Phrase-Based Dependency Evaluation of a Japanese Parser
نویسنده
چکیده
Extraction of predicate-argument structure is an important task that requires evaluation for many applications, yet annotated resources of predicate-argument structure are currently scarce, especially for languages other than English. This paper presents an evaluation of a Japanese parser based on dependency relations as proposed by Lin (1995, 1998), but using phrase dependency instead of word dependency. Phrase-based dependency analysis has been the preferred form of Japanese syntactic analysis, yet the use of annotated resources in this format has so far been limited to training and evaluation of dependency analyzers. We will show that (1) evaluation based on phrase-dependency is particularly well-suited for Japanese, even for an evaluation of phrase-structure grammar, and that (2) in spite of shortcomings, the proposed evaluation method has the advantage of utilizing currently available surface-based annotations in a way that is relevant to predicate-argument structure.
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 کاملتولید درخت بانک سازهای زبان فارسی به روش تبدیل خودکار
Treebanks is one of important and useful resource in Natural Language Processing tasks. Dependency and phrase structures are two famous kinds of treebanks. There have already made many efforts to convert dependency structure to phrase structure. In this paper we study an approach to convert dependency structure to phrase structure because of lack of a big phrase structure Treebank in Persian. A...
متن کاملارائۀ راهکاری قاعدهمند جهت تبدیل خودکار درخت تجزیۀ نحوی وابستگی به درخت تجزیۀ نحوی ساختسازهای برای زبان فارسی
In this paper, an automatic method in converting a dependency parse tree into an equivalent phrase structure one, is introduced for the Persian language. In first step, a rule-based algorithm was designed. Then, Persian specific dependency-to-phrase structure conversion rules merged to the algorithm. Subsequently, the Persian dependency treebank with about 30,000 sentences was used as an input ...
متن کاملImproving Fluency by Reordering Target Constituents Using MST Parser in English-to-Japanese Phrase-based SMT
We propose a reordering method to improve the fluency of the output of the phrase-based SMT (PBSMT) system. We parse the translation results that follow the source language order into non-projective dependency trees, then reorder dependency trees to obtain fluent target sentences. Our method ensures that the translation results are grammatically correct and achieves major improvements over PBSM...
متن کاملDependency Analysis of Read Japanese Sentences using Pause Information: A Speaker Independent Case
This paper deals with the problem of recovering syntactic structures of sentences by using the prosodic information extracted from spoken versions of the sentences. Prosodic information has proven to be effective to disambiguate syntactic structures, which is not utilized in a conventional rule-based parser. In our previous works, the duration of pauses at phrase boundaries has been found to be...
متن کامل