Tomoki Toda

Also published as: Tomiki Toda


2015

pdf
An Investigation of Machine Translation Evaluation Metrics in Cross-lingual Question Answering
Kyoshiro Sugiyama | Masahiro Mizukami | Graham Neubig | Koichiro Yoshino | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the Tenth Workshop on Statistical Machine Translation

pdf
Ckylark: A More Robust PCFG-LA Parser
Yusuke Oda | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations

pdf
Semantic Parsing of Ambiguous Input through Paraphrasing and Verification
Philip Arthur | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Transactions of the Association for Computational Linguistics, Volume 3

We propose a new method for semantic parsing of ambiguous and ungrammatical input, such as search queries. We do so by building on an existing semantic parsing framework that uses synchronous context free grammars (SCFG) to jointly model the input sentence and output meaning representation. We generalize this SCFG framework to allow not one, but multiple outputs. Using this formalism, we construct a grammar that takes an ambiguous input string and jointly maps it into both a meaning representation and a natural language paraphrase that is less ambiguous than the original input. This paraphrase can be used to disambiguate the meaning representation via verification using a language model that calculates the probability of each paraphrase.

pdf
Syntax-based Simultaneous Translation through Prediction of Unseen Syntactic Constituents
Yusuke Oda | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf
Improving Pivot Translation by Remembering the Pivot
Akiva Miura | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

pdf
Improving translation of emphasis with pause prediction in speech-to-speech translation systems
Quoc Truong Do | Sakriani Sakti | Graham Neubig | Tomoki Toda | Satoshi Nakamura
Proceedings of the 12th International Workshop on Spoken Language Translation: Papers

2014

pdf
Acquiring a Dictionary of Emotion-Provoking Events
Hoa Trong Vu | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers

pdf
Linguistic and Acoustic Features for Automatic Identification of Autism Spectrum Disorders in Children’s Narrative
Hiroki Tanaka | Sakriani Sakti | Graham Neubig | Tomoki Toda | Satoshi Nakamura
Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality

pdf
Rule-based Syntactic Preprocessing for Syntax-based Machine Translation
Yuto Hatakoshi | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation

pdf
Collection of a Simultaneous Translation Corpus for Comparative Analysis
Hiroaki Shimizu | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

This paper describes the collection of an English-Japanese/Japanese-English simultaneous interpretation corpus. There are two main features of the corpus. The first is that professional simultaneous interpreters with different amounts of experience cooperated with the collection. By comparing data from simultaneous interpretation of each interpreter, it is possible to compare better interpretations to those that are not as good. The second is that for part of our corpus there are already translation data available. This makes it possible to compare translation data with simultaneous interpretation data. We recorded the interpretations of lectures and news, and created time-aligned transcriptions. A total of 387k words of transcribed data were collected. The corpus will be helpful to analyze differences in interpretations styles and to construct simultaneous interpretation systems.

pdf
Towards Multilingual Conversations in the Medical Domain: Development of Multilingual Medical Data and A Network-based ASR System
Sakriani Sakti | Keigo Kubo | Sho Matsumiya | Graham Neubig | Tomoki Toda | Satoshi Nakamura | Fumihiro Adachi | Ryosuke Isotani
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

This paper outlines the recent development on multilingual medical data and multilingual speech recognition system for network-based speech-to-speech translation in the medical domain. The overall speech-to-speech translation (S2ST) system was designed to translate spoken utterances from a given source language into a target language in order to facilitate multilingual conversations and reduce the problems caused by language barriers in medical situations. Our final system utilizes a weighted finite-state transducers with n-gram language models. Currently, the system successfully covers three languages: Japanese, English, and Chinese. The difficulties involved in connecting Japanese, English and Chinese speech recognition systems through Web servers will be discussed, and the experimental results in simulated medical conversation will also be presented.

pdf
Optimizing Segmentation Strategies for Simultaneous Speech Translation
Yusuke Oda | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf
Discriminative Language Models as a Tool for Machine Translation Error Analysis
Koichi Akabe | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf
Reinforcement Learning of Cooperative Persuasive Dialogue Policies using Framing
Takuya Hiraoka | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf
Towards High-Reliability Speech Translation in the Medical Domain
Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura | Yuji Matsumoto | Ryosuke Isotani | Yukichi Ikeda
The First Workshop on Natural Language Processing for Medical and Healthcare Fields

pdf
The NAIST English speech recognition system for IWSLT 2013
Sakriani Sakti | Keigo Kubo | Graham Neubig | Tomoki Toda | Satoshi Nakamura
Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper describes the NAIST English speech recognition system for the IWSLT 2013 Evaluation Campaign. In particular, we participated in the ASR track of the IWSLT TED task. Last year, we participated in collaboration with Karlsruhe Institute of Technology (KIT). This year is our first time to build a full-fledged ASR system for IWSLT solely developed by NAIST. Our final system utilizes weighted finitestate transducers with four-gram language models. The hypothesis selection is based on the principle of system combination. On the IWSLT official test set our system introduced in this work achieves a WER of 9.1% for tst2011, 10.0% for tst2012, and 16.2% for the new tst2013.

pdf bib
Constructing a speech translation system using simultaneous interpretation data
Hiroaki Shimizu | Graham Neubig | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 10th International Workshop on Spoken Language Translation: Papers

There has been a fair amount of work on automatic speech translation systems that translate in real-time, serving as a computerized version of a simultaneous interpreter. It has been noticed in the field of translation studies that simultaneous interpreters perform a number of tricks to make the content easier to understand in real-time, including dividing their translations into small chunks, or summarizing less important content. However, the majority of previous work has not specifically considered this fact, simply using translation data (made by translators) for learning of the machine translation system. In this paper, we examine the possibilities of additionally incorporating simultaneous interpretation data (made by simultaneous interpreters) in the learning process. First we collect simultaneous interpretation data from professional simultaneous interpreters of three levels, and perform an analysis of the data. Next, we incorporate the simultaneous interpretation data in the learning of the machine translation system. As a result, the translation style of the system becomes more similar to that of a highly experienced simultaneous interpreter. We also find that according to automatic evaluation metrics, our system achieves performance similar to that of a simultaneous interpreter that has 1 year of experience.

