論文・実績

ジャーナル・国際会議論文 – Journal and international conference papers

1. Shun Katada, Ryu Takeda, Kazunori Komatani:
   Collecting Human-Agent Dialogue Dataset with Frontal Brain Signal toward Capturing Unexpressed Sentiment.
   Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), (accepted), 2024.

ジャーナル・国際会議論文 – Journal and international conference papers

1. 塩谷 尚正，木村 昌紀，北小屋 裕，駒谷 和範： 119番通報要領の事前知識が迅速性と正確性におよぼす影響ー模擬通報場面による実験的検討ー． 社会安全学研究，Vol. 14，pp.47-62, 2024. [pdf]
2. Ryu Takeda, Kazunori Komatani:
   Toward OOV-word Acquisition during Spoken Dialogue using Syllable-based ASR and Word Segmentation.
   International Workshop on Spoken Dialogue Systems (IWSDS), Mar. 6, 2024.
3. Mikio Nakano, Hisahiro Mukai, Yoichi Matsuyama, Kazunori Komatani:
   Evaluating Dialogue Systems from the System Owners’ Perspectives.
   International Workshop on Spoken Dialogue Systems (IWSDS), Mar. 4, 2024. [link]
4. Ryu Takeda, Hokuto Munakata, Kazunori Komatani:
   Link Prediction Based on Large Language Model and Knowledge Graph Retrieval under Open-World and Resource-Restricted Environment.
   International Joint Conference on Knowledge Graphs (IJCKG 2023), Dec. 8, 2023.
   (Best Research Paper Award)
5. Zhaojie Luo, Stefan Christiansson, Bence Ladoczki, Kazunori Komatani:
   Speech Emotion Recognition Using Threshold Fusion for Enhancing Audio Sensitivity.
   Workshop of Multimodal, Multilingual and Multitask Modeling Technologies for Oriental Languages (M3Oriental), pp. 3:1-3:5, Dec. 8, 2023. [doi]
6. Shuichi Chikatsuji, Kenta Yamamoto, Ryu Takeda, Kazunori Komatani:
   Knowledge Graph Augmentation with Entity Identification for Improving Knowledge Graph Completion Performance.
   Pacific Rim International Conference on Artificial Intelligence (PRICAI 2023), pp.480-486, Nov. 18, 2023. [doi]
7. Ryu Takeda, Yui Sudo, Kazunori Komatani:
   Flexible Evidence Model to Reduce Uncertainty Mismatch Between Speech Enhancement and ASR Based on Encoder-Decoder Architecture.
   Asia Pacific Signal and Information Processing Association Annual Summit and Conerence (APSIPA ASC), pp.1830-1837, Nov. 2, 2023. [doi]
8. Miki Oshio, Hokuto Munakata, Ryu Takeda, Kazunori Komatani:
   Out-Of-Vocabulary Word Detection in Spoken Dialogues Based on Joint Decoding with User Response Patterns.
   Asia Pacific Signal and Information Processing Association Annual Summit and Conerence (APSIPA ASC), pp.1753-1759, Nov. 2, 2023. [doi]
9. Zhaojie Luo, Kazunori Komatani:
   Multi-Modal Emotion Recognition Based on 2D Kernel Density Estimation for Multiple Labels Fusion.
   Asia Pacific Signal and Information Processing Association Annual Summit and Conerence (APSIPA ASC), pp.1484-1491, Nov. 2, 2023. [doi]
10. Kazunori Komatani, Ryu Takeda, Shogo Okada:
    Analyzing Differences in Subjective Annotations by Participants and Third-party Annotators in Multimodal Dialogue Corpus.
    24th Annual SIGDIAL Meeting on Discourse and Dialogue (SIGDIAL2023), pp. 104-113, Sep. 13, 2023. [doi]
11. Hokuto Munakata, Ryu Takeda, Kazunori Komatani:
    Recursive Sound Source Separation with Deep Learning-based Beamforming for Unknown Number of Sources.
    Interspeech 2023, pp. 1688-1692, Aug. 20, 2023. [doi]
12. Hokuto Munakata, Yoshiaki Bando, Ryu Takeda, Kazunori Komatani, Masaki Onishi:
    Joint Separation and Localization of Moving Sound Sources Based on Neural Full-Rank Spatial Covariance Analysis.
    IEEE Signal Processing Letters, Vol. 30, pp. 384-388, 2023. ［doi］

