Neural Scoring Function for MST Parser

Jindřich Libovický


Abstract
Continuous word representations appeared to be a useful feature in many natural language processing tasks. Using fixed-dimension pre-trained word embeddings allows avoiding sparse bag-of-words representation and to train models with fewer parameters. In this paper, we use fixed pre-trained word embeddings as additional features for a neural scoring function in the MST parser. With the multi-layer architecture of the scoring function we can avoid handcrafting feature conjunctions. The continuous word representations on the input also allow us to reduce the number of lexical features, make the parser more robust to out-of-vocabulary words, and reduce the total number of parameters of the model. Although its accuracy stays below the state of the art, the model size is substantially smaller than with the standard features set. Moreover, it performs well for languages where only a smaller treebank is available and the results promise to be useful in cross-lingual parsing.
Anthology ID:
L16-1110
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
694–698
Language:
URL:
https://aclanthology.org/L16-1110
DOI:
Bibkey:
Cite (ACL):
Jindřich Libovický. 2016. Neural Scoring Function for MST Parser. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 694–698, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Neural Scoring Function for MST Parser (Libovický, LREC 2016)
Copy Citation:
PDF:
https://aclanthology.org/L16-1110.pdf