Paper reading (2022)

このセミナーについて (About this seminar)

担当者が見つけた面白い研究を紹介するセミナーです．以下の内容で構成されます． In this seminar, presenters share interesting studies that they found. The seminar consists of the following elements.

1. 論文紹介 (Paper presentation): 面白いと思う論文（基本的にLong Paper）を選んで，その内容を著者の代わりになったつもりで発表する． A presenter reads a paper (long paper is strongly preffered) that he or she finds interesting, and explains the content as if he or she was an author of the paper.
2. 著者プレゼンの上映と解説 (Watching talk videos): 担当者は面白いと思う研究の発表動画を選び，その論文の内容を把握する．担当者の補足説明を聞きながら，参加者みんなで発表動画を鑑賞する． Finding an interesting video presentation, a presenter reads and understands the content of the paper. Attendees watch the presentation video of the author of the paper. The presenter is expected to explain supplementary information about the research.

前者 (1) はプレゼンテーションの練習を兼ねています．後者 (2) は「よい」プレゼンテーションを鑑賞しながら，英語でのプレゼンテーションやディスカッションに慣れることを狙っています． The former (1) aims at practicing presentations. The latter (2) aims at improving listening and discussion skills in English as we enjoy good presentations.

発表者は一人目は (1) を，二人目は (1) か (2) のどちらかを担当します． The 1st presentator take (1). The 2nd one can select (1) or (2).

座長(chair)は、セミナーの司会進行をおこないます。 chair person host the seminar. 座長の仕事を参考にして，円滑に議論が進むように心がけてください． Please contribute to active discussion refering to Chair’s Job.

発表時間 (Presentation Time)

• Presentation: 15 ~ 20 minnutes
• QA: 5 ~ 10 minutes

日時 (Date and time)

• 3Q: 10:45~ (Mon)
• 4Q: 17:30~ (Mon)

参加者 (Attendee)

• 全員

:exclamation: 発表を登録するときは，著者名，発表年，タイトル，会議名／ジャーナル名，（巻，号，ページ番号など）を必ず記入してください． :exclamation: Please include author names, publication year, title, conference/journal name, (volume and page numbers) when you add an entry for presentation.

論文へのリンク集 (Links to the papers)

• ACL Anthlogy: TACL, ACL, NAACL, EMNLP, EACL, COLING, CoNLL, IJCNLP
• AAAI
• IJCAI
• NeurIPS
• ICML
• ICLR

著者プレゼンテーションのリンク集 (Links to authors’ presentations)

• ACL 2022
• EMNLP 2021
• ICLR 2022 (Oral, Spotlight)
• ICLR 2021
• ICML 2021
• NeurIPS 2019~

Tips

• リモートミーティングでビデオプレゼンテーションを行う場合は，画面およびオーディオを共有してください．
  • Zoomの場合：特別な操作は不要です
  • Microsoft Teamsの場合：システムオーディオの共有(Share the system audio)機能を利用してください．
• When you stream the video presentation via remote meeting, please share the both screen and system audio.
  • For Zoom: You don’t have to do nothing special. Just share your screen.
  • For Microsoft Teams: Please activate Share the system audio feature.

今後の予定 (Planned Seminars)

2022-12-05 (Mon) 10:45~

• presenter
  • hattori
  • muraoka
    • Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs (NeurIPS 2022)
    • slide
• chair
  • panatchakorn

2022-12-12 (Mon) 17:30~

• presenter
  • kaneko
  • hattori
    • QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization (NAACL 2022)
    • Slide (English)
  • cognetta
• chair
  • loem

2022-12-19 (Mon) 17:30~

• presenter
  • sangwhan
  • hirai
• chair
  • ishikawa

2023-01-16 (Mon) 17:30~

• presenter
  • panatchakorn
  • emil
• chair
  • endo

2023-01-23 (Mon) 17:30~

• presenter
  • endo
  • loem
• chair
  • nguyen

2023-01-30 (Mon) 17:30~

• presenter
  • yang
  • nguyen
• chair
  • hattori

2023-02-06 (Mon) 17:30~

• presenter
  • (erick)
• chair
  • TBD

waiting list (cancels)

• erick (10/17)

Past seminars

2022-04-18(Mon) 12:30~

• presenter
  • liu
    • Neural Machine Translation with Monolingual Translation Memory. Deng Cai, Yan Wang, Huayang Li, Wai Lam, and Lemao Liu. ACL 2021.
    • [Paper] [Slide]
  • yang Attention Bottlenecks for Multimodal Fusion Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, Chen Sun , NeurIPS 2021 paper Attention Bottlenecks for Multimodal Fusion.pdf (896.2 kB)
• chair
  • ishikawa