国内学会発表 – Domestic Conference Presentations

1. 平川 巧人，大塩 幹，近辻 脩壱，武田 龍，駒谷 和範： 誤りを含む音節認識結果に対応する知識グラフ内エンティティの同定． 情報処理学会全国大会, 4R-04, 3/16発表, 2024.
2. 峯瀬 平，堅田 俊，羅 兆傑，武田 龍，駒谷 和範： 異なる収録環境での対話音声に対する心象推定のためのL1距離に基づく特徴選択． 情報処理学会全国大会, 4R-03, 3/16発表, 2024.
3. 大塩 幹，武田 龍，駒谷 和範： 未知語認識機能を有する音声対話システムの構築とデータ収集． 情報処理学会全国大会, 4R-02, 3/16発表, 2024. （学生奨励賞受賞）
4. 久保 裕之輔，柳元 涼，山本 賢太，中野 幹生，武田 龍，駒谷 和範： 対話ロボットコンペティションのためのユーザ応答に対する肯定否定判定器の開発． 情報処理学会全国大会, 2W-09, 3/15発表, 2024.
5. 堀口 勇輝，山本 賢太，武田 龍，駒谷 和範： 特定ドメインの対話システムにおける発話矛盾検出のための前提文生成． 情報処理学会全国大会, 2W-03, 3/15発表, 2024.
6. 脇 一晟，堅田 俊，武田 龍，駒谷和範： 新語を含む単語分割のためのストリーム型能動学習における獲得関数の強化学習． 情報処理学会全国大会, 2W-02, 3/15発表, 2024. （学生奨励賞受賞）
7. 柳元 涼，山本 賢太，武田 龍，駒谷 和範： ユーザの性別・年齢・性格特性に基づくマルチモーダル心象推定． 情報処理学会全国大会, 2R-05, 3/15発表, 2024. （学生奨励賞受賞）
8. 山本 賢太，駒谷 和範： 大規模言語モデルにより性格特性を反映させた発話生成の評価．第100回言語・音声理解と対話処理研究会, pp.7-12, 2/29発表, 2024.  [doi]
9. Ryo Yanagimoto, Yunosuke Kubo, Miki Oshio, Mikio Nakano, Kenta Yamamoto, Kazunori Komatani: User-adaptive Tourist Information Dialogue System with Yes/No Classifier and Sentiment Estimator. arXiv preprint (Proceedings of the Dialogue Robot Competition 2023), 12/23発表, 2023. [doi] （優秀賞（2位）受賞）
10. 吉崎 亜里香，斉藤 まなぶ，村田 絵美，田中 早苗，平田 郁子，毛利 育子，駒谷 和範，谷池 雅子： 幼児の睡眠習慣を支援する双方向性アプリ「ねんねナビ」におけるAI技術に基づく介入事例． 第14回 日本臨床睡眠医学会学術集会 (ISMSJ), 10/7発表, 2023.

ジャーナル・国際会議論文 – Journal and international conference papers

1. Liyun Zhang, Photchara Ratsamee, Bowen Wang, Zhaojie Luo, Yuki Uranishi, Manabu Higashida, Haruo Takemura: Panoptic-aware Image-to-Image Translation. IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 259-268, 2023. [doi]
2. Shuyun Tang, Zhaojie Luo, Guoshun Nan, Jun Baba, Yuichiro Yoshikawa, Hiroshi Ishiguro: Fusion With Hierarchical Graphs for Multimodal Emotion Recognition. Asia Pacific Signal and Information Processing Association Annual Summit and Conference, pp. 1288-1296, 2022. [doi]
3. Shun Katada, Shogo Okada, Kazunori Komatani: Transformer-Based Physiological Feature Learning for Multimodal Analysis of Self-Reported Sentiment. International Conference on Multimodal Interaction (ICMI), pp. 349-358, Nov. 8, 2022. [doi]
4. Ryu Takeda, Yui Sudo, Kazuhiro Nakadai and Kazunori Komatani: Empirical Sampling from Latent Utterance-wise Evidence Model for Missing Data ASR based on Neural Encoder-Decoder Model. Interspeech 2022, pp. 3789-3793, Sep. 22, 2022. [doi]
5. Hokuto Munakata, Ryu Takeda, Kazunori Komatani: Training Data Generation with DOA-based Selecting and Remixing for Unsupervised Training of Deep Separation Models. Interspeech 2022, pp. 861-865, Sep. 20, 2022. [doi]
6. Zhaojie Luo, Shoufeng Lin, Rui Liu, Jun Baba, Yuichiro Yoshikawa, Ishiguro Hiroshi: Decoupling Speaker-independent Emotions for Voice Conversion Via Source-Filter Networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 31, No. 1, pp. 11-24, 2022. [doi]
7. Kazunori Komatani, Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano: User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues. Dialogue and Discourse, Vol. 13, No. 1, pp.96-122, 2022. ［doi］
8. Michimasa Inaba, Yuya Chiba, Ryuichiro Higashinaka, Kazunori Komatani, Yusuke Miyao, Takayuki Nagai: Collection and Analysis of Travel Agency Task Dialogues with Age-Diverse Speakers. Language Resources and Evaluation Conference (LREC), pp. 5759-5767, Jun. 21-23 (remote), 2022. [link] [pdf]
9. Zhaodong Wang, Kazunori Komatani: Graph-combined Coreference Resolution Methods on Conversational Machine Reading Comprehension with Pre-trained Language Model. Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp.72-82, May. 26, 2022. [doi]
10. Shun Katada, Shogo Okada, Kazunori Komatani: Effects of Physiological Signals in Different Types of Multimodal Sentiment Estimation. IEEE Transactions on Affective Computing, Vol. 14, Issue 3, pp.2443-2457, 2023. ［doi］
11. 武田 龍，駒谷 和範，中島 圭祐，中野 幹生： 複数の対話システムコンペティションにおけるシステム開発の設計指針． 人工知能学会論文誌，Vol.37, No.3，p. IDS-B_1-9，2022． ［doi］

解説 – Explanation

1. 駒谷 和範, 岡田 将吾： マルチモーダル対話コーパスHazumi． 自然言語処理, Vol.29, No.4, pp.1322-1329, 2022. ［doi］
2. 駒谷 和範： マルチモーダル対話コーパスの設計と公開． （小特集：音声対話システムにおける“不気味の谷”を超えるには） 日本音響学会誌, Vol.78, No.5, pp.265-270, 2022. ［doi］

