Transparency and Building Lexical Dependency Graphs

نویسندگان
چکیده

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Peking: Building Semantic Dependency Graphs with a Hybrid Parser

This paper is a description of our system for SemEval-2015 Task 18: Broad-Coverage Semantic Dependency Parsing. We implement a hybrid parser which benefits from both transition-based and graph-based parsing approaches. In particular, the tree approximation method is explored to take advantage of wellstudied tree parsing techniques. Evaluation on multilingual data sets demonstrates that consider...

متن کامل

Building Specialized Multilingual Lexical Graphs Using Community Resources

We are describing methods for compiling domain-dedicated multilingual terminological data from various resources. We focus on collecting data from online community users as a main source, therefore, our approach depends on acquiring contributions from volunteers (explicit approach), and it depends on analyzing users’ behaviors to extract interesting patterns and facts (implicit approach). As a ...

متن کامل

Strictly Lexical Dependency Parsing

We present a strictly lexical parsing model where all the parameters are based on the words. This model does not rely on part-of-speech tags or grammatical categories. It maximizes the conditional probability of the parse tree given the sentence. This is in contrast with most previous models that compute the joint probability of the parse tree and the sentence. Although the maximization of join...

متن کامل

Dependency Constraints for Lexical Disambiguation

We propose a generic method to perform lexical disambiguation in lexicalized grammatical formalisms. It relies on dependency constraints between words. The soundness of the method is due to invariant properties of the parsing in a given grammar that can be computed statically from the grammar.

متن کامل

Building phylogenetic lexical ontologies∗

This paper describes a new application of the theory of cladistics to automatic acquisition of lexical ontologies. In the case of life forms, those which are phylogenetically related are expected to share common properties and hence to appear in similar contexts in texts. The procedure has been tested with other words that do not refer to life beings, and a standard phylogenetic algorithm is us...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Annual Meeting of the Berkeley Linguistics Society

سال: 2002

ISSN: 2377-1666,0363-2946

DOI: 10.3765/bls.v28i1.3825