Sixth International Joint Conference on Natural Language Processing Proceedings of the Seventh SIGHAN Workshop on Chinese Language Processing
نویسندگان
چکیده
In this talk, we are going to give a systematic view of lexical semantics of Chinese language. From macro perspective point of view, lexical conceptual meanings are classified into hierarchical semantic types and each type plays some particular semantic functions of Host, Attribute, and Value to form a semantic compositional system. Lexical senses and their compositional functions will be exemplified by the semantic expressions of E-HowNet. Entities and relations are two major semantic types of the compositional system. Lexical senses and phrasal senses are compositions of these two types. From micro perspective point of view, each lexical word has individual idiosyncratic semantic contents, focuses and features. Hence words of same semantic type may have various different syntactic properties which make automatic language processing very difficult. On the other hand lexical syntactic properties are strongly influenced by lexical semantic structures. Morpho-semantic structures may systematically lead the way to derive lexical senses and syntactic behaviors of lexemes. It was observed that allowable alternations of sentence-patterns for verbs are mainly determined by their lexical semantic structures. It follows that senses and syntactic properties of out-ofvocabulary words become predictable and lexical compositional properties do shed light on automatic Chinese language understanding. Supporting evidences and logical interpretations of semantic and syntactic interactions will be presented in this talk.
منابع مشابه
The Second CIPS - SIGHAN Joint Conference on Chinese Language Processing 20 - 21 December 2012 Tianjin University Tianjin , China
متن کامل
Sixth International Joint Conference on Natural Language Processing Proceedings of the Fourth Workshop on South and Southeast Asian Natural Language Processing
This paper deals with the fast bootstrapping of Grapheme-to-Phoneme (G2P) conversion system, which is a key module for both automatic speech recognition (ASR), and text-to-speech synthesis (TTS). The idea is to exploit language contact between a local dominant language (Malay) and a very under-resourced language (Iban spoken in Sarawak and in several parts of the Borneo Island) for which no res...
متن کاملIJCNLP 2008 Sixth SIGHAN Workshop on Chinese Language Processing
In this paper, we propose an example-based decoder for a statistical machine translation (SMT) system, which is used for spoken language machine translation. In this way, it will help to solve the re-ordering problem and other problems for spoken language MT, such as lots of omissions, idioms etc. Through experiments, we show that this approach obtains improvements over the baseline on a Chines...
متن کاملSixth International Joint Conference on Natural Language Processing Proceedings of the 11th Workshop on Asian Language Resources
Bilingual corpora play an important role as resources not only for machine translation research and development but also for studying tasks in comparative linguistics. Manual annotation of word alignments is of significance to provide a gold-standard for developing and evaluating machine translation models and comparative linguistics tasks. This paper presents research on building an English-Vi...
متن کاملThe First International Chinese Word Segmentation Bakeoff
This paper presents the results from the ACL-SIGHAN-sponsored First International Chinese Word Segmentation Bakeoff held in 2003 and reported in conjunction with the Second SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan. We give the motivation for having an international segmentation contest (given that there have been two within-China contests to date) and we report on the resu...
متن کامل