国内学会発表 – Domestic Conference Presentations

1. 久保 祐喜, 羅 兆傑, 武田 龍, 駒谷 和範： マルチモーダル対話におけるクロスコーパスでの心象推定のための特徴量選択． 情報処理学会全国大会, 7U-04, 3/4発表, 2023. （学生奨励賞受賞）
2. 久保 裕之輔, 羅 兆傑, 武田 龍, 駒谷 和範： マルチモーダル対話におけるユーザごとの心象推定のための学習データの割当て． 情報処理学会全国大会, 7P-06, 3/4発表, 2023.
3. 生嶋 竜実, 武田 龍, 合原 一究, 駒谷 和範： カエルの合唱音声に対する教師ありモノラル音源分離のための音声合成によるデータ拡張． 情報処理学会全国大会, 5S-03, 3/3発表, 2023.
4. 宗像 北斗, 坂東 宜昭, 武田 龍, 駒谷 和範, 大西 正輝： 音源定位・分離の同時学習に基づく移動音源の深層ブラインド音源分離． 情報処理学会全国大会, 5S-01, 3/3発表, 2023. （学生奨励賞受賞）
5. 近辻 脩壱, 宗像 北斗, 武田 龍, 駒谷 和範： 知識グラフ補完性能向上のための同一エンティティ判定を用いた知識グラフ拡充． 情報処理学会全国大会, 4W-06, 3/3発表, 2023. （学生奨励賞受賞）
6. 大塩　幹, 宗像 北斗, 武田 龍, 駒谷 和範： 対話中のユーザの返答パターンに基づく音声発話中の未知語認識． 情報処理学会全国大会, 4S-04, 3/3発表, 2023. （学生奨励賞受賞）
7. 駒谷 和範, 武田 龍, 岡田 将吾： マルチモーダル対話コーパスに対する主観的アノテーション結果に関する分析． 第96回 言語・音声理解と対話処理研究会（第13回対話システムシンポジウム）, pp.181-186, 12/14発表, 2022. [doi]
8. 中野 幹生, 駒谷 和範： DialBB: 情報技術の教材を指向した対話システム構築フレームワーク． 第96回 言語・音声理解と対話処理研究会（第13回対話システムシンポジウム）, pp.175-180, 12/14発表, 2022. [doi]
9. 谷口 琉聖, 武田 龍, 駒谷 和範, 翠 輝久, 細見 直希, 山田 健太郎： 物体検出器により得た確信度が対話システム性能に与える影響． 第96回 言語・音声理解と対話処理研究会（第13回対話システムシンポジウム）, pp.63-68, 12/13発表, 2022. [doi]
10. Yuki Kubo, Ryo Yanagimoto, Hayato Futase, Mikio Nakano, Zhaojie Luo, Kazunori Komatani: Team OS’s System for Dialogue Robot Competition 2022. arXiv preprint (Proceedings of the Dialogue Robot Competition 2022), 10/25実施, 2022. [doi] （Outstanding Performance Award受賞）

ジャーナル・国際会議論文 – Journal and international conference papers

1. Hokuto Munakata, Ryu Takeda, Kazunori Komatani: Multiple-Embedding Separation Networks: Sound Class-Specific Feature Extraction for Universal Sound Separation. Asia Pacific Signal and Information Processing Association Annual Summit and Conerence (APSIPA ASC), pp.961-967, Dec. 17, 2021.
2. Ryu Takeda, Kazuhiro Nakadai, Kazunori Komatani: Spatial Normalization to Reduce Positional Complexity in Direction-Aided Supervised Binaural Sound Source Separation. Asia Pacific Signal and Information Processing Association Annual Summit and Conerence (APSIPA ASC), pp.248-253, Dec. 15, 2021.
3. Kazunori Komatani, Ryu Takeda, Keisuke Nakashima, Mikio Nakano: Design guidelines for developing systems for dialogue system competitions. International Workshop on Spoken Dialogue Systems (IWSDS), 16 pages, Nov. 16, 2021.
4. Yuki Hirano, Shogo Okada, Kazunori Komatani: Recognizing Social Signals with Weakly Supervised Multitask Learning for Multimodal dialogue Systems. International Conference on Multimodal Interaction (ICMI), pp.141-149, Oct. 20, 2021.
5. Wenqing Wei, Sixia Li, Shogo Okada, Kazunori Komatani: Multimodal User Satisfaction Recognition for Non-task Oriented Dialogue Systems. International Conference on Multimodal Interaction (ICMI), pp.586-594, Oct. 20, 2021.
6. Kazunori Komatani, Shogo Okada: Multimodal Human-Agent Dialogue Corpus with Annotations at Utterance and Dialogue Levels International Conference on Affective Computing & Intelligent Interaction (ACII), pp.1-8, Sep. 29, 2021.
7. Yuta Matsumoto, Takafumi Fujita, Arne Ludwig, Andreas D. Wieck, Kazunori Komatani, and Akira Oiwa: Noise-robust classification of single-shot electron spin readouts using a deep neural network. npj Quantum Information 7, Article number 136, 2021.
8. Ryu Takeda, Kazunori Komatani: Age Estimation with Speech-age Model for Heterogeneous Speech Datasets. Interspeech 2021, pp.4164-4168, Sep. 3, 2021.
9. Kazunori Komatani, Yuma Fujioka, Keisuke Nakashima, Katsuhiko Hayashi, Mikio Nakano: Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues. Annual Conference on Intelligent User Interfaces (IUI), pp.531-541, Apr. 15, 2021.

