Kazunori Muraki

Translation ambiguity resolution based on text corpora of source and target languages

We propose a new method to resolve ambiguity in translation and meaning interpretation using linguistic statistics extracted from dual corpora of source and target languages in addition to the logical restrictions described on dictionary and grammar rules for ambiguity resolution. It provides reasonable criteria for determining a suitable equivalent translation or meaning by making the dependency relation in the source language be reflected in the translated text. The method can be tractable because the required statistics can be computed semi-automatically in advance from a source language corpus and a target language corpus, while an ordinal corpus-based translation method needs a large volume of bilingual corpus of strict pairs of a sentence and its translation. Moreover, it also provides the means to compute the linguistic statistics on the pairs of meaning expressions.

VENUS: two-phase machine translation system

Abstract NEC has been developing a Japanese-English bi-directional machine translation system called VENUS (Vehicle for Natural language Understanding & Synthesis) in order to reduce the increasing cost of the manual translation of vast amounts of in-house technical documents. In addition, a translation support subsystem has been developed on the basis of VENUS, and extended to have the requisite facilities to prepare translated documents, such as document entry, editing, translation, printing, management, etc. This paper briefly introduces the current status of the VENUS translation system, and the basic idea for the system development.

Information Classification and Navigation based on 5W1H of the Target Information

This paper proposes a method by which 5W1H (who, when, where, what, why, how, and predicate) information is used to classify and navigate Japanese-language texts. 5W1H information, extracted from text data, has an access platform with three functions: episodic retrieval, multi-dimensional classification, and overall classification. In a six-month trial, the platform was used by 50 people to access 6400 newspaper articles. The three functions proved to be effective for office documentation work and the precision of extraction was approximately 82%.

NEC: description of the VENIEX system as used for MUC-5

NEC Corporation has had years of experience in natural language processing and machine translation[1, 2, 3, 4, 5], and currently markets commercial natural language processing systems. Utilizing dictionaries and parsing engines we have already had, we have developed the VENIEX System (VENus for Information EXtraction) as used for MUC-5 in only three months. Our method is to apply both domain-specific keyword-based analysis and full sentential parsing with general grammar[6, 7]. The keyword dictionary of VENIEX contains about thirty thousand entries, whose semantic structures are sub_ME_Capability frame, and the parsing and discourse processing are controlled with the information given in this semantic structure of keywords. The resulting scores of VENIEX for formal run texts were from 0.7181 (minimum) to 0.7548 (maximum) in Richness-Normalized Error and 48.33 in F-MEASURES (P&R).

An Interactive Translation Support Facility for Non-Professional Users

We present an interactive translation method to support non-professional users to write an original document. The method, combining dictionary lookup function and user-guided stepwise interactive machine translation, allows the user to obtain clear result with an easy operation. We implemented the method as an English writing support facility that serves as a translation support front-end to an arbitrary application.

Augmented Dependency Grammar: a simple interface between the grammar rule and the knowledge

This paper describes some operational aspects of a language comprehension model which unifies the linguistic theory and the semantic theory in respect to operations. The computational model, called Augmented Dependency Grammar (ADG), formulates not only the linguistic dependency structure of sentences but also the semantic dependency structure using the extended deep case grammar and field-oriented fact-knowledge based inferences. Fact knowledge base and ADG model clarify the qualitative difference between what we call semantics and logical meaning. From a practical view point, it provides clear image of syntactic/semantic computation for language processing in analysis and synthesis. It also explains the gap in semantics and logical meaning, and gives a clear computational image of what we call conceptual analysis.This grammar is used for analysis of Japanese and synthesis of English, in the Japanese-to-English machine translation system called VENUS (Vehicle for Natural Language Understanding and Synthesis) currently developed by NEC.

From interlingua to speech: generating prosodic information from conceptual representation

A method for generating prosodic information for speech synthesis from conceptual representation is presented. A computational model of generating prosodic information from pragmatic, semantic, syntactic, and lexical information of the utterance is proposed. The various types of information are computed using the information extracted from the conceptual representation and the lexicon through the process of uttered sentence generation. An experimental system for speech synthesis from conceptual representation is developed, and better prosodic quality is obtained than with conventional synthetic speech, according to an informal listening test.<<ETX>>

On a semantic model for multi-lingual paraphrasing

The aim of the present paper is to formalize semantic-directed lexical selection by virtue of frame-based semantic inference capability built in the CFL representation language. The DG model of paraphrasing semantic descriptions can explicate logical process of knowledge-based sentence generation excluding any particular procedures for lexical selection or syntax structure generation. In addition this paper emphasises that this model is basically not dependent on target languages.

An empirical architecture for verb subcategorization frame: a lexicon for a real-world scale Japanese-English interlingual MT

The verb subcategorization frame information plays a major role of disambiguations in many NLP applications. Japanese, however, imposes difficulties of subcategorizing in part because it allows arbitrary ellipses of case elements. We propose a new type of verb subcategorization frame code set that combines the verbs surface case set and the deep case set, as a solution to the difficulties of empirical researches on Japanese. The lexicon developed by this design has comprehensive information on the correspondences between the surface case frame and the deep case frame, and yet restrains the potential combinatorial explosion of the number of verb subcategorization frames by carefully identifying superficially different frames with an idea of alternative case markers and semantic roles, and by introducing the notion of surface case frame permutations. The number of different surface/deep case mapping types is 250, after we completed the new subcategorization frame code development for 30,000 verbs and adjectives.

Lexical information for determining Japanese unbounded dependency

This paper presents a practical method for a global structure analyzing algorithm of Japanese long sentences with lexical information, a method which we call Lexical Discourse Grammar (LDG). This method assumes that Japanese function words, such as conjunctive particles (postpositions) located at the end of each clause, have modality and suggest global structures of Japanese long sentences in cooperation with modality within predicates or auxiliary verbs. LDG classifies the encapsulating powers of function words into six levels, and modality in predicates into four types. LDG presumes the inter-clausal dependency within Japanese sentences prior to syntactic and semantic analyses, by utilizing the differences of the encapsulating powers each Japanese function word has, and by utilizing modification preference between function words and predicates that reflects consistency of modality in them. In order to confirm the encapsulation power of Japanese function words, we analyzed the speech utterances of a male announcer and found the correlation between a particles encapsulating power and the pause length inserted after the clause with a conjunctive particle.