Statistical Ambiguity Resolution for Principle-Based Parsing
نویسندگان
چکیده
The goal of syntactic ambiguity resolution is to produce the naturally preferred interpretation of any given input, while limiting computational resources. We present in this paper a statistical pruning device developed for a principle-based parser which attempts to satisfy this goal. We compare the performances of the resulting hybrid parser with an instance of the same parser including a symbolic pruning device, showing that the statistical approach has better performance .
منابع مشابه
Relative clause attachment ambiguity resolution in Persian
The present study seeks to find the way Persian native speakers resolve relative clause attachment ambiguities in sentences containing a complex NP of the type NP of NP followed by a relative clause (RC). Previous off-line studies have found a preference for high attachment in the present study, an on-line technique was used to help identify the nature of this process. Persian speakers were pre...
متن کاملRelative Clause Ambiguity Resolution in L1 and L2: Are Processing Strategies Transferred?
This study aims at investigating whether Persian native speakers highly advanced in English as a second language (L2ers) can switch to optimal processing strategies in the languages they know and whether working memory capacity (WMC) plays a role in this respect. To this end, using a self-paced reading task, we examined the processing strategies 62 Persian speaking proficient L2ers used to read...
متن کاملAmbiguity Resolution for Vt-N Structures in Chinese
The syntactic ambiguity of a transitive verb (Vt) followed by a noun (N) has long been a problem in Chinese parsing. In this paper, we propose a classifier to resolve the ambiguity of Vt-N structures. The design of the classifier is based on three important guidelines, namely, adopting linguistically motivated features, using all available resources, and easy integration into a parsing model. T...
متن کاملResolving Ambiguity in Inter-chunk Dependency Parsing
Recently, dependency grammar has become quite popular in relatively free word-order languages. We encounter many structural ambiguities when parsing a sentence using dependency grammar. We use a chunking procedure to avoid constructing a mistaken dependency structure. Chunking reduces the scope of dependency relations between dependents and governors. This paper presents a method to resolve amb...
متن کاملOptimising the speed and accuracy of a statistical GLR parser
The focus of this thesis is to develop techniques that optimise both the speed and accuracy of a unification-based statistical GLR parser. However, we can apply these methods within a broad range of parsing frameworks. We first aim to optimise the level of tag ambiguity resolved during parsing, given that we employ a front-end PoS tagger. This work provides the first broad comparison of tag mod...
متن کامل