国内学会発表 – Domestic Conference Presentations

1. 奥野 尚己, 武田 龍, 駒谷 和範： 対話システムにおけるマルチモーダル情報を用いた自己開示の可否判断． 情報処理学会全国大会, 7ZE-01, 3/5発表, 2022. 学生奨励賞受賞
2. 吉田朋矢，生嶋竜実，武田　龍，駒谷和範： Vocal Effortの変動に頑健な話者識別のためのフィルタバンク特徴量の設計． 情報処理学会全国大会, 5R-08, 3/4発表, 2022.
3. 時末卓幹, 武田龍, 駒谷和範, 翠輝久, 細見直希, 山田健太郎： 不完全な物体検出結果に基づく対話を通じた目的地推定のための質問選択． 情報処理学会全国大会, 2ZE-04, 3/3発表, 2022.
4. 稲葉通将, 東中竜一郎, 千葉祐弥, 駒谷和範, 宮尾祐介, 長井隆行： 多様な年代の話者による旅行代理店タスク対話コーパスの収集と分析． 第93回 言語・音声理解と対話処理研究会（第12回対話システムシンポジウム）, pp.192-197, 11/30発表, 2021.
5. 久保祐喜, 生嶋竜実, 二瀬颯斗, 武田龍, 駒谷和範： ルールと用例を併用してユーザ発話を誘導する対話システムの構築． 第93回 言語・音声理解と対話処理研究会（第12回対話システムシンポジウム）, pp.125-130, 11/29発表, 2021. 
   第4回対話システムライブコンペティション シチュエーショントラック 優秀賞受賞
6. 黒田佑樹, 武田龍, 駒谷和範： システム発話間の整合性を重視した発話選択への深層強化学習の適用． 第93回 言語・音声理解と対話処理研究会（第12回対話システムシンポジウム）, pp.62-67, 11/29発表, 2021.

ジャーナル・国際会議論文 – Journal and international conference papers

1. Kazuhiro Nakadai, Yosuke Fukumoto, Ryu Takeda: Investigation of Node Pruning Criteria for Neural Networks Model Compression with Non-linear Function and Non-Uniform Network Topology. 8th IEEE Spoken Language Technology Workshop (SLT), pp.117-124, Jan., 2021.
2. Shun Katada, Shogo Okada, Yuki Hirano, Kazunori Komatani: Is She Truly Enjoying the Conversation?: Analysis of Physiological Signals toward Adaptive Dialogue Systems. International Conference on Multimodal Interaction (ICMI), pp.315-323, Oct. 27, 2020.
3. Ryu Takeda, Kazunori Komatani: Frame-wise Online Unsupervised Adaptation of DNN-HMM Acoustic Model from Perspective of Robust Adaptive Filtering. Interspeech 2020, pp.1291-1295, Oct. 26, 2020.
4. Mikio Nakano, Kazunori Komatani: A Framework for Building Closed-Domain Chat Dialogue Systems. Knowledge-Based Systems, Volume 204, 24 pages, 106212, September 2020.
5. Kazunori Komatani, Mikio Nakano: User Impressions of Questions to Acquire Lexical Knowledge. 21st Annual SIGDIAL Meeting on Discourse and Dialogue (SIGDIAL), pp.147‑156, Jul. 2, 2020.
6. 平野 裕貴，岡田 将吾，西本 遥人，駒谷 和範： マルチタスク学習による発話対ごとに付与された複数ラベルの推定． 電子情報通信学会論文誌，Vol.J104-A, No.2, pp.84-94，2021．

国内学会発表 – Domestic Conference Presentations

1. 宗像 北斗, 武田 龍, 駒谷 和範： モノラル音源分離のための音源間の類似度に基づく学習用混合信号の選択． 情報処理学会全国大会, 7N-04, 3/20発表, 2021.
2. 生嶋 竜実, 武田龍, 駒谷和範： 教師ありモノラル音声分離のための残響音声データ内の単一話者区間を活用した転移学習． 情報処理学会全国大会, 7N-03, 3/20発表, 2021. （学生奨励賞受賞）
3. 黒田 佑樹, 武田 龍, 駒谷 和範： システム発話間の内容的整合性を用いた強化学習に基づく発話選択． 情報処理学会全国大会, 4P-03, 3/19発表, 2021. （学生奨励賞受賞）
4. 駒谷 和範, 岡田 将吾, 堅田 俊： マルチモーダル対話コーパスHazumi公開と生体信号を含む新規データ収集． 第90回 言語・音声理解と対話処理研究会（第11回対話システムシンポジウム）, pp.170-177, 12/1発表, 2020.
5. 中島 圭祐, 駒谷 和範： グラフデータベース中のエンティティの分布を活用したシステム発話候補の自動抽出． 第90回 言語・音声理解と対話処理研究会（第11回対話システムシンポジウム）, pp.16-19, 11/30発表, 2020.
6. 市村匡輝, 武田龍, 駒谷和範： 空間スペクトルを用いた音声強調のための教師あり時間周波数マスク推定． 第19回情報科学技術フォーラム（FIT2020）, 9/1発表, 2020.

