Articles

We discuss the basic ideas behind a Japanese to American Sign Language Translation System for the Japanese users, which assists Japanese Deaf people to communicate. Our discussion covers two main points. The first describes the necessity of a Sign Language Translation System. Since there is no “universal sign language” or …...

Language identification has been an interesting and fascinating issue in natural language processing for decades, and there have been many researches on it. However, most of the researches are for documents, and though the possibility of high accuracy for shorter strings of characters, language identification for words or phrases has …...

The paper attempts to demonstrate how Conversation Analysis (CA) can help us pragmatically to explore the repair organization of human talk-in-interaction via the Web, and reports on a case study of conversational repair structures for Chinese academic discussion through Web. The data collection was based on naturally occurring written interaction …...

Given a targeted subject and a text collection, information extraction techniques provide the capability to populate a database in which each record entry is a subject instance documented in the text collection. However, even with the state-of-the-art IE techniques, IE task results are expected to contain errors. Manual error detection …...

This paper describes a text retrieval system for cellular phones with Web browsing capability, which accepts spoken queries over the cellular phone and provides the search result on the cellular phone screen. This system recognizes spoken queries by large vocabulary continuous speech recognition (LVCSR), retrieves relevant document by text retrieval, …...

In the paper, an effective technique, based on the non-uniform redistribution probability for novel events (the unknown events), to improve the smoothing method in language models is proposed. Basically, there are two processes in the smoothing methods: 1) discounting and 2) redistributing. Instead of uniform probability assignment to each unseen …...

Forms of Japanese referring expressions are mainly divided into four types: bare NPs, demonstrative NPs (i.e. either as determiner or as pronoun) and zero pronouns. Out of the four types of the referring expressions, bare NPs are the most common type as a subsequent mention and zero pronouns are used …...

Japanese Bare Nouns (JBNs) appear to behave like indefinites in some contexts, and mass nouns in some other contexts. For example, when accomplishment verbs have JBNs as their theme, they are modified by both in-adverbs and for-adverbs. This paper first claims that JBNs are weak indefinites and introduce a variable …...

This paper explores the semantic properties and extension paths of modern Mandarin Chinese spatial terms nei4 內‘in, inside’ and wai4 外‘out, outside’. Their symmetric and asymmetric contrasts are accounted for with idealized cognitive models (ICMs) and metonymic models. These models are used to delineate the core meaning and main meaning …...

Centering theory (Grosz et al., 1995) tries to explain relations among attention, anaphora, and cohesion. It has two theoretical limitations. The first is the lack of a principle behind these discourse phenomena. The second is that the salience of discourse entities has not been quantitatively defined, although it plays a …...

This paper presents an analysis of Internally Headed Relative Clause (IHRC) construction in Japanese within the framework of Combinatory Categorial Grammar (Steedman 2000). Shimoyama (1999) argues that when an IHRC appears within the scope of a universal quantifier, the interpretation of the IHRC exemplifies E-type anaphora and that the LF …...

This paper is concerned with frequency adverbs in Japanese. Many linguists have pointed out that frequency statements and generic sentences have multiple readings when they co-occur with a kind of adjuncts. More often than not, the interpretation is complicated by the ambiguity of temporal adverbs and the context-dependent nature of …...

This paper presents a novel method of semantic parsing that maps a natural language (NL) sentence to a logical form. We propose a semantic parsing method by conducting separately two steps as follows; 1) The first step is to predict semantic tags for a given input sentence. 2) The second …...

Errors of the translation of tense, aspect, and modality by machine translation systems were analyzed for six translation systems on the market and our new systems for translating tense, aspect, and modality. The results showed that our systems outperformed the other systems. They also showed that the other systems often …...

This article explores the construction of filler-gap dependencies in Chinese possessor relative clauses (PRCs), which are different from typical relative clauses (RCs) considered in the literature because Chinese PRCs contain no overt missing arguments (i.e. gaps). As Chinese RCs are prenominal, the gaps precede the head noun fillers. It has …...

Most machine translators are implemented using example based, rule based, and statistical approaches. However, each of these paradigms has its drawbacks. Example based and statistical based approaches are domain specific and requires a large database of examples to produce accurate translation results. Although rule based approach is known to produce …...

In the past two hundred years or so, a sizable corpus of Taiwanese text in Latin script has been accumulated. However, due to the political and historical situation of Taiwan, few people can read these materials at present. It is regrettable that the utilization of these plentiful materials is very …...

The count-mass distinction often served as a test case for asking how syntax and semantics are related, whether knowledge of one helps the acquisition of the other. Virtually no studies examined this distinction in classifier languages which supposedly lack the distinction. However, Cheng and Sybesma (1998) argued Mandarin as a …...

In this paper, MARKET metaphors used by different communities (Chinese, Malay and English) are laid out based on the frequency counts of these metaphors and their occurrences in different syntactic positions. The results show that certain types of metaphors have preferences for different syntactic positions for ‘market.’ For instance, MARKET …...

In this paper, we address the problem of automatically converting information in the Korean language to one in a sign language as used in Korea. First, we discuss the differences between sign language and natural language, and in particular between the sign language in Korea and the Korean language. Then, …...