H
Hideki Isozaki
Researcher at Nippon Telegraph and Telephone
Publications - 83
Citations - 2541
Hideki Isozaki is an academic researcher from Nippon Telegraph and Telephone. The author has contributed to research in topics: Machine translation & Sentence. The author has an hindex of 25, co-authored 83 publications receiving 2445 citations.
Papers
More filters
Proceedings Article
Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach
TL;DR: This paper proposes a framework for semi-supervised structured output learning (SOL), specifically for sequence labeling, based on a hybrid generative and discriminative approach that significantly outperforms the stateof-the-art performance obtained with supervised SOL methods, such as conditional random fields (CRFs).
Proceedings Article
Sequence and Tree Kernels with Statistical Feature Mining
Jun Suzuki,Hideki Isozaki +1 more
TL;DR: This paper discusses the issue of convolution kernels and proposes a statistical feature selection that enable us to use larger sub-structures effectively and compares the performance of a conventional method to that of the proposed method.
Proceedings ArticleDOI
Effects of self-disclosure and empathy in human-computer dialogue
TL;DR: This analysis shows that empathic utterances by users are strong indicators of increasing closeness and user satisfaction, and self-disclosure by users increases when users have positive preferences on topics being discussed.
NTT's Text Summarization System for DUC-2002
TL;DR: The result of the Single-Document Summarization task shows that the summarization system employs the machine learning algorithm, Support Vector Machines, to classify a sentence into an important or an unimportant sentence.
Proceedings ArticleDOI
Incorporating Speech Recognition Confidence into Discriminative Named Entity Recognition of Speech Data
TL;DR: In experiments using support vector machines (SVMs) and speech data from Japanese newspaper articles, the proposed method outperformed a simple application of text-based NER to ASR results in NER F-measure by improving precision.