out-of-domain data.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
Nyckelord
- dependency parsing
- punctuation
- noisy data
- generalization
- Datorlingvistik
- Computational Linguistics
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)