国際会議論文 – International Conference Papers

1. Ryu Takeda, Kazunori Komatani: Attribute Prediction of Unknown Lexical Entities Based on Mixture of Bayesian Segmentation Model. Life Long Learning for Spoken Language Systems Workshop, 7 pages, Dec. 14, 2019.
2. Yuki Hirano, Shogo Okada, Haruto Nishimoto, Kazunori Komatani: Multitask Prediction of Exchange-level Annotations for Multimodal Dialogue Systems. International Conference on Multimodal Interaction (ICMI), pp.85-94, Oct. 15, 2019. (Best Paper Runner-ups Award)
3. Kazunori Komatani, Shogo Okada, Haruto Nishimoto, Masahiro Araki, Mikio Nakano: Multimodal Dialogue Data Collection and Analysis of Annotation Disagreement. International Workshop on Spoken Dialogue Systems (IWSDS), 12 pages, Apr. 25, 2019.
4. Koki Kishimoto, Katsuhiko Hayashi, Genki Akai, Masashi Shimbo, Kazunori Komatani: Binarized Knowledge Graph Embeddings. 41st European Conference on IR Research (ECIR 2019), pp.181-196, Apr. 2019.

招待講演 – Invited Lectures

1. Kazunori Komatani: User-aware dialogue systems with adaptive responses (Invited Talk). International Conference on Natural Language Generation (INLG), Oct. 30, 2019.

ジャーナル論文 – Journal Papers

1. Arisa Ema, Hirotaka Osawa, Reina Saijo, Akinori Kubo, Takushi Otani, Hiromitsu Hattori, Naonori Akiya, Nobutsugu Kanzaki, Minao Kukita, Kazunori Komatani, Ryutaro Ichise: Clarifying Privacy, Property, and Power: Case Study on Value Conflict Between Communities. Proceedings of the IEEE，Volume, 107, Issue 3，pp.575–581, Mar. 2019.
2. Sho Hoshino, Yusuke Miyao, Katsuhito Sudoh, Katsuhiko Hayashi, Masaaki Nagata: A Simple Syntax-based Preordering Method for Statistical Machine Translation, Journal of Information Processing, Vol.60, No.3, Mar. 2019.
3. 古崎晃司, 溝口理一郎: オントロジー構築におけるPart-of記述とその実践 -ロール理論に基づく部分構造表現モデル, 人工知能学会論文誌, Vol.34, No.1, p. C-I52_1-13, 2019.
4. Aiko Endo, Terukazu Kumazawa, Michinori Kimura, Makoto Yamada, Takaaki Kato, Kouji Kozaki:Describing and Visualizing a Water-Energy-Food Nexus System, Water, Volume 10, Issue 9, 1245, 2018.
5. 熊澤 輝一，古崎 晃司: 環境・サステイナビリティ領域におけるドメイン知識間の因果論理構築支援ツールの開発. 人工知能学会論文誌, Vol.33, No.3, p. E-SGAI04_1-13, 2018.

解説 – Explanation

1. 駒谷 和範: 円滑な対話進行のための音声からの情報抽出. 電子情報通信学会誌, Vol.101, No.9, pp.908-913, 2018. [link]

国際会議論文 – International Conference Papers

1. Ryu Takeda, Kazunori Komatani, Alexander Rudnicky: Word Segmentation from Phoneme Sequences based on Pitman-Yor Semi-Makov Model Exploiting Subword Information. Proceedings of IEEE Workshop on Spoken Language Technology (SLT), pp.763-770, Dec. 20, 2018.
2. Tomoki Matsuno, Katsuhiko Hayashi, Takahiro Ishihara, Hitoshi Manabe, Yuji Matsumoto: Reduction of Parameter Redundancy in Biaffine Classifiers with Symmetric and Circulant Weight Matrices, The 32nd Pacific Asia Conference on Language, Information and Computation (PACLIC 32), pp.1-9, Dec. 2, 2018.
3. Tatsuya Kushida, Kouji Kozaki, Takahiro Kawamura, Yuka Tateisi, Yasunori Yamamoto, Toshihisa Takagi: Inference of Functions, Roles, and Applications of Chemicals Using Linked Open Data and Ontologies, The 8th Joint International Semantic Technology Conference (JIST2018), pp.385-397, Nov.26-28, 2018.
4. Julio Vizcarra, Kouji Kozaki, Miguel Torres-Ruiz, Rolando Quintero Tellez: Knowledge-based Identification of Emotional Status on Social Networks, The Joint International Workshop on PAOS2018 and PASSCR2018, Nov. 26, 2018.
5. Julio Vizcarra, Kouji Kozaki, Miguel Torres-Ruiz, Rolando Quintero Tellez: Content-Based Visualization System for Sentiment Analysis On Social Networks, The 8th Joint International Semantic Technology Conference (JIST2018), Nov. 26-28, 2018.
6. Ting Han, Sina Zariess, Kazunori Komatani, David Schlangen: Learning to describe multimodally from parallel unimodal data? A pilot study on verbal and sketched object descriptions. Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL2018 (AixDial)), pp.6-15, Nov. 19, 2018.
7. Kazuaki Yamabe, Chihiro Suga, Teruhisa Misu, Ryu Takeda, Kazunori Komatani: Predicting when drivers need AR navigation. The 8th Biennial Workshop on DSP for In-Vehicle and Mobile Systems, 7 pages, Oct. 9, 2018.
8. Ryu Takeda, Kazuhiro Nakadai, Kazunori Komatani: Multi-timescale Feature-extraction Architecture of Deep Neural Networks for Acoustic Model Training from Raw Speech Signal. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.2503-2510, Oct 2, 2018.
9. Shogo Okada, Kazunori Komatani: Investigating Effectiveness of Linguistic Features Based on Speech Recognition for Storytelling Skill Assessment. The 31st International Conference on Industrial, Engineering and Other Applications of Applied Intelligence Systems (IEA/AIE-2018), pp.148-157, June 26, 2018.
10. Hidetaka Kamigaito, Katsuhiko Hayashi, Tsutomu Hirao, Masaaki Nagata: Higher-order Syntactic Attention Network for Longer Sentence Compression. The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-2018), pp.1716-1726, June 4, 2018.
11. Takahiro Ishihara, Katsuhiko Hayashi, Hitoshi Manabe, Masashi Shimbo, Masaaki Nagata: Neural Tensor Networks with Diagonal Slice Matrices. The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-2018), pp.506-515, June 2, 2018.
12. Masahiro Araki, Sayaka Tomimasu, Mikio Nakano, Kazunori Komatani, Shogo Okada, Shinya Fujie, Hiroaki Sugiyama: Collection of Multimodal Dialog Data and Analysis of the Result of Annotation of Users’ Interests. Language Resources and Evaluation Conference (LREC), pp.1584-1588, May 10, 2018.
13. Ryu Takeda, Yoshiki Kudo, Kazuki Takashima, Yoshifumi Kitamura, Kazunori Komatani: Unsupervised Adaptation of Neural Networks for Discriminative Sound Source Localization with Eliminative Constraint. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.3514-3518, Apr. 20, 2018.

