Supertagging: an approach to almost parsing

TLDR

Supertags in LTAG encode both phrase‑structure and dependency information, increasing the number of lexical descriptions and thereby raising local parsing ambiguity. The authors propose a robust parsing approach that localizes linguistic structure by associating lexical items with rich supertags and leveraging statistical techniques, enabling parsing of full sentences and fragments. Each lexical item is linked to multiple supertags, each encoding constraints for a specific syntactic context, and disambiguated supertags form an almost‑parse that the parser combines into a full parse. Statistical distributions of supertag co‑occurrences from a parse corpus resolve the local ambiguity, and the method was tested within the LTAG framework.

Abstract

In this paper, we have proposed novel methods for robust parsing that integrate the flexibility of linguistically motivated lexical descriptions with the robustness of statistical techniques. Our thesis is that the computation of linguistic structure can be localized if lexical items are associated with rich descriptions (supertags) that impose complex constraints in a local context. The supertags are designed such that those elements on which the lexical item imposes constraints appear within a given supertag. Further, each lexical item is associated with as many supertags as the number of different syntactic contexts in which the lexical item can appear. This makes the number of different descriptions for each lexical item much larger than when the descriptions are less complex, thus increasing the local ambiguity for a parser. But this local ambiguity can be resolved by using statistical distributions of supertag co-occurrences collected from a corpus of parses. We have explored these ideas in the context of the Lexicalized Tree-Adjoining Grammar (LTAG) framework. The supertags in LTAG combine both phrase structure information and dependency information in a single representation. Supertag disambiguation results in a representation that is effectively a parse (an almost parse), and the parser need only combine the individual supertags. This method of parsing can also be used to parse sentence fragments such as in spoken utterances where the disambiguated supertag sequence may not combine into a single structure.