2012

pdf
The NAIST machine translation system for IWSLT2012
Graham Neubig | Kevin Duh | Masaya Ogushi | Takamoto Kano | Tetsuo Kiso | Sakriani Sakti | Tomoki Toda | Satoshi Nakamura
Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper describes the NAIST statistical machine translation system for the IWSLT2012 Evaluation Campaign. We participated in all TED Talk tasks, for a total of 11 language-pairs. For all tasks, we use the Moses phrase-based decoder and its experiment management system as a common base for building translation systems. The focus of our work is on performing a comprehensive comparison of a multitude of existing techniques for the TED task, exploring issues such as out-of-domain data filtering, minimum Bayes risk decoding, MERT vs. PRO tuning, word alignment combination, and morphology.

pdf
The 2012 KIT and KIT-NAIST English ASR systems for the IWSLT evaluation
Christian Saam | Christian Mohr | Kevin Kilgour | Michael Heck | Matthias Sperber | Keigo Kubo | Sebatian Stüker | Sakriani Sakri | Graham Neubig | Tomoki Toda | Satoshi Nakamura | Alex Waibel
Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper describes our English Speech-to-Text (STT) systems for the 2012 IWSLT TED ASR track evaluation. The systems consist of 10 subsystems that are combinations of different front-ends, e.g. MVDR based and MFCC based ones, and two different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cM-LLR.

pdf
The KIT-NAIST (contrastive) English ASR system for IWSLT 2012
Michael Heck | Keigo Kubo | Matthias Sperber | Sakriani Sakti | Sebastian Stüker | Christian Saam | Kevin Kilgour | Christian Mohr | Graham Neubig | Tomoki Toda | Satoshi Nakamura | Alex Waibel
Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper describes the KIT-NAIST (Contrastive) English speech recognition system for the IWSLT 2012 Evaluation Campaign. In particular, we participated in the ASR track of the IWSLT TED task. The system was developed by Karlsruhe Institute of Technology (KIT) and Nara Institute of Science and Technology (NAIST) teams in collaboration within the interACT project. We employ single system decoding with fully continuous and semi-continuous models, as well as a three-stage, multipass system combination framework built with the Janus Recognition Toolkit. On the IWSLT 2010 test set our single system introduced in this work achieves a WER of 17.6%, and our final combination achieves a WER of 14.4%.

pdf bib
A method for translation of paralinguistic information
Takatomo Kano | Sakriani Sakti | Shinnosuke Takamichi | Graham Neubig | Tomoki Toda | Satoshi Nakamura
Proceedings of the 9th International Workshop on Spoken Language Translation: Papers

This paper is concerned with speech-to-speech translation that is sensitive to paralinguistic information. From the many different possible paralinguistic features to handle, in this paper we chose duration and power as a first step, proposing a method that can translate these features from input speech to the output speech in continuous space. This is done in a simple and language-independent fashion by training a regression model that maps source language duration and power information into the target language. We evaluate the proposed method on a digit translation task and show that paralinguistic information in input speech appears in output speech, and that this information can be used by target language speakers to detect emphasis.

2006

pdf
Transcription Cost Reduction for Constructing Acoustic Models Using Acoustic Likelihood Selection Criteria
Tomoyuki Kato | Tomiki Toda | Hiroshi Saruwatari | Kiyohiro Shikano
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

This paper describes a novel method for reducing the transcription effort in the construction of task-adapted acoustic models for a practical automatic speech recognition (ASR) system. We have to prepare actual data samples collected in the practical system and transcribe them for training the task-adapted acoustic models. However, transcribing utterances is a time-consuming and laborious process. In the proposed method, we firstly adapt initial models to acoustic environment of the system using a small number of collected data samples with transcriptions. And then, we automatically select informative training data samples to be transcribed from a large-sized speech corpus based on acoustic likelihoods of the models. We perform several experimental evaluations in the framework of “Takemarukun”, a practical speech-oriented guidance system. Experimental results show that 1) utterance sets with low likelihoods cause better task-adapted models compared with those with high likelihoods although the set with the lowest likelihoods causes the performance degradation because of including outliers, and 2) MLLR adaptation is effective for training the task-adapted models when the amount of the transcribed data is small and EM training outperforms MLLR if we transcribe more than around 10,000 utterances.

2004

pdf
Perceptual Evaluation of Quality Deterioration Owing to Prosody Modification
Kazuki Adachi | Tomoki Toda | Hiromichi Kawanami | Hiroshi Saruwatari | Kiyohiro Shikano
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

2002

pdf
Designing speech database with prosodic variety for expressive TTS system
Hiromichi Kawanami | Tsuyoshi Masuda | Tomoki Toda | Kiyohiro Shikano
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02)