2022-04-25(Mon) 12:30~

• presenter
  • maeda
    • Data Augmentation of Incorporating Real Error Patterns and Linguistic Knowledge for Grammatical Error Correction, Xia Li and Junyi He, CoNLL 2021

    • [paper]

      [slide]

  • takase
• chair
  • maruyama

2022-05-09(Mon) 12:30~

• presenter
  • loem : Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting (EMNLP 2021)
    • Authors : Wangchunshu Zhou, Tao Ge, Canwen Xu, Ke Xu, Furu Wei
    • [Paper] [Slide]
  • kaneko
    • Reframing Human-AI Collaboration for Generating Free-Text Explanations (NAACL 2022)
    • Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark Riedl, Yejin Choi
    • Paper, Slide
• chair
  • taniguchi

2022-05-16(Mon) 12:30~

• presenter
  • Erick:
    • On Vision Features in Multimodal Machine Translation. ACL 2022.
    • Bei Li, Chuanhao Lv, Zefan Zhou, Tao Zhou, Tong Xiao, Anxiang Ma, Jingbo Zhu.
    • paper , presentation
  • kuo
    • Testing the Ability of Language Models to Interpret Figurative Language (NAACL 2022)
    • Emmy Liu, Chenxuan Cui, Kenneth Zheng, Graham Neubig
    • paper, slides
• chair
  • loem

2022-05-30(Mon) 12:30~

• presenter
  • ma
    • Multilingual Autoregressive Entity Linking
    • Nicola De Cao, Mikel Artetxe, Nicola Cancedda, Naman Goyal, Fabio Petroni, Mikhail Plekhanov, Kashyap Popat, Sebastian Riedel, Ledell Wu, Luke Zettlemoyer
    • TACL 2022
    • paper, slides
  • muraoka
    • VIDLANKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
    • Zineng Tang, Jaemin Cho, Hao Tan, and Mohit Bansal (at UNC Chapel Hill)
    • NeurIPS 2021
    • video, paper, supplemental slide
• chair
  • maeda

2022-06-06(Mon) 12:30~

• presenter
  • niwa
    • Nearest Neighbor Knowledge Distillation for Neural Machine Translation (NAACL 2022)
    • Zhixian Yang, Renliang Sun, Xiaojun Wan
    • paper, slide
  • yoshikawa
    • Learning Disentangled Representations of Negation and Uncertainty (ACL 2022)
    • Jake Vasilakes, Chrysoula Zerva, Makoto Miwa, Sophia Ananiadou
    • paper, slides
• chair
  • kuo

2022-06-13(Mon) 12:30~

• presenter
  • ishikawa
    • GLM: General Language Model Pretraining with Autoregressive Blank Infilling
      • Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang. ACL2022
      • paper, slide
  • iida Sean MacAvaney et.al. ABNIRML: Analyzing the Behavior of Neural IR Models(TACL(ACL)2022)
    • paper, paper(arXiv ver), video, author’s slides, supplement
• chair
  • hirai

2022-06-20(Mon) 12:30~

• presenter
  • vijay
    • Planning with Learned Entity Prompts for Abstractive Summarization. In ACL 2022
    • Paper, Video Presentation, Poster, Slides
  • mizuki
    • AUSTIN, Jacob, et al. Structured denoising diffusion models in discrete state-spaces. In: NeurIPS 2021. 2021.
    • paper, video presentation, supplementary material
    • introduction: Diffusion Models as a kind of VAE
• chair
  • nguyen

2022-06-27(Mon) 12:30~

• presenter
  • koyama
    • Probing for the Usage of Grammatical Number (Karim Lasri, Tiago Pimentel, Alessandro Lenci, Thierry Poibeau, Ryan Cotterell) (ACL 2022)
    • paper, slide
  • wang
    • Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity, Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, Pontus Stenetorp, ACL 2022 Outstanding Paper
    • paper, video, supplementary material
• chair
  • panatchakorn

2022-07-04(Mon) 12:30\~

• cancled

2022-07-11(Mon) 12:30~

• presenter
  • taniguchi
    • “Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging”, Findings of ACL 2022
    • Yutai Hou, Cheng Chen, Xianzhen Luo, Bohan Li, Wanxiang Che
    • Paper, Slide
  • maruyama
• chair
  • hirai

2022-07-18(Mon) 12:30\~

• （海の日）

2022-07-25(Mon) 12:30~

• presenter
  • cognetta
    • “Overcoming a Theoretical Limitation of Self-Attention” (ACL 2022)
      • David Chiang & Peter Cholak
      • slides
  • hattori
    • DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization (AAAI 2022)
    • Slide (English)
    • esaのページ (日本語)
• chair
  • endo

