TüSBL: A Similarity-Based Chunk Parser for Robust Syntactic Processing

T¨uSBL: A Similarity-Based Chunk Parser for Robust Syntactic Processing Sandra K¨ubler Seminar f¨ur Sprachwissenschaft University of T¨ubingen Wilhelmstr. 113 D-72074 T¨ubingen, Germany kuebler@sfs.nphil.uni-tuebingen.de Erhard W. Hinrichs Seminar f¨ur Sprachwissenschaft University of T¨ubingen Wilhelmstr. 113 D-72074 T¨ubingen, Germany eh@sfs.nphil.uni-tuebingen.de ABSTRACT Chunk parsing has focused on the recognition of partial constituent structures at the level of individual chunks. Little attention has been paid to the question of how such partial analyses can be combined into larger structures for complete utterances. The T¨uSBL parser extends current chunk parsing techniques by a tree-construction component that extends partial chunk parses to complete tree structures including recursive phrase structure as well as function-argument structure. T¨uSBL’s tree construction algo- rithm relies on techniques from memory-based learning that allow similarity-based classification of a given input structure relative to a pre-stored set of tree instances from a fully annotated treebank. A quantitative evaluation of T¨uSBL has been conducted using a semi-automatically constructed treebank of German that consists of appr. 67,000 fully annotated sentences. The basic PARSEVAL measures were used although they were developed for parsers that have as their main goal a complete analysis that spans the entire in- put. This runs counter to the basic philosophy underlying T¨uSBL, which has as its main goal robustness of partially analyzed struc- tures. Keywords robust parsing, chunk parsing, similarity-based learning 1. INTRODUCTION Current research on natural language parsing tends to gravitate toward one of two extremes: robust, partial parsing with the goal of broad data coverage versus more traditional parsers that aim at complete analysis for a narrowly defined set of data. Chunk pars- ing [1, 2] offers a particularly promising and by now widely used example of the former kind. The main insight that underlies the chunk parsing strategy is to isolate the (finite-state) analysis of non- recursive, syntactic structure, i.e. chunks, from larger, recursive structures. This results in a highly-efficient parsing architecture that is realized as a cascade of finite-state transducers and that pur- . sues a longest-match, right-most pattern-matching strategy at each level of analysis. Despite the popularity of the chunk parsing approach, there seem to be two apparent gaps in current research: 1. Chunk parsing research has focused on the recognition of partial constituent structures at the level of individual chunks. By comparison, little or no attention has been paid to the question of how such partial analyses can be combined into larger structures for complete utterances. 2. Relatively little has been reported on quantitative evaluations of chunk parsers that measure the correctness of the output structures obtained by a chunk parser. The main goal of the present paper is help close those two re- search gaps. 2. THE T ¨USBL ARCHITECTURE In order to ensure a robust and efficient architecture, T¨uSBL, a similarity-based chunk parser, is organized in a three-level archi- tecture, with the output of each level serving as input for the next higher level. The first level is part-of-speech (POS) tagging of the input string with the help of the bigram tagger LIKELY [10].1 …

Content truncated to 500 words