Book ChapterDOI
Enhancing czech parsing with verb valency frames
Miloš Jakubíček,Vojtěch Kovář +1 more
- pp 282-293
TLDR
An effective implementation is described that uses the syntactic information in the complex valency frames to resolve some of the standard parsing ambiguities, thereby improving the analysis results.Abstract:
In this paper an exploitation of the verb valency lexicons for the Czech parsing system Syntis presented and an effective implementation is described that uses the syntactic information in the complex valency frames to resolve some of the standard parsing ambiguities, thereby improving the analysis results. We discuss the implementation in detail and provide evaluation showing improvements in parsing accuracy on the Brno Phrasal Treebank.read more
Citations
More filters
Proceedings ArticleDOI
Valency-Augmented Dependency Parsing
Tianze Shi,Lillian Lee +1 more
TL;DR: A complete, automated, and efficient approach for utilizing valency analysis in making dependency parsing decisions, which includes extraction of valency patterns, a probabilistic model for tagging these patterns, and a joint decoding process that explicitly considers the number and types of each token’s syntactic dependents.
Improving Verb Phrase Extraction from Historical Text by use of Verb Valency Frames
Eva Pettersson,Joakim Nivre +1 more
TL;DR: By using verb valency information in a post-processing step to the verb phrase extraction system, it is possible to remove improbable complements extracted by the parser and insert probable complements not extracted byThe parser, leading to an increase in both precision and recall for the extracted complements.
References
More filters
Book ChapterDOI
Automatic Extraction of Polish Language Errors from Text Edition History
TL;DR: By applying the methods of automatic extraction of various kinds of errors such as spelling, typographical, grammatical, syntactic, semantic, and stylistic ones from text edition histories to Wikipedia's article revision history, this paper created the large and publicly available corpus of naturally-occurring language errors for Polish, called PlEWi.
Book
Foundations of Computational Linguistics: Human-Computer Communication in Natural Language
TL;DR: In the third edition the author has modernized the text, leaving the overview of traditional, theoretical, and computational linguistics, analytic philosophy of language, and mathematical complexity theory with their historical backgrounds intact.
BookDOI
Foundations of Computational Linguistics
TL;DR: This foundations of computational linguistics is well known book in the world, of course many people will try to own it and this is it the book that you can receive directly after purchasing.
Journal ArticleDOI
A test of the leaf-ancestor metric for parse accuracy
Geoffrey Sampson,Anna Babarczy +1 more
TL;DR: The Leaf-Ancestor (LA) metric arguably comes closer to formalizing the intuitive concept of relative parse accuracy than the GEIG metric, and is supported via an experiment that contrasts the performance of alternative metrics on the same body of automatically-parsed examples.
VerbaLex - New Comprehensive Lexicon of Verb Valencies forCzech
Dana Hlaváčková,Aleš Horák +1 more
TL;DR: The paper presents new lexicon of verb valencies for the Czech language named VerbaLex, which comprehends all the information found in these resources plus additional relevant information such as verb aspect, verb synonymity, types of use and semantic verb classes based on the VerbNet project.