MURAWAKI Yugo
Last Update: March 4, 2023.
日本の組織を所属とする者が、2022年に言語処理のトップカンファレンスもしくはトップ論文誌で発表した論文一覧です (2021年版、2020年版、2019年版、2018年版、2017年版、2016年版) (2015年版、2014年版は Graham Neubig さん (NAIST、現 CMU) が作成)。 対象は TACL、ACL、NAACL、COLING、EMNLP です (Findings は除外)。Student/Demo 論文も含みます。 収集は手作業なので漏れがあるかもしれません。 データ・スクリプトは GitHub で公開しているのでご自由にお使いください。
方針:| 数 | 所属 |
|---|---|
| 11.10 | 東工大 |
| 10.61 | 東大 |
| 6.31 | 理研 |
| 4.11 | 京大 |
| 3.58 | 東北大 |
| 3.38 | 早大 |
| 2.24 | NII |
| 1.92 | 産総研 |
| 1.75 | NTT |
| 1.63 | 名大 |
| 1.63 | 都立大 |
| 1.50 | 慶応大 |
| 1.15 | NAIST |
| 1.00 | 電通大 |
| 1.00 | 日立 |
| 1.00 | 豊田中央研究所 |
| 0.98 | NICT |
| 0.94 | Studio Ousia |
| 0.92 | Yahoo |
| 0.88 | 阪大 |
| 0.88 | 愛媛大 |
| 0.75 | 富士フィルム |
| 0.75 | 東芝 |
| 0.38 | LegalForce |
| 0.31 | Langsmith |
| 0.28 | JST |
| 0.25 | 九大 |
| 0.20 | LINE |
| 0.17 | CogSmart |
| 0.13 | OMRON SINIC X |
| 0.13 | 国語研 |
| 0.13 | 甲南大 |
| 0.13 | 目白大 |
| 0.13 | 筑波大 |
| 0.13 | 統数研 |
| 0.08 | お茶大 |
| 0.08 | 豊田工大 |
| 0.08 | KDDI |
| 0.05 | 神田外語大 |
| 種別 | 著者 (所属) | 論文表題 |
|---|---|---|
| LONG | Noriki Nishida (理研) Yuji Matsumoto (理研) | Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation |
| LONG | Gaku Morio (日立) Hiroaki Ozaki (日立) Terufumi Morishita (日立) Kohsuke Yanai (日立) | End-to-end Argument Mining with Cross-corpora Multi-task Learning |
| LONG | Hitomi Yanaka (東大) Koji Mineshima (慶応大) | Compositional Evaluation on Japanese Textual Entailment and Similarity |
| LONG | Yi Zhou (リバプール大) Masahiro Kaneko (東工大) Danushka Bollegala (リバプール大; Amazon) | Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings |
| LONG | Jinyu Guo (北京郵電大) Kai Shuang (北京郵電大) Jijie Li (北京郵電大) Zihan Wang (東大) Yixuan Liu (北京郵電大) | Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking |
| LONG | Pride Kavumba (東北大; 理研) Ryo Takahashi (LegalForce) Yusuke Oda (LegalForce; 東北大) | Are Prompt-based Models Clueless? |
| LONG | Ao Liu (東工大) An Wang (東工大) Naoaki Okazaki (東工大) | Semi-Supervised Formality Style Transfer with Consistency Training |
| LONG | Saku Sugawara (NII) Nikita Nangia (ニューヨーク大) Alex Warstadt (ニューヨーク大) Samuel Bowman (ニューヨーク大) | What Makes Reading Comprehension Questions Difficult? |
| LONG | Masahiro Kaneko (東工大) Sho Takase (東工大) Ayana Niwa (東工大) Naoaki Okazaki (東工大) | Interpretability for Language Learners Using Example-Based Grammatical Error Correction |
| LONG | Alham Fikri Aji (Amazon) Genta Indra Winata (Bloomberg) Fajri Koto (メルボルン大) Samuel Cahyawijaya (HKUST) Ade Romadhony (Telkom大; INACL) Rahmad Mahendra (インドネシア大; INACL) Kemal Kurniawan (メルボルン大; INACL) David Moeljadi (神田外語大) Radityo Eko Prasojo (Kata.ai) Timothy Baldwin (メルボルン大; MBZUAI) Jey Han Lau (メルボルン大) Sebastian Ruder (Google) | One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia |
| LONG | Ryokan Ri (東大) Yoshimasa Tsuruoka (東大) | Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models |
| LONG | Ryokan Ri (Studio Ousia; 東大) Ikuya Yamada (Studio Ousia; 理研) Yoshimasa Tsuruoka (東大) | mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models |
| LONG | Junjie Chen (東大) Xiangheng He (ICL) Yusuke Miyao (東大) | Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models |