2022-08-01(Mon) 12:30~

• presenter
  • endo
  • loem
    • Compression of Generative Pre-trained Language Models via Quantization. Chaofan Tao, Lu Hou, Wei Zhang, Lifeng Shang, Xin Jiang, Qun Liu, Ping Luo, Ngai Wong. ACL 2022.
    • [paper][slide]
• chair
  • maruyama

2022-09-12(Mon) 12:30~

• presenter
  • panatchakorn
    • Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives (WMT 2021)
    • Authors: Jonas-Dario Troles, Ute Schmid
    • Paper, Slides
  • sangwhan
• chair
  • taniguchi

2022-09-19(Mon) 12:30\~

• （敬老の日）

2022-09-26(Mon) 12:30~

• presenter
  • sangwhan
    • KinyaBERT: a Morphology-aware Kinyarwanda Language Model. Antoine Nzeyimana and Andre Niyongabo Rubungo. ACL 2022. (Best linguistic insight paper)
    • Paper, Video, and Slides (WIP).
  • yang
    • OCR Post Correction for Endangered Language Texts Shruti Rijhwani, Antonios Anastasopoulos, Graham Neubig. EMNLP 2021
    • paper, video, slide
• chair
  • panatchakorn

2022-10-03 (Mon) 10:45~

• presenter
  • endo: Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning(ACL2022)
    • Authors: Moxin Li, Fuli Feng, Hanwang Zhang, Xiangnan He,Fengbin Zhu, Tat-Seng Chua
    • [Paper] [Slide]
  • vijay: NEUROLOGIC A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
    • Authors: Ximing Lu, Sean Welleck, Peter West, Liwei Jiang, Jungo Kasai, Daniel Khashabi, Ronan Le Bras, Lianhui Qin, Youngjae Yu, Rowan Zellers, Noah Smith, Yejin Choi
    • Paper
    • Presentation
• chair
  • ishikawa

2022-10-10 (Mon) 10:45\~

• （スポーツの日）

2022-10-17 (Mon) 10:45~

• presenter
  • wang: Towards a Unified View of Parameter-efficient Transfer Learning
    • paper
    • slides
  • erick
• chair
  • hirai

2022-10-24 (Mon) 10:45~

• presenter
  • hirai
    • Learning Transferable Visual Models From Natural Language Supervision
    • paper,slide
  • ma:
    • Zero-Shot Cross-lingual Semantic Parsing. ACL 2022.
    • Tom Sherborne and Mirella Lapata.
    • paper, slides
• chair
  • nguyen

2022-10-31 (Mon) 10:45~

• presenter
  • niwa: XPrompt: Exploring the Extreme of Prompt Tuning. EMNLP 2022.
    • Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan, Dawei Song
    • paper, slide
  • ishikawa: Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-Based Hate. NAACL 2022.
    • Hannah Kirk, Bertie Vidgen, Paul Rottger, Tristan Thrush, Scott Hale
    • paper, slide
• chair
  • endo

2022-11-07 (Mon) 10:45~

• self-introduction
  • koike
    • Slide
• presenter
  • nguyen
    • Causal Distillation for Language Models (NAACL 2022)
    • Paper, Slide
  • koyama
    • Evaluating Factuality in Text Simplification (ACL 2022)
    • Ashwin Devaraj, William Sheffield, Byron C. Wallace, Junyi Jessy Li
    • paper slide
• chair
  • hattori

2022-11-14 (Mon) 10:45~

• presenter

  • iida: Bin Wang, , C.-C. Jay Kuo, , Haizhou Li Just Rank: Rethinking Evaluation with Word and Sentence Similarities (ACL2022) - paper, slides

  • maeda : Bias Mitigation in Machine Translation Quality Estimation (ACL 2022, Behnke et al.)

    • [paper]

      [slides]

• chair
  • taniguchi

2022-11-21 (Mon) 10:45~

• presenter
  • mizuki
    • MENG, Kevin, et al. Locating and Editing Factual Associations in GPT. To Appear: NeurIPS 2022. 2022.
    • paper, paper explained video, presentation, official article (incl. demo), follow-up research, related work
  • taniguchi
    • Sun et al. “Do Long-Range Language Models Actually Use Long-Range Context?” (EMNLP 2021)
    • paper, video
• chair
  • maeda

2022-11-28 (Mon) 10:45~

• presenter
  • yoshikawa
    • Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View (ACL2022)
    • Boxi Cao, Hongyu Lin, Xianpei Han, Fangchao Liu, Le Sun
    • paper, slides
  • liu
    • Graph Pre-training for AMR Parsing and Generation (ACL2022)
    • Xuefeng Bai, Yulong Chen, Yue Zhang
    • paper,slides
• chair
  • hirai