Partial parsing via finite-state cascades

Abstract

Finite-state cascades represent an attractive architecture for parsing unrestricted text. Deterministic parsers specified by finite-state cascades are fast and reliable. They can be extended at modest cost to construct parse trees with finite feature structures. Finally, such deterministic parsers do not necessarily involve trading off accuracy against speed-they may in fact be more accurate than exhaustive-search stochastic contextfree parsers. Finite-State CascadesOf current interest in corpus-oriented computational linguistics are techniques for bootstrapping broad-coverage parsers from text corpora. The work described here is a step along the way toward a bootstrapping scheme that involves inducing a tagger from word distributions, a lowlevel "chunk" parser from a tagged corpus, and lexical dependencies from a chunked corpus. In particular, I describe a chunk parsing technique based on what I will call a finite-state cascade. Though I shall not address the question of inducing such a parser from a corpus, the parsing technique has been implemented and is being used in a project for inducing lexical dependencies from corpora in English and German. The resulting parsers are robust and very fast.A finite-state cascade consists of a sequence of levels. Phrases at one level are built on phrases at the previous level, and there is no recursion: phrases never contain same-level or higher-level phrases. Two levels of special importance are the level of chunks and the level of simplex clauses [2,1]. Chunks are the non-recursive cores of "major" phrases, i.e., NP, VP, PP, AP, AdvP. Simplex clauses are clauses in which embedded clauses have been turned into siblingstail recursion has been replaced with iteration, so to speak. To illustrate, (1) shows a parse tree represented as a sequence of levels.

Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands

“…The learned grammar G is then used to parse new (previously unseen) natural language commands. We compare our technique with (1) a supervised parser (Abney, 1996) trained on labelled data, i.e. pairs of sentences and human-annotated RCL trees, and (2) an unsupervised parser (Ponvert et al 2011) trained on unlabelled sentences, i.e.…”

Extraction of complex index terms in non-English IR: A shallow parsing based approach

“…This situation is even more problematic in the case of Spanish, due to the lack of freely available resources such as grammars, treebanks, etc. In this context, seeking to obtain a compromise between the quality of the syntactic information to be extracted and the ease of its extraction, the employment of shallow parsing techniques (Abney, 1997) enables us both to reduce computational complexity and increase robustness. Shallow parsing has shown itself to be useful in several NLP application fields, particularly in Information Extraction (Aone et al, 1998;Grishman, 1995;Hobbs et al, 1997).…”

Statistical models for the induction and use of selectional preferences

“…Shown are objects of eat found in the British National Corpus (100 million words) (Burnard, 1995), together with their frequency of occurrence. These data were extracted using an automated partial parser (Abney, 1997).…”