| LONG | Jake Vasilakes (マンチェスター大) Chrysoula Zerva (Técnico) Makoto Miwa (豊田工大; 産総研) Sophia Ananiadou (マンチェスター大; 産総研) | Learning Disentangled Representations of Negation and Uncertainty |
| LONG | Hsiang-Sheng Tsai (台湾大) Heng-Jui Chang (台湾大) Wen-Chin Huang (名大) Zili Huang (Johns Hopkins) Kushal Lakhotia (Meta) Shu-wen Yang (台湾大) Shuyan Dong (MIT) Andy Liu (台湾大) Cheng-I Lai (MIT) Jiatong Shi (CMU) Xuankai Chang (CMU) Phil Hall (LXT) Hsuan-Jui Chen (台湾大) Shang-Wen Li (Meta) Shinji Watanabe (CMU) Abdelrahman Mohamed (Meta) Hung-yi Lee (台湾大) | SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities |
| LONG | Hisashi Kamezawa (東大) Noriki Nishida (理研) Nobuyuki Shimizu (Yahoo) Takashi Miyazaki (Yahoo) Hideki Nakayama (東大) | RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization |
| SHORT | Keiji Shinzato (Rakuten) Naoki Yoshinaga (東大) Yandi Xia (Rakuten) Wei-Te Chen (Rakuten) | Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction |
| SHORT | Koh Mitsuda (NTT) Ryuichiro Higashinaka (NTT) Tingxuan Li (筑波大) Sen Yoshida (NTT) | Investigating person-specific errors in chat-oriented dialogue systems |
| STUDENT | Tatsuya Ide (早大) Daisuke Kawahara (早大) | Building a Dialogue Corpus Annotated with Expressed and Experienced Emotions |
| STUDENT | Tomoya Kurosawa (東大) Hitomi Yanaka (東大) | Logical Inference for Counting on Semi-structured Tables |
| STUDENT | Tomoki Sugimoto (東大) Hitomi Yanaka (東大) | Compositional Semantics and Inference System for Temporal Order based on Japanese CCG |
| STUDENT | Zuchao Li (上海交通大) Masao Utiyama (NICT) Eiichiro Sumita (NICT) Hai Zhao (上海交通大) | Restricted or Not: A General Training Framework for Neural Machine Translation |
| STUDENT | Yongmin Kim (京大) Chenhui Chu (京大) Sadao Kurohashi (京大) | Flexible Visual Grounding |
| STUDENT | Shumpei Miyawaki (東北大) Taku Hasegawa (NTT) Kyosuke Nishida (NTT) Takuma Kato (東北大) Jun Suzuki (東北大) | Scene-Text Aware Image and Text Retrieval with Dual-Encoder |
| SHORT | Machel Reid (東大) Mikel Artetxe (Meta) | PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining |
| SHORT | Toshiki Kawamoto (東工大) Hidetaka Kamigaito (東工大) Kotaro Funakoshi (東工大) Manabu Okumura (東工大) | Generating Repetitions with Appropriate Repeated Words |
| LONG | Rujun Han (南カリフォルニア大) Hong Chen (東大) Yufei Tian (UCLA) Nanyun Peng (UCLA) | Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts |
| SHORT | Ryoma Sato (京大; 理研) | Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem |
| LONG | Masahiro Kaneko (東工大) Aizhan Imankulova (CogSmart) Danushka Bollegala (リバプール大; Amazon) Naoaki Okazaki (東工大) | Gender Bias in Masked Language Models for Multiple Languages |
| LONG | David Adelani (ザールラント大) Jesujoba Alabi (Inria) Angela Fan (Meta) Julia Kreutzer (Google) Xiaoyu Shen (Amazon) Machel Reid (東大) Dana Ruiter (ザールラント大) Dietrich Klakow (ザールラント大) Peter Nabende (マケレレ大) Ernie Chang (ザールラント大) Tajuddeen Gwadabe (中国科学院大) Freshia Sackey (JKUAT) Bonaventure F. P. Dossou (JUB) Chris Emezue (TUM) Colin Leong (デイトン大) Michael Beukman (ウィットウォーターズランド大) Shamsuddeen Muhammad (LIAAD-INESC TEC) Guyo Jarso () Oreen Yousuf (ウプサラ大) Andre Niyongabo Rubungo (UPC) Gilles Hacheme (Ai4Innov) Eric Peter Wairagala (マケレレ大) Muhammad Umair Nasir (Ominor AI) Benjamin Ajibade () Tunde Ajayi () Yvonne Gitau () Jade Abbott () Mohamed Ahmed (Microsoft) Millicent Ochieng (Microsoft) Anuoluwapo Aremu () Perez Ogayo (CMU) Jonathan Mukiibi (マケレレ大) Fatoumata Ouoba Kabore () Godson Kalipe () Derguene Mbaye (Baamtu) Allahsera Auguste Tapo (RIT) Victoire Memdjokam Koagne () Edwin Munkoh-Buabeng () Valencia Wagner (SPU) Idris Abdulmumin (ABU) Ayodele Awokoya (UI Ibadan) Happy Buzaaba () Blessing Sibanda (NUST) Andiswa Bukula (SADiLaR) Sam Manthalu (マラウィ大) | A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation |
| SHORT | Ikuya Yamada (Studio Ousia; 理研) Koki Washio (Megagon Labs) Hiroyuki Shindo (NAIST; 理研) Yuji Matsumoto (理研) | Global Entity Disambiguation with BERT |
| LONG | Sosuke Nishikawa (Studio Ousia; 東大) Ryokan Ri (Studio Ousia; 東大) Ikuya Yamada (Studio Ousia; 理研) Yoshimasa Tsuruoka (東大) Isao Echizen (東大; NII) | EASE: Entity-Aware Contrastive Learning of Sentence Embedding |
| LONG | Jingyi You (東工大) Dongyuan Li (東工大) Hidetaka Kamigaito (東工大) Kotaro Funakoshi (東工大) Manabu Okumura (東工大) | Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization |
| SHORT | Tomohiro Yamasaki (東芝) | Grapheme-to-Phoneme Conversion for Thai using Neural Regression Models |
| LONG | Terne Thorn Jakobsen (コペンハーゲン大) Anna Rogers (コペンハーゲン大; 理研) | What Factors Should Paper-Reviewer Assignments Rely On? Community Perspectives on Issues and Ideals in Conference Peer-Review |
| STUDENT | Ritvik Choudhary (早大) Daisuke Kawahara (早大) | Grounding in social media: An approach to building a chit-chat dialogue model |
| STUDENT | Mengsay Loem (東工大) Sho Takase (東工大) Masahiro Kaneko (東工大) Naoaki Okazaki (東工大) | ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization |
| STUDENT | Ryoma Sakaeda (早大) Daisuke Kawahara (早大) | Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation |
| STUDENT | Tomohito Kasahara (早大) Daisuke Kawahara (早大) Nguyen Tung (LINE) Shengzhe Li (LINE) Kenta Shinzato (LINE) Toshinori Sato (LINE) | Building a Personalized Dialogue System with Prompt-Tuning |
| STUDENT | Xiaomeng Pan (都立大) Hongfei Wang (都立大) Teruaki Oka (都立大) Mamoru Komachi (都立大) | Zuo Zhuan Ancient Chinese Dataset for Word Sense Disambiguation |
| STUDENT | Yi-Pei Chen (東大) Nobuyuki Shimizu (Yahoo) Takashi Miyazaki (Yahoo) Hideki Nakayama (東大) | How do people talk about images? A study on open-domain conversations with images. |
| STUDENT | Jun Takeuchi (東大) Noriki Nishida (理研) Hideki Nakayama (東大) | Neural Networks in a Product of Hyperbolic Spaces |
| STUDENT | Takumi Yoshikoshi (京大) Hayato Atarashi (京大) Takashi Kodama (京大) Sadao Kurohashi (京大) | Explicit Use of Topicality in Dialogue Response Generation |
| STUDENT | Prakhar Saxena (京大) Yin Jou Huang (京大) Sadao Kurohashi (京大) | Static and Dynamic Speaker Modeling based on Graph Neural Network for Emotion Recognition in Conversation |
| LONG | Yoshifumi Kawasaki (東大) Maëlys Salingre (目白大) Marzena Karpinska (UMASS) Hiroya Takamura (産総研) Ryo Nagata (甲南大) | Revisiting Statistical Laws of Semantic Shift in Romance Cognates |
