Search Results - "Akiba, Tomoyosi"

Taking advantage of spontaneous speech for document retrieval: Lessons from the organization of evaluation tasks by Akiba, Tomoyosi

“…This work reports our experiments on organizing evaluation tasks aiming at spoken document retrieval (SDR). The NTCIR Project is a series of evaluation…”
Get full text

Agenda Extraction from Assembly Minutes by exploiting Relation between Questions and Answers by Ohsugi, Ryoto, Akiba, Tomoyosi, Masuyama, Shigeru

“…Obtaining agenda discussed in assembly minutes is useful for grasping their structure. In this paper, we propose a method to automatically extract a list of…”
Get full text

English-Japanese Machine Translation for Lecture Subtitles using Back-Translation and Transfer Learning by Yamagishi, Yuuki, Akiba, Tomoyosi, Tsukada, Hajime

“…In this study, we report our efforts to improve the performance of English-Japanese machine translation on the "Technology, Entertainment, Design (TED)"…”
Get full text

Rapid Speaker Adaptation of Neural Network Based Filterbank Layer for Automatic Speech Recognition by Seki, Hiroshi, Yamamoto, Kazumasa, Akiba, Tomoyosi, Nakagawa, Seiichi

“…Deep neural networks (DNN) have achieved significant success in the field of automatic speech recognition. Previously, we proposed a filterbank-incorporated…”
Get full text

Semi-supervised ASR based on Iterative Joint Training with Discrete Speech Synthesis by Takagi, Keiya, Akiba, Tomoyosi, Tsukada, Hajime

“…This paper proposes Iterative Joint Training (IJT) with discrete speech synthesis for semi-supervised ASR. Thanks to the recent advances in Text-to-Speech…”
Get full text

Using a Sequence-to-sequence Model for Large-scale Automated ICD Coding by Hatanaka, Hiroki, Akiba, Tomoyosi

“…In the domain of NLP (Natural Language Processing), there are studies on automated ICD coding from text data. Due to the sparsity of the training data, it is…”
Get full text

Abstractive Approach for Agenda Extraction from Assembly Minutes by Ohsugi, Ryoto, Akiba, Tomoyosi, Masuyama, Shigeru

“…Automatic agenda extraction from minutes is useful for quickly grasping the contents discussed in the meeting. Extracted agendas can also be used as indexes…”
Get full text

Development of Political QA Systems aimed at Assembly Minutes based on Abstractive Summarization by Kawai, Teruya, Akiba, Tomoyosi, Masuyama, Shigeru

“…The assembly minutes published on the Web by local assemblies in Japan are not fully utilized. They are very long and complex in structure, making it difficult…”
Get full text

Addressing unknown word problem for neural machine translation using distributee representations of words as input features by Nishimura, Tomoki, Akiba, Tomoyosi

“…In recent years, the machine translation system based on neural network, called Neural Machie Translation, have attracted much attention, in which the entire…”
Get full text

Multi-label Disease Classification of Patient's Tweets using Automatically Acquired Training Corpus by Okuda, Tomohiro, Asakawa, Reine, Akiba, Tomoyosi

“…Morbidity determination using tweet data is currently drawing huge attention within the field of influenza outbreak prediction. This work aims to develop a…”
Get full text

Effects of class-based statistical machine translation on unknown names by Mizukami, Hitoshi, Akiba, Tomoyosi

“…This paper address the issue of dealing with named entities in statistical machine translation (SMT). Named entities (NEs) tend to become out-of-vocabulary of…”
Get full text

ICD-10 code retrieval based on distributional semantics of diagnosis descriptions by Akiba, Tomoyosi, Sy, Bon, Zeidan, Ayman

“…In this paper, we propose a method for extracting ICD-10 codes from the natural language description of a patient illness complaint. The proposed method is…”
Get full text

Open vocabulary spoken content retrieval by front-ending with spoken term detection by Takigami, Tomoko, Akiba, Tomoyosi

“…How to deal with speech recognition errors and out-of-vocabulary (OOV) words are common challenging problems in spoken document processing. In this work, we…”
Get full text

Incorporating syllable duration into line-detection-based spoken term detection by Ohno, T., Akiba, T.

“…A conventional method for spoken term detection (STD) is to apply approximate string matching to subword sequences in a spoken document obtained by speech…”
Get full text

Effects of Language Modeling on Speech-driven Question Answering by Akiba, Tomoyosi, Fujii, Atsushi, Itou, Katunobu

“…Proceedings of the 8th International Conference on Spoken Language Processing (ICSLP 2004), pp.1053-1056, Oct. 2004 We integrate automatic speech recognition…”
Get full text

Unsupervised Topic Adaptation for Lecture Speech Retrieval by Fujii, Atsushi, Itou, Katunobu, Akiba, Tomoyosi, Ishikawa, Tetsuya

“…Proceedings of the 8th International Conference on Spoken Language Processing (ICSLP 2004), pp.2957-2960, Oct. 2004 We are developing a cross-media information…”
Get full text

A Cross-media Retrieval System for Lecture Videos by Fujii, Atsushi, Itou, Katunobu, Akiba, Tomoyosi, Ishikawa, Tetsuya

“…Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech 2003), pp.1149-1152, Sep. 2003 We propose a cross-media…”
Get full text