Teiji Furugori

Similarity between words computed by spreading activation on an English dictionary

This paper proposes a method for measuring semantic similarity between words as a new tool for text analysis. The similarity is measured on a semantic network constructed systematically from a subset of the English dictionary, LDOCE (Longman Dictionary of Contemporary English). Spreading activation on the network can directly compute the similarity between any two words in the Longman Defining Vocabulary, and indirectly the similarity of all the other words in LDOCE. The similarity represents the strength of lexical cohesion or semantic relation, and also provides valuable information about similarity and coherence of texts.

Structural Analysis of Compound Words in Japanese Using Semantic Dependency Relations

Structural analysis of compound words is a necessary and important process in natural language processing. Proposed here is a corpus- and statistics-based method for the structural analysis of compound words in Japanese. We determine the structure of a compound word by using an Internet corpus and calculating the strength of word association among its constituent words. Experiments with 5, 6, 7, and 8 kanji compound words show that our method works well and its performance is better than those of other comparable studies.

Word‐sense disambiguation with a corpus‐based semantic network*

Abstract Disambiguating word meanings is an essential part of natural language processing. This paper offers a method of determining the meaning of polysemous words in text. We first provide a semantic network, automatically created from a corpus, as a tool for representing the context. We then describe the process of resolving lexical ambiguities using the network. Finally we show an experimental result with a success rate of over 85 per cent that proves effectiveness of the method.

Disambiguation of Syntactic Structures Using the Strength of Association in Three Word Dependency Relations

We propose a syntactic disambiguation method that uses a measure of strengths of association that hold among three words in co-occurrence relations. Using the method, a disambiguation experiment in Japanese noun phrases with particle no is conducted. Its result is better than those of others and seems to show an effectiveness in resolving syntactic ambiguities appearing also in coordinated constructions, prepositional phrase attachments, and the like in English.

Recognition and Utilization of Clausal Relations in Complex Sentences for Improving the Performance of Machine Translation Systems

Machine translation systems are inefficient when translating complex sentences. An important reason for this, among others, comes from the fact that the systems translate a complex sentence without taking into account the clausal relation between main and subordinate clauses. We devise a method for recognizing and utilizing the clausal relation to make the machine translation systems self-improve their performance. First, we attempt to find the clausal relation between the two clauses in a complex sentence through a machine learning mechanism. Second, utilizing this information, we try to pre-edit or modify the sentence so that the clausal relation is expressed overtly in the modified sentence. Experiments with a machine translation system have shown that our idea and methodology improve the performance of the system.

A CAI system for learning English as a second language

We describe a CAI system for learning a second language: English. Our purpose here is to devise a practical system that serves educational aims, primarily for the Japanese junior high school students. The system works by generating sentences, using sentential patterns and a set of vocabularies, and then creating, from the sentences, four different types of problems for the students to learn: translation of Japanese words into English, word rearrangements, various grammatical transformations, and proper word selection problems. The sentence generation mechanism is the center of the system. While it lacks elegance, our way of generating sentences serves its purposes well. It generates, within a limitation, both syntactically and semantically versatile, consistent, and, above all, realistic sentences from everyday life. We are able to create fresh problems for each drill from the sentences generated. The system is adaptable to the learners of any nationality who intend to practise English as a second language. And the power of the system can easily be multiplied by supplying different types of problems.

Prepositional phrase attachment through a hybrid disambiguation model

Prepositional phrase attachment is a major cause of structural ambiguity in natural language. Recent work has been dependent on corpus-based approaches to deal with this problem. However, corpus-based approaches suffer from the sparse-data problem. To cope with this problem, we introduce a hybrid method of integrating corpus-based approach with knowledge-based techniques, using a wide-variety of information that comes from annotated corpora and a machinere-adable dictionary. When the occurrence frequency on the corpora is low, we use preference rules to determine PP attachment based on clues from conceptual information. An experiment has proven that our hybrid method is both effective and applicable in practice.