Satoshi Tojo


2017

pdf bib
Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregation
Van-Khanh Tran | Le-Minh Nguyen | Satoshi Tojo
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

Natural language generation (NLG) is an important component in spoken dialogue systems. This paper presents a model called Encoder-Aggregator-Decoder which is an extension of an Recurrent Neural Network based Encoder-Decoder architecture. The proposed Semantic Aggregator consists of two components: an Aligner and a Refiner. The Aligner is a conventional attention calculated over the encoded input information, while the Refiner is another attention or gating mechanism stacked over the attentive Aligner in order to further select and aggregate the semantic elements. The proposed model can be jointly trained both sentence planning and surface realization to produce natural language utterances. The model was extensively assessed on four different NLG domains, in which the experimental results showed that the proposed generator consistently outperforms the previous methods on all the NLG domains.

2007

pdf bib
How has belief modality contributed to formal semantics?
Satoshi Tojo
Proceedings of the 21st Pacific Asia Conference on Language, Information and Computation

2006

pdf bib
Multi-dimensional Temporal Logic for Events and States
Satoshi Tojo
Proceedings of the Fifth International Workshop on Inference in Computational Semantics (ICoS-5)

2005

pdf bib
Analysis of The Elements by HPSG
Satoshi Tojo | Ken Saito
Proceedings of the 19th Pacific Asia Conference on Language, Information and Computation

1994

pdf bib
Free-ordered CUG on Chemical Abstract Machine
Satoshi Tojo
COLING 1994 Volume 2: The 15th International Conference on Computational Linguistics

1990

pdf bib
A Type-theoretical Analysis of Complex Verb Generation
Satoshi Tojo
COLING 1990 Volume 2: Papers presented to the 13th International Conference on Computational Linguistics