Structural Correspondence Learning for Parse Disambiguation
نویسنده
چکیده
The paper presents an application of Structural Correspondence Learning (SCL) (Blitzer et al., 2006) for domain adaptation of a stochastic attribute-value grammar (SAVG). So far, SCL has been applied successfully in NLP for Part-of-Speech tagging and Sentiment Analysis (Blitzer et al., 2006; Blitzer et al., 2007). An attempt was made in the CoNLL 2007 shared task to apply SCL to non-projective dependency parsing (Shimizu and Nakagawa, 2007), however, without any clear conclusions. We report on our exploration of applying SCL to adapt a syntactic disambiguation model and show promising initial results on Wikipedia domains.
منابع مشابه
A Comparison of Structural Correspondence Learning and Self-training for Discriminative Parse Selection
This paper evaluates two semi-supervised techniques for the adaptation of a parse selection model to Wikipedia domains. The techniques examined are Structural Correspondence Learning (SCL) (Blitzer et al., 2006) and Self-training (Abney, 2007; McClosky et al., 2006). A preliminary evaluation favors the use of SCL over the simpler self-training techniques.
متن کاملCross-lingual Parse Disambiguation based on Semantic Correspondence
We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that different languages have different ambiguities. We simultaneously reduce ambiguity in multiple languages in a fully automatic way. Evaluation shows that the system reliably discards dispreferred parses from the raw parser out...
متن کاملUnsupervised Morphological Disambiguation using Statistical Language Models
In this paper, we present a probabilistic model for the unsupervised morphological disambiguation problem. Our model assigns morphological parses T to the contexts C instead of assigning them to the words W . The target word w ∈ W determines the possible parse set Tw ⊂ T that can be used in w’s context cw ∈ C. To assign the correct morphological parse t ∈ Tw to w, our model finds the parse t ∈ ...
متن کاملIntegrating Prosodics into a Language Model for Spoken Language Understanding of Thai
This paper describes a preliminary work on prosody modeling aspect of a spoken language understanding system for Thai. Specifically, the model is designed to integrate prosodics into a language model based on constraint dependency grammar. There are two steps involved, namely the prosodic annotation process and the prosodic disambiguation process. The annotation process uses prosodic informatio...
متن کاملAre Structural Principles Useful for Automatic Disambiguation ?
In this paper we discuss how structural Preferences can be expressed within an LTAG framework on dependancy like structures. We argue that the use of psycholinguistically motivated criteria is useful for building practical parse-ranking applications.
متن کامل