Learning-Based Argument Structure Analysis of Event-Nouns in Japanese

نویسندگان

  • Mamoru Komachi
  • Ryu Iida
  • Kentaro Inui
  • Yuji Matsumoto
چکیده

Previous work on predicate-argument structure analysis has focused largely on verbs and adjectives. However, to extract richer information from such a sentence as “His decision was right,” not only the predicate “was right” but also the noun “decision” need to be identi ed as an event denoting expression. Here, we call event denoting nouns event-nouns, which refer to events like “he decided something.” We de ne a task of argument structure analysis of event-nouns in Japanese. Some event-nouns, such as ryouri “cook/cuisine”, do not always refer to an event, and word sense disambiguation of event-nouns has to be done depending on their context. In this paper, we present an unsupervised machine learning method to extract patterns of event-nouns for event-hood determination. We also investigate verb-noun co-occurrences and support verb constructions for argument identi cation of event-nouns.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning Probabilistic Subcategorization Preference by Identifying Case Dependencies and Optimal Noun Class Generalization Level

This paper proposes a novel method of learning probabilistic subcategorization preference. In the method, for the purpose of coping with the ambiguities of case dependencies and noun class generalization of argument/adjunct nouns, we introduce a data structure which represents a tuple of independent partial subcategorization frames. Each collocation of a verb and argument/adjunct nouns is assum...

متن کامل

Learning Probabilistic Subcategorization Preference and its Application to Syntactic Disambiguation

This paper proposes a novel method of learning probabilistic subcategorization preference. In the method, for the purpose of coping with the ambiguities of case dependencies and noun class generalization of argument/adjunct nouns, we introduce a data structure which represents a tuple of independent partial subcategorization frames. Each collocation of a verb and argument/adjunct nouns is assum...

متن کامل

Children’s use of argument structure, meta-knowledge of the lexicon, and extra-linguistic contextual cues in inferring meanings of novel verbs

Verbs are the centerpiece of the sentence, and understanding of verb meanings is essential for language acquisition. Yet verb learning is said to be more challenging than noun learning for young children for several reasons. First, while nouns tend to denote concrete objects, which are perceptually stable over time, verbs tend to refer to action events, which are temporally ephemeral, and the b...

متن کامل

A Korean-Japanese-Chinese Aligned Wordnet with Shared Semantic Hierarchy

A Korean-Japanese-Chinese aligned wordnet, “CoreNet” is introduced. For the purpose of this paper, the term “wordnet” refers to a network of words. It is constructed based on a shared semantic hierarchy that is originated from NTT Goidaikei (Lexical Hierarchical System). Korean wordnet was constructed through the semantic category assignment to every meaning of Korean words in a dictionary. Ver...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007