ジャーナル論文 – Journal Papers

1. 増田 壮志，古崎 晃司，駒谷 和範: 分類観点毎の概念階層の包括的な比較に基づくオントロジー品質向上支援システムの開発. 人工知能学会論文誌, Vol.33, No.2, 2018.
2. 大野 航平，武田 龍，ニコルズ エリック，中野 幹生，駒谷 和範： 対話を通じた未知語のクラス獲得に向けた暗黙的確認の提案． 人工知能学会論文誌，Vol.33, No.1，2018．
3. 林 克彦, 永田 昌明: K-best反復ビタビパージング, 情報処理学会論文誌, Vol. 59, No. 1, pp.227-235, 1月, 2018.
4. 古崎 晃司, 横山 輝明, 深見 嘉明: GPS移動履歴の収集とオープンデータを用いた移動軌跡のLOD化─国際会議ISWC2016における実証実験を例として─. デジタルプラクティス, Vol. 9 No. 1, pp.138-163, 1月, 2018.
5. Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano: User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems. Dialogue and Discourse, Vol. 8, No. 2, pp.206-224, 2017.
6. Ryu Takeda, Kazuhiro Nakadai and Kazunori Komatani: Acoustic Model Training based on Node-wise Weight Boundary Model for Fast and Small-footprint Deep Neural Networks. Computer Speech & Language, Volume 46, Pages 461-480, November 2017.
7. Xiaojun Ma, Takeshi Imai, Emiko Y. Shinohara, Ryota Sakurai, Kouji Kozaki, Kazuhiko Ohe: A Semi-Automatic Framework to Identify Abnormal States in EHR Narratives. Stud Health Technol Inform, Vol. 245, pp.910-914, 2017.
8. Kouji Kozaki, Yuki Yamagata, Riichiro Mizoguchi, Takeshi Imai, Kazuhiko Ohe: Disease Compass -A Navigation System for Disease Knowledge based on Ontology and Linked Data Techniques. Journal of Biomed Sem, Vol. 8, No.1:22, 2017.

国際会議論文 – International Conference Papers

1. Hitoshi Manabe, Katsuhiko Hayashi, Masashi Shimbo: Data-dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base Completion. Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), Feb. 5, 2018.
2. Shusaku Egami, Takahiro Kawamura, Kouji Kozaki and Akihiko Ohsuga: Urban Problem LOD for Understanding the Problem Structure and Detecting Vicious Cycles. The 12th IEEE International Conference on Semantic Computing (ICSC2018), Feb. 2, 2018.
3. Takeshi Masuda, Kouji Kozaki, Tatsuya Kushida, Yuka Tateisi, Katsutaro Watanabe, Katsuji Matsumura, Takahiro Kawamura, Kazunori Komatani: Extending A Bioscience Ontology Based on Comparison between Sibling Concepts. 8th International Conference on Internet Technologies & Society, Dec. 11, 2017.
4. Atsuko Yamaguchi, Kouji Kozaki, Yasunori Yamamoto, Hiroshi Masuya, Norio Kobayashi: LOD Surfer API: Web API for LOD Surfing Using Class-Class Relationships in Life Sciences. 10th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences (SWAT4LS 2017), Dec. 4-7, 2017.
5. Ryu Takeda, Kazunori Komatani: Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context. International Joint Conference on Natural Language Processing (IJCNLP), pp.243-252, Nov. 28, 2017.
6. Hidetaka Kamigaito, Katsuhiko Hayashi, Tsutomu Hirao, Masaaki Nagata, Hiroya Takamura, Manabu Okumura: Supervised Attention for Sequence-to-Sequence Constituency Parsing. International Joint Conference on Natural Language Processing (IJCNLP), pp.7-12, Nov. 27, 2017.
7. Tatsuya Kushida, Yuka Tateisi, Takeshi Masuda, Katsutaro Watanabe, Katsuji Matsumura, Takahiro Kawamura, Kouji Kozaki, Toshihisa Takagi: Refined JST Thesaurus Extended with Data from Other Open Life Science Data Sources. The 7th Joint International Semantic Technology Conference (JIST2017), pp. 35-48, Nov. 13, 2017.
8. Atsuko Yamaguchi, Kouji Kozaki, Yasunori Yamamoto, Hiroshi Masuya, Norio Kobayashi: Semantic Graph Analysis for Federated LOD Surfing in Life Sciences. The 7th Joint International Semantic Technology Conference (JIST2017), pp. 268-276, Nov. 12, 2017.
9. Shusaku Egami, Takahiro Kawamura, Kouji Kozaki, Akihiko Ohsuga: Linked Urban Open Data Including Social Problems’ Causality and Their Costs. The 7th Joint International Semantic Technology Conference (JIST2017), pp. 334-349, Nov. 12, 2017.
10. Kouji Kozaki, Teruaki Yokoyama, Yoshiaki Fukami: GPS Trajectory Linked Open Data based on Open POI Information -Through an Experiment in ISWC2016-. 16th International Semantic Web Conference Posters & Demonstrations Track, Oct. 23, 2017.
11. Takaaki Tanaka, Katsuhiko Hayashi, Masaaki Nagata: Hierarchical Word Structure-based Parsing: A Feasibility Study on UD-style Dependency Parsing in Japanese. 15th International Conference on Parsing Technologies (IWPT), pp.56-60, Sep. 21, 2017.
12. Tatsuya Kushida, Kouji Kozaki, Yuka Tateisi, Katsutaro Watanabe, Takeshi Masuda, Katsuji Matsumura, Takahiro Kawamura, Toshihisa Takagi: Efficient construction of a new ontology for life sciences by subclassifying related terms in the Japan Science and Technology Agency thesaurus. The 8th International Conference on Biomedical Ontology (ICBO 2017), Sep. 14, 2017.
13. Ryu Takeda, Kazuhiro Nakadai, Kazunori Komatani: Node pruning based on Entropy of Weights and Node Activity for Smal-footprint Acoustic Model based on Deep Neural Networks. Interspeech-2017, pp.1636-1640, Aug. 22, 2017.
14. Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano and Kazunori Komatani: Lexical Acquisition through Implicit Confirmations over Multiple Dialogues. 18th Annual SIGDIAL Meeting on Discourse and Dialogue, pp.50-59, Aug. 17, 2017.
15. Katsuhiko Hayashi, Masashi Shimbo: On the Equivalence of Holographic and Complex Embeddings for Link Prediction. 55th Annual Meeting of the Association for Computational Linguistics (ACL), pp.554-559, Aug. 1, 2017.
16. Shusaku Egami, Takahiro Kawamura, Kouji Kozaki, Akihiko Ohsuga: Construction of Linked Urban Problem Data with Causal Relations using Crowdsourcing. 6th International Congress on Advanced Applied Informatics (IIAI AAI 2017), July 11, 2017.
17. Arisa Ema, Hirotaka Osawa, Hiromitsu Hattori, Naonori Akiya, Nobutsugu Kanzaki, Ryutaro Ichise, Minao Kukita, Takushi Otani, Akinori Kubo, Kazunori Komatani, Reina Saijo, Mikihito Tanaka, Koziro Honda, Naoki Miyano, Yoshimi Yashiro, Go Yoshizawa: Breaking Down Silos: Involving Various Researchers for Driving HCI Research. CHI Conference on Human Factors in Computing Systems, Extended Abstracts, pp.837-847, May. 9, 2017.
18. Katsuhiko Hayashi, Masaaki Nagata: K-best Iterative Viterbi Parsing. 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp.3-7, Apr. 5, 2017.

ジャーナル論文 – Journal Papers

1. 増田 壮志, 古崎 晃司: 概念階層の比較に基づくオントロジー品質向上支援手法．人工知能学会論文誌，Vol.32, No.2，p.E-G71_1-10，2017．
2. Ryu Takeda, Kazuhiro Nakadai and Kazunori Komatani: Acoustic Model Training based on Node-wise Weight Boundary Model for Fast and Small-footprint Deep Neural Networks. Computer Speech & Language, 2017. (in press)
3. Ryu Takeda, Kazunori Komatani: Noise-robust MUSIC-based Sound Source Localization using Steering Vector Transformation for Small Humanoids. Journal of Robotics and Mechatronics, Vol.29, No.1, pp.26-36, 2017.
4. Ikkyu Aihara, Ryu Takeda, Takeshi Mizumoto, Takuma Otsuka, Hiroshi G. Okuno: Size Effect on Call Properties of Japanese Tree Frogs Revealed by Audio-Processing Technique. Journal of Robotics and Mechatronics, Vol.29, No.1, pp.247-254, 2017.
5. 杉山 貴昭，船越 孝太郎，中野 幹生，駒谷 和範： 多人数対話におけるユーザの状態に着目したロボットの応答義務の推定．人工知能学会論文誌，Vol.31, No.3，p.C-FB2_1-9，2016．

国際会議論文 – International Conference Papers

1. Ryu Takeda, Kazunori Komatani: Unsupervised Adaptation of Deep Neural Networks for Sound Source Localization using Entropy Minimization. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.2217-2221, Mar. 7, 2017.
2. Ryu Takeda, Kazunori Komatani: Discriminative Multiple Sound Source Localization based on Deep Neural Networks using Independent Location Model. Proceedings of IEEE Workshop on Spoken Language Technology (SLT), pp.603-609, Dec. 16, 2016.
3. Ryu Takeda, Kazunori Komatani: Bayesian Language Model based on Mixture of Segmental Contexts for Spontaneous Utterances with Unexpected Words. Proceedings of International Conference on Computational Linguistics (COLING), pp.161-170, Dec. 13, 2016.
4. Takahiro Kawamura, Kouji Kozaki, Tatsuya Kushida, Katsutaro Watanabe, Katsuji Matsumura: Expanding Science and Technology Thesauri from Bibliographic Datasets using Word Embedding, The 28th IEEE International Conference on Tools with Artificial Intelligence (ICTAI2016), 8 pages, Nov.8, 2016.
5. Atsuko Yamaguchi, Kouji Kozaki, Kai Lenz, Yasunori Yamamoto, Hiroshi Masuya, Norio Kobayashi: Semantic Data Acquisition by Traversing Class-Class Relationships over Linked Open Data, Proceedings of the 6th Joint International Semantic Technology (JIST2016),pp.136-151, Nov. 4, 2016.
6. Takeshi Masuda, Kouji Kozaki, Kazunori Komatani: Ontology Refinement System for Improving Consistency of Classification among Brother Concepts, Workshop and Poster Proceedings of the 6th Joint International Semantic Technology (JIST2016), pp.74-77, Nov. 3, 2016.
7. Atsuko Yamaguchi, Kouji Kozaki, Kai Lenz, Yasunori Yamamoto, Hiroshi Masuya, Norio Kobayashi: SPARQL Builder: Constructing SPARQL Query by Traversing Class-Class Relationships for Life Science Databases, Workshop and Poster Proceedings of the 6th Joint International Semantic Technology (JIST2016), pp.58-61, Nov. 3, 2016.
8. Tatsuya Kushida, Takeshi Masuda, Yuka Tateisi, Katsutaro Watanabe, Katsuji Matsumura, Takahiro Kawamura, Kouji Kozaki, Toshihisa Takagi: Refining JST thesaurus and discussing the effectiveness in life science research, Proceedings of International Workshop on Intelligent Exploration of Semantic Data (IESD2016), 12pages, Oct. 8, 2016.
9. Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano and Kazunori Komatani: Toward Lexical Acquisition during Dialogues through　Implicit Confirmation for Closed-Domain Chatbots. Proceedings of Second Workshop on Chatbots and Conversational Agent Technologies (WOCHAT), Sep. 20, 2016.
10. Takeshi Imai, Kazuhiko Ohe, Emiko Shinohara, Masayuki Kajino, Ryota Sakurai, Kouji Kozaki, Riichiro Mizoguchi: An Ontological Framework for Representing Topological Information in Human Anatomy, Proceedings of the 7th International Conference on Biomedical Ontology (ICBO 2016), 6pages, Aug. 3, 2016.

ジャーナル論文 – Journal Papers

1. 古崎 晃司, 來村 徳信, 溝口 理一郎: 生物規範工学オントロジーとLinked Dataに基づくキーワード探索. 人工知能学会論文誌, Vol.31, No.1, p.LOD-D_1-12, 2016.
2. 山縣 友紀, 古崎 晃司, 今井 健, 大江 和彦, 溝口 理一郎: 疾患知識統合に向けた異常状態オントロジーのLinked Data化. 人工知能学会論文誌, Vol.31, No.1, LOD-A_1-15, 2016.
3. Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano: Posteriori Restoration of Turn-Taking and ASR Results for Incorrectly Segmented Utterances. IEICE Transactions on Information and Systems, Vol.E98-D, No.11, pp.1923-1931, 2015.
4. Riichiro Mizoguchi, Antony Galton, Yoshinobu Kitamura, Kouji Kozaki: Families of roles: A new theory of occurrent-dependent roles. Applied Ontology, Vol.10, No.3-4, pp.367-399, 2015.

国際会議論文 – International Conference Papers

1. Ryu Takeda, Kazunori Komatani: Sound Source Localization based on Deep Neural Networks with Directional Activate Function Exploiting Phase Information. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), pp.405–409, Mar. 23, 2016.
2. Kazunori Komatani, Tsugumi Otsuka, Satoshi Sato, Mikio Nakano: Question Selection based on Expected Utility to Acquire Information through Dialogue. International Workshop on Spoken Dialogue Systems (IWSDS2016), 12 pages, Jan. 14, 2016.
3. Ryu Takeda, Kazuhiro Nakadai, Kazunori Komatani: Acoustic Model Training based on Node-wise Weight Boundary Model Increasing Speed of Discrete Neural Networks. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), pp.52-58, Dec. 14, 2015.
4. Ryu Takeda, Kazunori Komatani: Performance Comparison of MUSIC-based Sound Localization Methods on Small Humanoid under Low SNR Conditions. IEEE-RAS International Conference on Humanoid Robots (Humanoids 2015), pp.859–865, Nov. 4, 2015.
5. Takaaki Sugiyama, Kotaro Funakoshi, Mikio Nakano, Kazunori Komatani: Estimating Response Obligation in Multi-Party Human-Robot Dialogues. IEEE-RAS International Conference on Humanoid Robots (Humanoids 2015), pp.166–172, Nov. 3, 2015.
6. Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano: User Adaptive Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems. 16th Annual SIGDIAL Meeting on Discourse and Dialogue, pp.393–401, Sep. 4, 2015.

国際会議論文 – International Conference Papers

1. Naoki Hotta, Kazunori Komatani, Satoshi Sato, Mikio Nakano: Detecting Incorrectly-Segmented Utterances for Posteriori Restoration of Turn-Taking and ASR Results. Interspeech-2014, pp.313-317, Sep. 15, 2014.