Ubertagging: Joint Segmentation and Supertagging for English

Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1201–1212, Seattle, Washington, USA, 18-21 October 2013. c⃝2013 Association for Computational Linguistics Ubertagging: Joint segmentation and supertagging for English Rebecca Dridan Institutt for Informatikk Universitetet i Oslo rdridan@ifi.uio.no Abstract A precise syntacto-semantic analysis of En- glish requires a large detailed lexicon with the possibility of treating multiple tokens as a sin- gle meaning-bearing unit, a word-with-spaces. However parsing with such a lexicon, as in- cluded in the English Resource Grammar, can be very slow. We show that we can apply supertagging techniques over an ambiguous token lattice without resorting to previously used heuristics, a process we call ubertagging. Our model achieves an ubertagging accuracy that can lead to a four to eight fold speed up while improving parser accuracy. 1 Introduction and Motivation Over the last decade or so, supertagging has become a standard method for increasing parser efficiency for heavily lexicalised grammar formalisms such as LTAG (Bangalore and Joshi, 1999), CCG (Clark and Curran, 2007) and HPSG (Matsuzaki et al., 2007). In each of these systems, fine-grained lexical cate- gories, known as supertags, are used to prune the parser search space prior to full syntactic parsing, leading to faster parsing at the risk of removing nec- essary lexical items. Various methods are used to configure the degree of pruning in order to balance this trade-off. The English Resource Grammar (ERG; Flickinger (2000)) is a large hand-written HPSG- based grammar of English that produces fine- grained syntacto-semantic analyses. Given the high level of lexical ambiguity in its lexicon, parsing with the ERG should therefore also benefit from supertagging, but while various attempts have shown possibilities (Blunsom, 2007; Dridan et al., 2008; Dridan, 2009), supertagging is still not a standard element in the ERG parsing pipeline. There are two main reasons for this. The first is that the ERG lexicon does not assign simple atomic categories to words, but instead builds complex structured signs from information about lemmas and lexical rules, and hence the shape and integration of the supertags is not straightforward. Bangalore and Joshi (2010) define a supertag as a primitive structure that contains all the information about a lexical item, including argument structure, and where the arguments should be found. Within the ERG, that information is not all contained in the lexicon, but comes from different places. The choice, therefore, of what information may be predicted prior to parsing and how it should be integrated into parsing is an open question. The second reason that supertagging is not stan- dard with ERG processing is one that is rarely con- sidered when processing English, namely ambigu- ous segmentation. In most mainstream English pars- ing, the segmentation of parser input into tokens that will become the leaves of the parse tree is consid- ered a fixed, unambiguous process. While recent work (Dridan and Oepen, 2012) has shown that pro- ducing even these tokens is not a solved problem, the issue we focus on here is the ambiguous …

Content truncated to 500 words