Eiko Yamamoto


2014

pdf bib
Fusion of Multiple Semantic Networks and Human Association
Hitoshi Isahara | Kyoko Kanzaki | Eiko Yamamoto | Takayuki Kuribayashi | Michinaga Otsuka
Proceedings of the Seventh Global Wordnet Conference

2008

pdf bib
Extraction of Informative Expressions from Domain-specific Documents
Eiko Yamamoto | Hitoshi Isahara | Akira Terada | Yasunori Abe
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

What kinds of lexical resources are helpful for extracting useful information from domain-specific documents? Although domain-specific documents contain much useful knowledge, it is not obvious how to extract such knowledge efficiently from the documents. We need to develop techniques for extracting hidden information from such domain-specific documents. These techniques do not necessarily use state-of-the-art technologies and achieve deep and accurate language understanding, but are based on huge amounts of linguistic resources, such as domain-specific lexical databases. In this paper, we introduce two techniques for extracting informative expressions from documents: the extraction of related words that are not only taxonomically related but also thematically related, and the acquisition of salient terms and phrases. With these techniques we then attempt to automatically and statistically extract domain-specific informative expressions in aviation documents as an example and evaluate the results.

pdf bib
Application of Resource-based Machine Translation to Real Business Scenes
Hitoshi Isahara | Masao Utiyama | Eiko Yamamoto | Akira Terada | Yasunori Abe
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

As huge quantities of documents have become available, services using natural language processing technologies trained by huge corpora have emerged, such as information retrieval and information extraction. In this paper we verify the usefulness of resource-based, or corpus-based, translation in the aviation domain as a real business situation. This study is important from both a business perspective and an academic perspective. Intuitively, manuals for similar products, or manuals for different versions of the same product, are likely to resemble each other. Therefore, even with only a small training data, a corpus-based MT system can output useful translations. The corpus-based approach is powerful when the target is repetitive. Manuals for similar products, or manuals for different versions of the same product, are real-world documents that are repetitive. Our experiments on translation of manual documents are still in a beginning stage. However, the BLEU score from very small number of training sentences is already rather high. We believe corpus-based machine translation is a player full of promise in this kind of actual business scene.

2007

pdf bib
Extracting Word Sets with Non-Taxonomical Relation
Eiko Yamamoto | Hitoshi Isahara
Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions

2006

pdf bib
Semantic Analysis of Abstract Nouns to Compile a Thesaurus of Adjectives
Kyoko Kanzaki | Qing Ma | Eiko Yamamoto | Hitoshi Isahara
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

Aiming to compile a thesaurus of adjectives, we discuss how to extract abstract nouns categorizing adjectives, clarify the semantic and syntactic functions of these abstract nouns, and manually evaluate the capability to extract the “instance-category” relations. We focused on some Japanese syntactic structures and utilized possibility of omission of abstract noun to decide whether or not a semantic relation between an adjective and an abstract noun is an “instance-category” relation. For 63% of the adjectives (57 groups/90 groups) in our experiments, our extracted categories were found to be most suitable. For 22 % of the adjectives (20/90), the categories in the EDR lexicon were found to be most suitable. For 14% of the adjectives (13/90), neither our extracted categories nor those in EDR were found to be suitable, or examinees’ own categories were considered to be more suitable. From our experimental results, we found that the correspondence between a group of adjectives and their category name was more suitable in our method than in the EDR lexicon.

pdf bib
Detection of inconsistencies in concept classifications in a large dictionary — Toward an improvement of the EDR electronic dictionary —
Eiko Yamamoto | Kyoko Kanzaki | Hitoshi Isahara
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

The EDR electronic dictionary is a machine-tractable dictionary developed for advanced computer-based processing of natural lan-guage. This dictionary comprises eleven sub-dictionaries, including a concept dictionary, word dictionaries, bilingual dictionaries, co-occurrence dictionaries, and a technical terminology dictionary. In this study, we focus on the concept dictionary and aim to revise the arrangement of concepts for improving the EDR electronic dictionary. We believe that unsuitable concepts in a class differ from other concepts in the same class from an abstract perspective. From this notion, we first try to automatically extract those concepts unsuited to the class. We then try semi-automatically to amend the concept explications used to explain the meanings to human users and rearrange them in suitable classes. In the experiment, we try to revise those concepts that are the lower-concepts of the concept “human” in the concept hierarchy and that are directly arranged under concepts with concept explications such as “person as defined by –” and “person viewed from –.” We analyze the result and evaluate our approach.

2004

pdf bib
Hierarchy Extraction based on Inclusion of Appearance
Eiko Yamamoto | Kyoko Kanzaki | Hitoshi Isahara
Proceedings of the ACL Interactive Poster and Demonstration Sessions

pdf bib
Construction of an Objective Hierarchy of Abstract Concepts via Directional Similarity
Kyoko Kanzaki | Eiko Yamamoto | Qing Ma | Hitoshi Isahara
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

pdf bib
Related Word-pairs Extraction Without Dictionaries
Eiko Yamamoto | Kyoji Umemura
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

pdf bib
Extraction of Hyperonymy of Adjectives from Large Corpora by Using the Neural Network Model
Kyoko Kanzaki | Qing Ma | Eiko Yamamoto | Masaki Murata | Hitoshi Isahara
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

2003

pdf bib
Dynamic Programming Matching for Large Scale Information Retrieval
Eiko Yamamoto | Masahiro Kishida | Yoshinori Takenami | Yoshiyuki Takeda | Kyoji Umemura
Proceedings of the Sixth International Workshop on Information Retrieval with Asian Languages

pdf bib
Extraction and Verification of KO-OU Expressions from Large Corpora
Atsuko Kida | Eiko Yamamoto | Kyoko Kanzaki | Hitoshi Isahara
The Companion Volume to the Proceedings of 41st Annual Meeting of the Association for Computational Linguistics