| LONG | Atsumoto Ohashi (名大) Ryuichiro Higashinaka (名大) | Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning |
| LONG | Itsugun Cho (慶応大) Dongyang Wang (慶応大) Ryota Takahashi (慶応大) Hiroaki Saito (慶応大) | A Personalized Dialogue Generator with Implicit User Persona Detection |
| SHORT | Yosuke Kishinami (東北大) Reina Akama (東北大; 理研) Shiki Sato (東北大) Ryoko Tokuhisa (東北大) Jun Suzuki (東北大; 理研) Kentaro Inui (東北大; 理研) | Target-Guided Open-Domain Conversation Planning |
| LONG | Kazumasa Omura (京大) Sadao Kurohashi (京大) | Improving Commonsense Contingent Reasoning by Pseudo-data and Its Application to the Related Tasks |
| LONG | Riki Fujihara (東北大) Tatsuki Kuribayashi (東北大; Langsmith) Kaori Abe (東北大) Ryoko Tokuhisa (東北大) Kentaro Inui (東北大; 理研) | Topicalization in Language Models: A Case Study on Japanese |
| LONG | Masahiro Kaneko (東工大) Danushka Bollegala (リバプール大; Amazon) Naoaki Okazaki (東工大) | Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks |
| LONG | Yuxuan Wu (東大) Hideki Nakayama (東大) | Weakly Supervised Formula Learner for Solving Mathematical Problems |
| LONG | Takumi Shibata (電通大) Masaki Uto (電通大) | Analytic Automated Essay Scoring Based on Deep Neural Networks Integrating Multidimensional Item Response Theory |
| SHORT | Haoxiang Shi (早大) Rongsheng Zhang (NetEase) Jiaan Wang (蘇州大) Cen Wang (KDDI) Yinhe Zheng (Lingxin AI) Tetsuya Sakai (早大) | LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency |
| LONG | Ryoko Tokuhisa (豊田中央研究所) Keisuke Kawano (豊田中央研究所) Akihiro Nakamura (豊田中央研究所) Satoshi Koide (豊田中央研究所) | Enhancing Contextual Word Representations Using Embedding of Neighboring Entities in Knowledge Graphs |
| SHORT | Keisuke Shirai (京大) Atsushi Hashimoto (OMRON SINIC X) Taichi Nishimura (京大) Hirotaka Kameko (京大) Shuhei Kurita (理研; JST) Yoshitaka Ushiku (OMRON SINIC X) Shinsuke Mori (京大) | Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows |
| LONG | Koki Maeda (東工大) Masahiro Kaneko (東工大) Naoaki Okazaki (東工大) | IMPARA: Impact-Based Metric for GEC Using Parallel Data |
| LONG | Mana Ashida (Yahoo) Saku Sugawara (NII) | Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios |
| LONG | Satoshi Sekine (理研) Kouta Nakayama (理研) Masako Nomoto (理研) Maya Ando () Asuka Sumida (理研) Koji Matsuda (理研) | Resource of Wikipedias in 31 Languages Categorized into Fine-Grained Named Entities |
| LONG | Takashi Wada (メルボルン大; 理研) Timothy Baldwin (メルボルン大; MBZUAI) Yuji Matsumoto (理研) Jey Han Lau (メルボルン大) | Unsupervised Lexical Substitution with Decontextualised Embeddings |
| SHORT | Canasai Kruengkrai (NII) Junichi Yamagishi (NII) | Mitigating the Diminishing Effect of Elastic Weight Consolidation |
| SHORT | Tatsuya Hiraoka (東工大) | MaxMatch-Dropout: Subword Regularization for WordPiece |
| SHORT | Abhisek Chakrabarty (NICT) Raj Dabre (NICT) Chenchen Ding (NICT) Hideki Tanaka (NICT) Masao Utiyama (NICT) Eiichiro Sumita (NICT) | FeatureBART: Feature Based Sequence-to-Sequence Pre-Training for Low-Resource NMT |
| SHORT | Yuto Kuroda (愛媛大) Tomoyuki Kajiwara (愛媛大) Yuki Arase (阪大) Takashi Ninomiya (愛媛大) | Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation |
| LONG | Zhi Qu (NAIST) Taro Watanabe (NAIST) | Adapting to Non-Centered Languages for Zero-shot Multilingual Translation |
| LONG | Shuhei Kurita (理研; JST) Hiroki Ouchi (NAIST; 理研) Kentaro Inui (東北大; 理研) Satoshi Sekine (理研) | Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling |
| LONG | Dongyuan Li (東工大) Jingyi You (東工大) Kotaro Funakoshi (東工大) Manabu Okumura (東工大) | A-TIP: Attribute-aware Text Infilling via Pre-trained Language Model |
| SHORT | Xuan-Dung Doan (Viettel Group) Le-Minh Nguyen (産総研) Khac-Hoai Nam Bui (Viettel Group) | Multi Graph Neural Network for Extractive Long Document Summarization |
| LONG | Hiroki Teranishi (理研) Yuji Matsumoto (理研) | Coordination Generation via Synchronized Text-Infilling |
| LONG | Jingyi You (東工大) Dongyuan Li (東工大) Manabu Okumura (東工大) Kenji Suzuki (東工大) | JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation |
| LONG | Mana Ihori (NTT) Hiroshi Sato (NTT) Tomohiro Tanaka (NTT) Ryo Masumura (NTT) | Multi-Perspective Document Revision |
| LONG | Masato Takatsuka (早大) Tetsunori Kobayashi (早大) Yoshihiko Hayashi (早大) | Phrase-Level Localization of Inconsistency Errors in Summarization by Weak Supervision |
| LONG | Yidong Wang (東工大) Hao Wu (東工大) Ao Liu (東工大) Wenxin Hou (南京大) Zhen Wu (MSRA) Jindong Wang (西湖大) Takahiro Shinozaki (東工大) Manabu Okumura (東工大) Yue Zhang (西湖大) | Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction |
| LONG | Machel Reid (東大) Victor Zhong (ワシントン大) Suchin Gururangan (ワシントン大) Luke Zettlemoyer (ワシントン大) | M2D2: A Massively Multi-Domain Language Modeling Dataset |
| LONG | Seiichi Inoue (都立大) Mamoru Komachi (都立大) Toshinobu Ogiso (国語研) Hiroya Takamura (産総研) Daichi Mochihashi (統数研) | Infinite SCAN: An Infinite Model of Diachronic Semantic Change |
| SHORT | Zhen Wan (京大) Qianying Liu (京大) Zhuoyuan Mao (京大) Fei Cheng (京大) Sadao Kurohashi (京大) Jiwei Li (浙江大) | Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction |
| LONG | Hong Chen (東大; 産総研) Duc Vo (東大) Hiroya Takamura (東工大; 産総研) Yusuke Miyao (東大; 産総研) Hideki Nakayama (東大; 産総研) | StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning |
| LONG | David Adelani (ザールラント大; UCL) Graham Neubig (CMU) Sebastian Ruder (Google) Shruti Rijhwani (CMU) Michael Beukman (ウィットウォーターズランド大) Chester Palen-Michel (ブランダイス大) Constantine Lignos (ブランダイス大) Jesujoba Alabi (ザールラント大) Shamsuddeen Muhammad (LIAAD-INESC TEC) Peter Nabende (マケレレ大) Cheikh M. Bamba Dione (ベルゲン大) Andiswa Bukula (SADiLaR) Rooweither Mabuya (SADiLaR) Bonaventure F. P. Dossou (Mila Quebec AI Institute) Blessing Sibanda () Happy Buzaaba (理研) Jonathan Mukiibi (ブランダイス大) Godson Kalipe () Derguene Mbaye (Baamtu) Amelia Taylor (Malawi University of Business and Applied Sciences) Fatoumata Kabore (ウプサラ大) Chris Chinenye Emezue (TU Munich) Anuoluwapo Aremu () Perez Ogayo (CMU) Catherine Gitau () Edwin Munkoh-Buabeng (TU Clausthal) Victoire Memdjokam Koagne () Allahsera Auguste Tapo (ロチェスター工科大) Tebogo Macucwa (プレトリア大) Vukosi Marivate (プレトリア大) Mboning Tchiaze Elvis () Tajuddeen Gwadabe () Tosin Adewumi (ルレオ工科大) Orevaoghene Ahia (ワシントン大) Joyce Nakatumba-Nabende (マケレレ大) Neo Lerato Mokono (プレトリア大) Ignatius Ezeani (ランカスター大) Chiamaka Chukwuneke (ランカスター大) Mofetoluwa Oluwaseun Adeyemi (ウォータールー大) Gilles Quentin Hacheme (Ai4innov) Idris Abdulmumin (アフマド・ベロ大) Odunayo Ogundepo (ウォータールー大) Oreen Yousuf (ウプサラ大) Tatiana Moteu () Dietrich Klakow (ザールラント大) | MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition |
| LONG | Jungo Kasai (ワシントン大 #Allen Institute for AI) Keisuke Sakaguchi (東北大) Ronan Le Bras (Allen Institute for AI) Hao Peng (Allen Institute for AI) Ximing Lu (ワシントン大 #Allen Institute for AI) Dragomir Radev (イェール大) Yejin Choi (ワシントン大 #Allen Institute for AI) Noah A. Smith (ワシントン大 #Allen Institute for AI) | Twist Decoding: Diverse Generators Guide Each Other |
| LONG | Aman Kumar (IIT Madras) Himani Shrotriya (IIT Madras) Prachi Sahu (IIT Madras) Amogh Mishra (コロンビア大) Raj Dabre (NICT) Ratish Puduppully (エジンバラ大) Anoop Kunchukuttan (Microsoft; AI4Bharat) Mitesh M. Khapra (IIT Madras; AI4Bharat) Pratyush Kumar (Microsoft; AI4Bharat) | IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages |
| LONG | Ao Liu (東工大) Haoyu Dong (Microsoft) Naoaki Okazaki (東工大) Shi Han (Microsoft) Dongmei Zhang (Microsoft) | PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation |
| LONG | Yuki Arase (阪大) Satoru Uchida (九大) Tomoyuki Kajiwara (愛媛大) | CEFR-Based Sentence Difficulty Annotation and Assessment |
| LONG | Qin Dai (東北大) Benjamin Heinzerling (東北大; 理研) Kentaro Inui (東北大; 理研) | Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction |
| LONG | Ping Yang (IDEA) Junjie Wang (早大) Ruyi Gan (IDEA) Xinyu Zhu (清華大) Lin Zhang (IDEA) Ziwei Wu (IDEA) Xinyu Gao (IDEA) Jiaxing Zhang (IDEA) Tetsuya Sakai (早大) | Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective |
| LONG | Toru Nishino (富士フィルム) Yasuhide Miura (富士フィルム) Tomoki Taniguchi (富士フィルム) Tomoko Ohkuma (富士フィルム) Yuki Suzuki (阪大) Shoji Kido (阪大) Noriyuki Tomiyama (阪大) | Factual Accuracy is not Enough: Planning Consistent Description Order for Radiology Report Generation |
| LONG | Edison Marrese-Taylor (産総研) Yumi Hamazono (産総研; お茶大) Tatsuya Ishigaki (産総研) Goran Topić (産総研) Yusuke Miyao (産総研; 東大) Ichiro Kobayashi (産総研; お茶大) Hiroya Takamura (産総研) | Open-domain Video Commentary Generation |
| SHORT | Hongkuan Zhang (名大) Saku Sugawara (NII) Akiko Aizaaw (NII) Lei Zhou (名大) Ryohei Sasano (名大) Koichi Takeda (名大) | Cross-Modal Similarity-Based Curriculum Learning for Image Captioning |
| SHORT | Johannes Mario Meissner (東大) Saku Sugawara (NII) Akiko Aizawa (東大; NII) | Debiasing Masks: A New Framework for Shortcut Mitigation in NLU |
| LONG | Hong Chen (東大) Rujun Han (Amazon) Te-Lin Wu (UCLA) Hideki Nakayama (東大) Nanyun Peng (UCLA) | Character-centric Story Visualization via Visual Planning and Token Alignment |
| LONG | Yuting Zhao (都立大) Ioan Calapodescu (Naver) | Multimodal Robustness for Neural Machine Translation |
| LONG | Tatsuki Kuribayashi (東北大; Langsmith) Yohei Oseki (東大; 理研) Ana Brassard (東北大; 理研) Kentaro Inui (東北大; 理研) | Context Limitations Make Neural Language Models More Human-Like |
| LONG | Qiyu Wu (東大) Chongyang Tao (Microsoft) Tao Shen (Microsoft) Can Xu (Microsoft) Xiubo Geng (Microsoft) Daxin Jiang (Microsoft) | PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings |