Hideki Isozaki


2015

pdf
Dependency Analysis of Scrambled References for Better Evaluation of Japanese Translation
Hideki Isozaki | Natsume Kouchi
Proceedings of the Tenth Workshop on Statistical Machine Translation

2014

pdf
Dependency-based Automatic Enumeration of Semantically Equivalent Word Orders for Evaluating Japanese Translations
Hideki Isozaki | Natsume Kouchi | Tsutomu Hirao
Proceedings of the Ninth Workshop on Statistical Machine Translation

2012

pdf bib
Head finalization: translation from SVO to SOV
Hideki Isozaki
Proceedings of the 9th International Workshop on Spoken Language Translation: Keynotes

2011

pdf
Learning Condensed Feature Representations from Large Unsupervised Data Sets for Supervised Learning
Jun Suzuki | Hideki Isozaki | Masaaki Nagata
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2010

pdf
Head Finalization: A Simple Reordering Rule for SOV Languages
Hideki Isozaki | Katsuhito Sudoh | Hajime Tsukada | Kevin Duh
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

pdf
N-Best Reranking by Multitask Learning
Kevin Duh | Katsuhito Sudoh | Hajime Tsukada | Hideki Isozaki | Masaaki Nagata
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

pdf
Automatic Evaluation of Translation Quality for Distant Language Pairs
Hideki Isozaki | Tsutomu Hirao | Kevin Duh | Katsuhito Sudoh | Hajime Tsukada
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

2009

pdf bib
Structural support vector machines for log-linear approach in statistical machine translation
Katsuhiko Hayashi | Taro Watanabe | Hajime Tsukada | Hideki Isozaki
Proceedings of the 6th International Workshop on Spoken Language Translation: Papers

Minimum error rate training (MERT) is a widely used learning method for statistical machine translation. In this paper, we present a SVM-based training method to enhance generalization ability. We extend MERT optimization by maximizing the margin between the reference and incorrect translations under the L2-norm prior to avoid overfitting problem. Translation accuracy obtained by our proposed methods is more stable in various conditions than that obtained by MERT. Our experimental results on the French-English WMT08 shared task show that degrade of our proposed methods is smaller than that of MERT in case of small training data or out-of-domain test data.

pdf
A Syntax-Free Approach to Japanese Sentence Compression
Tsutomu Hirao | Jun Suzuki | Hideki Isozaki
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf
A Succinct N-gram Language Model
Taro Watanabe | Hajime Tsukada | Hideki Isozaki
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers

pdf
An Empirical Study of Semi-supervised Structured Conditional Models for Dependency Parsing
Jun Suzuki | Hideki Isozaki | Xavier Carreras | Michael Collins
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Analysis of Listening-Oriented Dialogue for Building Listening Agents
Toyomi Meguro | Ryuichiro Higashinaka | Kohji Dohsaka | Yasuhiro Minami | Hideki Isozaki
Proceedings of the SIGDIAL 2009 Conference

2008

pdf
NTT statistical machine translation system for IWSLT 2008.
Katsuhito Sudoh | Taro Watanabe | Jun Suzuki | Hajime Tsukada | Hideki Isozaki
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

The NTT Statistical Machine Translation System consists of two primary components: a statistical machine translation decoder and a reranker. The decoder generates k-best translation canditates using a hierarchical phrase-based translation based on synchronous context-free grammar. The decoder employs a linear feature combination among several real-valued scores on translation and language models. The reranker reorders the k-best translation candidates using Ranking SVMs with a large number of sparse features. This paper describes the two components and presents the results for the evaluation campaign of IWSLT 2008.

pdf
Corpus-based Question Answering for why-Questions
Ryuichiro Higashinaka | Hideki Isozaki
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf
Multi-label Text Categorization with Model Combination based on F1-score Maximization
Akinori Fujino | Hideki Isozaki | Jun Suzuki
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-II

pdf
Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data
Jun Suzuki | Hideki Isozaki
Proceedings of ACL-08: HLT

2007

pdf
Online Large-Margin Training for Statistical Machine Translation
Taro Watanabe | Jun Suzuki | Hajime Tsukada | Hideki Isozaki
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf
Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach
Jun Suzuki | Akinori Fujino | Hideki Isozaki
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf
Learning to Rank Definitions to Generate Quizzes for Interactive Information Presentation
Ryuichiro Higashinaka | Kohji Dohsaka | Hideki Isozaki
Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions

pdf
Larger feature set approach for machine translation in IWSLT 2007
Taro Watanabe | Jun Suzuki | Katsuhito Sudoh | Hajime Tsukada | Hideki Isozaki
Proceedings of the Fourth International Workshop on Spoken Language Translation

The NTT Statistical Machine Translation System employs a large number of feature functions. First, k-best translation candidates are generated by an efficient decoding method of hierarchical phrase-based translation. Second, the k-best translations are reranked. In both steps, sparse binary features — of the order of millions — are integrated during the search. This paper gives the details of the two steps and shows the results for the Evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2007.

2006

pdf
Training Conditional Random Fields with Multivariate Evaluation Measures
Jun Suzuki | Erik McDermott | Hideki Isozaki
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf
Incorporating Speech Recognition Confidence into Discriminative Named Entity Recognition of Speech Data
Katsuhito Sudoh | Hajime Tsukada | Hideki Isozaki
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf
Left-to-Right Target Generation for Hierarchical Phrase-Based Translation
Taro Watanabe | Hajime Tsukada | Hideki Isozaki
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf
NTT statistical machine translation for IWSLT 2006
Taro Watanabe | Jun Suzuki | Hajime Tsukada | Hideki Isozaki
Proceedings of the Third International Workshop on Spoken Language Translation: Evaluation Campaign

pdf
NTT System Description for the WMT2006 Shared Task
Taro Watanabe | Hajime Tsukada | Hideki Isozaki
Proceedings on the Workshop on Statistical Machine Translation

2005

pdf
The NTT Statistical Machine Translation System for IWSLT2005
Hajime Tsukada | Taro Watanabe | Jun Suzuki | Hideto Kazawa | Hideki Isozaki
Proceedings of the Second International Workshop on Spoken Language Translation

pdf
Boosting-based Parse Reranking with Subtree Features
Taku Kudo | Jun Suzuki | Hideki Isozaki
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05)

pdf
Kernel-based Approach for Automatic Evaluation of Natural Language Generation Technologies: Application to Automatic Summarization
Tsutomu Hirao | Manabu Okumura | Hideki Isozaki
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing

2004

pdf
Convolution Kernels with Feature Selection for Natural Language Processing Tasks
Jun Suzuki | Hideki Isozaki | Eisaku Maeda
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf
A Deterministic Word Dependency Analyzer Enhanced With Preference Learning
Hideki Isozaki | Hideto Kazawa | Tsutomu Hirao
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

pdf
Dependency-based Sentence Alignment for Multiple Document Summarization
Tsutomu Hirao | Jun Suzuki | Hideki Isozaki | Eisaku Maeda
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

pdf
Evaluation Measures Considering Sentence Concatenation for Automatic Summarization by Sentence or Word Extraction
Chiori Hori | Tsutomu Hirao | Hideki Isozaki
Text Summarization Branches Out

2003

pdf
Japanese Zero Pronoun Resolution based on Ranking Rules and Machine Learning
Hideki Isozaki | Tsutomu Hirao
Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing

pdf
Spoken Interactive ODQA System: SPIQA
Chiori Hori | Takaaki Hori | Hajime Tsukada | Hideki Isozaki | Yutaka Sasaki | Eisaku Maeda
The Companion Volume to the Proceedings of 41st Annual Meeting of the Association for Computational Linguistics

2002

pdf
Extracting Important Sentences with Support Vector Machines
Tsutomu Hirao | Hideki Isozaki | Eisaku Maeda | Yuji Matsumoto
COLING 2002: The 19th International Conference on Computational Linguistics

pdf
Efficient Support Vector Classifiers for Named Entity Recognition
Hideki Isozaki | Hideto Kazawa
COLING 2002: The 19th International Conference on Computational Linguistics

2001

pdf
Japanese Named Entity Recognition based on a Simple Rule Generator and Decision Tree Learning
Hideki Isozaki
Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics