Articles

We present a bidirectional Example-Based Machine Translation (EBMT) system for Chinese—English. The prerequisite is a bilingual aligned corpus of Chinese—English sentences, and we describe the example extraction efforts purely based on word alignment. The whole system is designed to be language independent and as automatic as possible for construction. We …...

We compare the performance of several SYSTRAN systems on the BTEC corpus. Two language pairs: Chinese to English and Japanese to English are used. Whenever it is possible the system will be used “off the shelf” and then tuned. The first system we use is freely available on the web. …...

This paper introduces ATR’s project named Corpus-Centered Computation (C3), which aims at developing a translation technology suitable for spoken language translation. C3 places corpora at the center of its technology. Trans- lation knowledge is extracted from corpora, translation qual- ity is gauged by referring to corpora, the best translation among …...

This paper aims to account for dependency of long-distance anaphors within the derivational approach. Dependency between the antecedent and the anaphor is determined by the universal operations, Merge, Move and Agree. Following Hornstein (2001) and Zwart (2002), anaphors in Korean, Chinese, and Japanese are argued to merge with antecedents to …...

In Chinese, anaphors are frequently omitted, termed zero anaphor (ZA), from text due to their prominence. Thus the information carried by ZAs in text can not be used to contribute the calculation of text categorization. In this paper, we employ a ZA resolution method to recover the omissions of anaphors …...

Today, corpus plays an important role in development and evaluation language and speech technologies, such as part of speech tagging, parsing, word sense disambiguation, text categorization, named entity classification, information extraction, question answering, structure discovery (clustering), speech recognition and machine translation systems, etc. One can exploit valuable statistical parameters taken …...

To make real Web information more machine processable, this paper presents a new approach to intra-page and inter-page semantic analysis of Web pages. Our approach consists of Web pages structure analysis and semantic clustering for intra-page semantic analysis, and machine learning based link semantic analysis for inter-page analysis. Based on …...

This paper proposes to disambiguate word senses by corpus-based ontology learning. Our approach is a hybrid method. First, we apply the previously-secured dictionary information to select the correct senses of some ambiguous words with high precision, and then use the ontology to disambiguate the remaining ambiguous words. The mutual information …...

Two kinds of paraphrases extracted from a bilingual parallel corpus were analyzed. One is from an adjectival predicate sentence to a non-adjectival one. The other is from a passive form to a non-passive form. The ability to extract paraphrases is strongly desired for paraphrasing studies. Although extracting paraphrases from multi-lingual …...

The task of identifying proper names, unknown words and new terms, is an important step in text processing systems. This paper describes a method of using mutual information to collect possible segments as candidates of these three feature types in a document scope. Then the construction and context of each …...

Negative factors and their floating are the semantic marks of objective identification of the meaning of huaiyi and sub-categorization of sentence patterns of the huaiyi sentences. This article discusses negative factors, the floating of negative factors and recognition of different patterns of huaiyi sentences. It has also bee argued that …...

In this paper we investigate the structure of spatial expressions in Saisiyat based in part on corpus data. Our corpus material includes both narratives and conversations that together run for approximately 100 minutes. First, the corpus was searched for syntactic patterns of spatial expressions. The structure of dynamic motion expressions …...

Of the 57 basic sentence categories (SC) defined in the HNC theory, action-effect SC is an important one with distinctive features. In the light of the HNC conceptual network, action-effect sentences in the Chinese language arise directly from causative verbs and compelling verbs, and indirectly from general acting verbs, i.e. …...

This paper addresses a novel sentence reduction algorithm base on decision tree model where semantic information is used to enhance the accuracy of sentence reduction. The proposed algorithm is able to deal with the changeable order problem in sentence reduction. Experimental show a better result when comparing with the original …...

We report a Japanese parsing system with a linguistically fine-grained grammar based on the Lexical-Functional Grammar (LFG) formalism. The system is the first Japanese LFG parser with over 97% coverage for real-world text. We evaluated the accuracy of the system comparing it with standard Japanese dependency parsers. The LFG parser …...

Automatic Multi-word Units Extraction is an important issue in Natural Language Processing. This paper has proposed a new statistical method based on a large-scale balanced corpus to extract multi-word units. We have used two improved traditional parameters: mutual information and log-likelihood ratio, and have increased the precision for the top …...

In our information era, keywords are very useful to information retrieval, text clustering and so on. News is always a domain attracting a large amount of attention. Aiming at news documents' characteristics and the resources available, this paper proposes to use Maximum Entropy (ME) model to conduct automatic keyword indexing. …...

This paper addresses a novel translation method based on Hidden Markov Model using template rules after learning them from the bilingual corpus. The method can enhance the translation accuracy and ensure a low complexity in comparing with the pervious template learning translation method and draws a new perspective for applying …...

Multigram language model has become important in Speech Recognition, Natural Language Processing and Information Retrieval. An essential task in multigram language model is to establish a set of significant multigram compounds. In Yamamotto and Church (2001), an 0(NlogN) time complexity method based on Generalised Suffix Array (GSA) has been found, …...

In this paper an approach is proposed to combine different order N-grams based on the discriminative estimation criterion, on which the parameters of n-gram can be optimized. To raise the power of modeling language information, we propose several schemes to combine conventional different order n-gram language model. We employ Newton …...