Semantic-level Transfer in Japanese-German Speech Translation : Some Experiences
スポンサーリンク
概要
- 論文の詳細を見る
The Japanese-German transfer component of the ASURA speech-to-speech translation system transforms feature structures produced by Japanese analysis into modified feature structures suitable for input to German generation. The production-style rules which compose the J-G component are applied by the Feature Structure Rewriting System (RWS). This paper discusses several issues which arose during rule development and their implications for future work. First, we examine the level at which transfer operates: How should the symbols in transferred feature structures be interpreted? How should one define the boundary between transfer and generation? Second, we consider the possible use of language-neutral symbols in transfer. Third, we consider several issues of semantic representation. Sometimes problems arose because information was missing in the analysis output. In other cases, the proper semantic format was uncertain. Finally, we examine various ad hoc aspects of the current system. In many cases, greater generality can be achieved by taking full advantage of the RWS' typing system for feature structures. Other problems, however, may require extensive knowledge processing.
- 一般社団法人情報処理学会の論文
- 1993-05-20
著者
-
Morimoto Tsuyoshi
ATR Interpreting Telecommunications Research Laboratories
-
Suzuki M
Atr Interpreting Telecommunications Research Laboratories
-
Seligman M
Atr Interpreting Telecommunications Research Laboratories
-
Seligman Mark
ATR Interpreting Telecommunications Research Laboratories
-
Suzuki Masami
ATR Interpreting Telecommunications Research Laboratories
関連論文
- One-Pass Search Algorithm for Continuous Speech Recognition Using Generalized LR Parsing : A CFG-Driven, Frame-Synchronous HMM-Based Approach
- Spoken Sentence Recognition Based on HMM-LR with Hybrid Language Modeling (Special Issue on Natural Language Processing and Understanding)
- LR Parsing with a Category Reachability Test Applied to Speech Recognition (Special Issue on Speech and Discourse Processing in Dialogue Systems)
- Semantic-level Transfer in Japanese-German Speech Translation : Some Experiences
- FUSING MULTIMODAL INPUTS
- ANALYSIS AND INTEGRATION OF MULTIMODAL INPUTS IN INTERPRETING TELECOMMUNICATIONS
- パターンを用いた曖昧性の検出と再確認方式
- A Unification-Based Japanese Parser for Speech-to-Speech Translation (Special Issue on Speech and Discourse Processing in Dialogue Systems)
- Analysis of Gestures in a Multimedia/Multimodal Interpreting Experiment
- An Empirical Study on Rule Granularity and Unification Interleaving in Unification-Based Parsers
- English-Japanese Transfer within ASURA Framework
- Continuous Speech Recognition Using a Combination of Syntactic Constraints and Dependency Relationships
- An lnformation-Theoretic Model of Discourse for Next Utterance Type Prediction