Treelet Probabilities for HPSG Parsing and Error Correction

Angelina Ivanova, Gertjan van Noord

Abstract
Most state-of-the-art parsers take an approach to produce an analysis for any input despite errors. However, small grammatical mistakes in a sentence often cause parser to fail to build a correct syntactic tree. Applications that can identify and correct mistakes during parsing are particularly interesting for processing user-generated noisy content. Such systems potentially could take advantage of linguistic depth of broad-coverage precision grammars. In order to choose the best correction for an utterance, probabilities of parse trees of different sentences should be comparable which is not supported by discriminative methods underlying parsing software for processing deep grammars. In the present work we assess the treelet model for determining generative probabilities for HPSG parsing with error correction. In the first experiment the treelet model is applied to the parse selection task and shows superior exact match accuracy than the baseline and PCFG. In the second experiment it is tested for the ability to score the parse tree of the correct sentence higher than the constituency tree of the original version of the sentence containing grammatical error.
Anthology ID:
L14-1384
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
2887–2892
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/453_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Angelina Ivanova and Gertjan van Noord. 2014. Treelet Probabilities for HPSG Parsing and Error Correction. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2887–2892, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
Treelet Probabilities for HPSG Parsing and Error Correction (Ivanova & van Noord, LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/453_Paper.pdf
PDF Search