Abstract
Current supervised parsers are limited by the size of their labelled training data, making improving them with unlabelled data an important goal. We show how a state-of-the-art CCG parser can be enhanced, by predicting lexical categories using unsupervised vector-space embeddings of words. The use of word embeddings enables our model to better generalize from the labelled data, and allows us to accurately assign lexical categories without depending on a POS-tagger. Our approach leads to substantial improvements in dependency parsing results over the standard supervised CCG parser when evaluated on Wall Street Journal (0.8%), Wikipedia (1.8%) and biomedical (3.4%) text. We compare the performance of two recently proposed approaches for classification using a wide variety of word embeddings. We also give a detailed error analysis demonstrating where using embeddings outperforms traditional feature sets, and showing how including POS features can decrease accuracy.
Highlights
Combinatory Categorial Grammar (CCG) is widely used in natural language semantics (Bos, 2008; Kwiatkowski et al, 2010; Krishnamurthy and Mitchell, 2012; Lewis and Steedman, 2013a; Lewis and Steedman, 2013b; Kwiatkowski et al, 2013), largely because of its direct linkage of syntax and semantics
CCG parsers perform at state-of-the-art levels (Rimell et al, 2009; Nivre et al, 2010), fullsentence accuracy is just 25.6% on Wikipedia text, which gives a low upper bound on logical inference approaches to question-answering and textual entailment
Our results show that word embeddings are an effective way of adding distributional information into CCG supertagging
Summary
Combinatory Categorial Grammar (CCG) is widely used in natural language semantics (Bos, 2008; Kwiatkowski et al, 2010; Krishnamurthy and Mitchell, 2012; Lewis and Steedman, 2013a; Lewis and Steedman, 2013b; Kwiatkowski et al, 2013), largely because of its direct linkage of syntax and semantics. This connection means that performance on semantic applications is highly dependent on the quality of the syntactic parse. The supertagger model is overly dependent on POS-features—in Section 4.6 we show that supertagger performance drops dramatically on words which have been assigned an incorrect POS-tag
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the Association for Computational Linguistics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
