NJU-Parser: Achievements on Semantic Dependency Parsing
نویسندگان
چکیده
In this paper, we introduce our work on SemEval-2012 task 5: Chinese Semantic Dependency Parsing. Our system is based on MSTParser and two effective methods are proposed: splitting sentence by punctuations and extracting last character of word as lemma. The experiments show that, with a combination of the two proposed methods, our system can improve LAS about one percent and finally get the second prize out of nine participating systems. We also try to handle the multilevel labels, but with no improvement.
منابع مشابه
Feature Engineering in Persian Dependency Parser
Dependency parser is one of the most important fundamental tools in the natural language processing, which extracts structure of sentences and determines the relations between words based on the dependency grammar. The dependency parser is proper for free order languages, such as Persian. In this paper, data-driven dependency parser has been developed with the help of phrase-structure parser fo...
متن کاملبرچسبزنی خودکار نقشهای معنایی در جملات فارسی به کمک درختهای وابستگی
Automatic identification of words with semantic roles (such as Agent, Patient, Source, etc.) in sentences and attaching correct semantic roles to them, may lead to improvement in many natural language processing tasks including information extraction, question answering, text summarization and machine translation. Semantic role labeling systems usually take advantage of syntactic parsing and th...
متن کاملSemantic Dependency Parsing using N-best Semantic Role Sequences and Roleset Information
In this paper, we describe a syntactic and semantic dependency parsing system submitted to the shared task of CoNLL 2008. The proposed system consists of five modules: syntactic dependency parser, predicate identifier, local semantic role labeler, global role sequence candidate generator, and role sequence selector. The syntactic dependency parser is based on Malt Parser and the sequence candid...
متن کاملA Joint Syntactic and Semantic Dependency Parsing System based on Maximum Entropy Models
A joint syntactic and semantic dependency parsing system submitted to the CoNLL-2009 shared task is presented in this paper. The system is composed of three components: a syntactic dependency parser, a predicate classifier and a semantic parser. The first-order MSTParser is used as our syntactic dependency pasrser. Projective and non-projective MSTParsers are compared with each other on seven l...
متن کاملStatistical Ltag Parsing
STATISTICAL LTAG PARSING Libin Shen Aravind K. Joshi In this work, we apply statistical learning algorithms to Lexicalized Tree Adjoining Grammar (LTAG) parsing, as an effort toward statistical analysis over deep structures. LTAG parsing is a well known hard problem. Statistical methods successfully applied to LTAG parsing could also be used in many other structure prediction problems in NLP. F...
متن کامل