Treeblazing: Using External Treebanks to Filter Parse Forests for Parse Selection and Treebanking
نویسندگان
چکیده
We describe “treeblazing”, a method of using annotations from the GENIA treebank to constrain a parse forest from an HPSG parser. Combining this with self-training, we show significant dependency score improvements in a task of adaptation to the biomedical domain, reducing error rate by 9% compared to out-of-domain gold data and 6% compared to self-training. We also demonstrate improvements in treebanking efficiency, requiring 25% fewer decisions, and 17% less annotation time.
منابع مشابه
Unsupervised Parse Selection for HPSG
Parser disambiguation with precision grammars generally takes place via statistical ranking of the parse yield of the grammar using a supervised parse selection model. In the standard process, the parse selection model is trained over a hand-disambiguated treebank, meaning that without a significant investment of effort to produce the treebank, parse selection is not possible. Furthermore, as t...
متن کاملSynthetic Treebanking for Cross-Lingual Dependency Parsing
How do we parse the languages for which no treebanks are available? This contribution addresses the cross-lingual viewpoint on statistical dependency parsing, in which we attempt to make use of resource-rich source language treebanks to build and adapt models for the under-resourced target languages. We outline the benefits, and indicate the drawbacks of the current major approaches. We emphasi...
متن کاملUsing Treebanking Discriminants as Parse Disambiguation Features
This paper presents a novel approach of incorporating fine-grained treebanking decisions made by human annotators as discriminative features for automatic parse disambiguation. To our best knowledge, this is the first work that exploits treebanking decisions for this task. The advantage of this approach is that use of human judgements is made. The paper presents comparative analyses of the perf...
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 کاملParse Forest Diagnostics with Dr. Ambiguity
In this paper we propose and evaluate a method for locating causes of ambiguity in context-free grammars by automatic analysis of parse forests. A parse forest is the set of parse trees of an ambiguous sentence. Deducing causes of ambiguity from observing parse forests is hard for grammar engineers because of (a) the size of the parse forests, (b) the complex shape of parse forests, and (c) the...
متن کامل