Articles

We describe here an algorithm for detect- ing subject boundaries within text based on a statistical lexical similarity measure. Hearst has already tackled this problem with good results (Hearst, 1994). One of her main assumptions is that a change in subject is accompanied by a change in vo- cabulary. Using …...

AbstractThe tutorial will introduce purpose-dependent levels of translation. The levels will be defined and it will be shown how to correct errors in relation to those levels. Error collection procedures as well as file storage and naming procedures will be discussed. Examples will be discussed that show how to read …...

AbstractThis tutorial provides a nontechnical introduction to machine translation. It reviews the whole scope of MT, outlining briefly its history and the major application areas today, and describing the various kinds of MT techniques that have been invented—from direct replacement through transfer to the holy grail of interlinguas. It briefly …...

AbstractA successful MT operation is the result of good planning, an incremental approach, dedicated and talented people, and MT software that is capable of handling the types of text to be translated. The presenter will share insights gained during 20 years of experience with the development and implementation of machine …...

AbstractThe tutorial addresses the issues peculiar to machine translation evaluation, namely the difficulty in determining what constitutes correct translation, and which types of evaluation are the most meaningful for evaluation "consumers." The tutorial is structured around evaluation methods designed for particular purposes: types of MT design, stages in the development …...

The emerging network technologies such as Intranets and the Internet, particularly the World Wide Web (WWW), will create a new model of computing which I will call Network Computing (NC); others, e.g. Forrester Research Inc. call it Internet Computing with the obvious stress on the Internet. Recent analyses of this …...

A rather well-known aspect of French Stylistic Inversion is the impossibility of having a nominal object either precede or follow the inverted subject. A similar phenomenon is found in cases of French Stylistic Inversion with causative and perception verbs. The nominal subject of the infinitival complement can never appear with …...

Based on unmarkedness of coronal cross-linguistically, coronal has been considered to be underspecified. Also, place assimilation where coronal tends to assimilate to the adjacent labial or velar by a feature- filling rule has been support the underspecification of coronals. I instead argue that coronal should be specified in Optimality Theory …...

This paper reconsiders nasal assimilation in English within the framework of Optimality Theory and shows that the phenomena can be accounted for in a natural way in terms of some ranked violable constraints. In so doing, I also argue against an account based on structural interpretations of faithfulness, and propose …...

The aim of this paper is to show how an optimality-theoretic conception of phonology (McCarthy & Prince 1993, 1995; Prince & Smolensky 1993) overcomes some of the limitations of the traditional ways of treating the so-called irregular verbs' in Korean. Building on the notion of OT, I attempt to shed …...

To understand text, we must relate it with specified situations. This paper, on the basis of such an idea, discusses how the things that a text describes and the situation that the text relates to are expressed in a computer and how the topic of a text is extracted. 1....

There have been two opposing views on the so-called head internal relative construction (HIRC) in Korean/Japanese, i.e., a view that analyzes the HIRC categorially as a nominal projection and functionally as an argument (Kuroda 1992, Watanabe 1992, Hoshi 1994, Jhang 1991/1994, among others) vs. a view that analyzes the HIRC …...

The statistical induction of context free grammars from bracketed cor- pora with the Inside Outside Algorithm has often inspired researchers, but the computational complexity has made it impossible to generate a large scale grammar. The method we suggest achieves the same re- sults as earlier research, but at a much …...

This study investigated whether or not gender-based differences are evident in the language (North American English) children use to tell a story. An equal number of boys and girls representing 3 developmental stages (7;2, 10;10, and 13;8) were asked to perform a 3 part guided narrative task, which involved telling …...

This paper describes the implementation of Mandarin Chinese in the Pappi system, a principle-based multi-lingual parser. We show that sub- stantive linguistic coverage for new and linguistically diverse languages such as Chinese can be achieved, conveniently and efficiently, through pa- rameterization and minimal modifications to a core system. In particular, …...

This paper . proposes a similarity measure which takes account of point- of-views (abbreviated to POV, hereafter) in the calculation of similarity values. So far many researches on similarity measures have been per- formed but none takes account of POVs. The similarity measure pro- posed in this paper is based …...

This paper reviews the treatment of wh-question facts offered by Lappin and Johnson 1996, and suggests that their account of certain island phenomena should be adapted by assuming that certain phrase structures license binding of inherited features. In Japanese, Lappin and Johnson's INHERILQUE feature appears to be dependent on INHERIQUE …...

Over the past few years, HNC has developed a neural network based, vector space approach to text retrieval. This approach, embodied in a system called MatchPlus, allows the user to retrieve information on the basis of meaning and context of a fi'ee text query. The MatchPlus system uses a neural …...

Several classification and routing methods were im- plemented and compared. The experiments used FBIS documents from four categories, and the measures used were the ff.idf and Cosine similarity measures, and a maximum likelihood estimate based on ass~lming a Multinomial Distribution for the various topics (popula- tions). In addition, the SMART …...

TRW has developed a text search tool that allows users to enter a query in foreign lan- guages and retrieve documents that match the query. A single query can contain words and phrases in a mix of different languages, with the foreign-language terms entered using the native script. The browser …...