Paper Info
Title
Treelet Probabilities for HPSG Parsing and Error Correction.
Abstract
Most state-of-the-art parsers aim to produce an analysis for any input despite errors. However, small grammatical mistakes in a sentence often cause a 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 the 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.
Year
Venue
Keywords
2014
LREC 2014 - NINTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION
treelet model,parsing with error correction,English Resource Grammar
Field
DocType
Citations 
Rule-based machine translation,Top-down parsing,S-attributed grammar,Parse tree,Computer science,Bottom-up parsing,Speech recognition,Artificial intelligence,Natural language processing,Parsing,Parser combinator,Sentence
Conference
0
PageRank 
References 
Authors
0.34
12
2
Name
Order
Citations
PageRank
Angelina Ivanova1704.26
van noord268492.89