Paper reading (2021)
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.
- 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.
- 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: 12:30~ (Fri)
- 4Q: 12:30~ (Fri)
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)
著者プレゼンテーションのリンク集 (Links to authors’ presentations)
- ICLR 2021
- NeurIPS 2020
- EMNLP 2020
- ACL 2020
- ICLR 2020
- NeurIPS 2019
- ACL 2019
- NAACL 2019
- ICML 2019
- ICLR 2019
- NIPS 2018
- EMNLP 2018
- ACL 2018
- NAACL 2018
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)
2021-02-04(Fri) 12:30~
- presenter
- Kaneko
- Yoshikawa
- chair
- Ueki
過去の記録 (Past Seminars)
2021-04-14(Wed) 12:30~
- presenter
- Koyama
- Zhaohong Wan, et al. Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation (COLING 2020)
- paper, slide
- Mizuki
- Koyama
2021-04-21(Wed) 12:30~
- presenter
- Muraoka
Candidate 1: Hao Tan, and Mohit Bansal. Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision. (EMNLP2020)paper-> I will introduce it somewhere else in the near future :)
- Candidate 2: Irwan Bello. LambdaNetworks: Modeling long-range Interactions without Attention. (ICLR2021, spotlight)
- paper, slides (4.4 MB)
- Yang
- Muraoka
2021-04-28(Wed) 12:30~
- presenter
- Taniguchi
- Non-Autoregressive Text Generation with Pre-trained Language Models Yixuan Su, Deng Cai, Yan Wang, David Vandyke, Simon Baker, Piji Li, Nigel Collier EACL2021
- paper, slide
- Niwa
- Taniguchi
2021-05-05(Wed)
- national holiday
2021-05-12(Wed) 12:30~
- presenter
- Maruyama
- Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs. In NeurIPS 2020. Slide Paper
- Liu
- Maruyama
2021-05-19(Wed) 12:30~
- presenter
2021-05-26(Wed) 12:30~
- presenter
- Hiraoka
- Error Analysis and the Role of Morphology
- Marcel Bollmann and Anders Søgaard. EACL2021, Best Paper Award.
- slide
- slide with annimation(PRPの参考用)
- Ueki
- DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION
- Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen (ICLR2021)
- slide
### 2021-06-02(Wed) 12:30~
- Hiraoka
- Presenter:
- Erick:
- Nikolay Malkin et all. GPT Perdetry Test: Generating new meanings for new words. In: NAACL 2021.
- Paper, Slide
- Erick:
- Sangwhan
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby
- In ICLR2021.
- Paper Slides
2021-06-09(Wed) 12:30~
- Iida
- Yixing Fan, Jiafeng Guo, Xinyu Ma, Ruqing Zhang, Yanyan Lan, and Xueqi Cheng A Linguistic Study on Relevance Modeling in Information Retrieval WWW2021
- slides, paper
- Koyama
- Dhruv Kumar, Lili Mou, Lukasz Golab, Olga Vechtomova. Iterative Edit-Based Unsupervised Sentence Simplification. ACL 2020.
- paper, slide
2021-06-16(Wed) 18:05~
- presenter
- Mizuki
- SAUNSHI, Nikunj; MALLADI, Sadhika; ARORA, Sanjeev. A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks. In: ICLR 2021. 2021.
- paper, slide, video (for the interested readers)
- Muraoka
- Mizuki
- chair
- Wiem
2021-06-23(Wed) 18:05~
- presenter
- Kaneko
- Cunxiao Du, Zhaopeng Tu, Jing Jiang. Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation (ICML 2021)
- paper, slides
- Yoshikawa
- Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards?
- Pedro Rodriguez, Joe Barrow, Alexander Hoyle, John P. Lalor, Robin Jia and Jordan Boyd-Graber (ACL-IJCNLP2021)
- paper, slides
- Kaneko
- chair
- Koyama
### 2021-06-30(Wed) 18:05~
- presenter
- Takase
- Are Pre-trained Convolutions Better than Pre-trained Transformers?
- Yi Tay, Mostafa Dehghani, Jai Gupta, Dara Bahri, Vamsi Aribandi, Zhen Qin, Donald Metzler. ACL 2021.
- paper, slide
- Are Pre-trained Convolutions Better than Pre-trained Transformers?
- Vijay
- Hooks in the Headline: Learning to Generate Headlines with Controlled Styles
- Di Jin, Zhijing Jin, Joey Tianyi Zhou, Lisa Orii, Peter Szolovits. ACL 2020
- paper, slide
- Hooks in the Headline: Learning to Generate Headlines with Controlled Styles
- Takase
- chair
- Ueki
2021-07-07(Wed) 18:05~
- presenter
- Liu
- CoDA: Contrast-enhanced and Diverse-promoting Data Augmentation for Natural Language Understanding. (ICLR 2021)
- Yanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Jiawei Han, Weizhu Chen
- Paper. Slide
- CoDA: Contrast-enhanced and Diverse-promoting Data Augmentation for Natural Language Understanding. (ICLR 2021)
- Yang
- Liu
- chair
- Kuo
2021-07-14(Wed) 18:05~
- presenter
- Kuo
- Automatic Detection of Generated Text isEasiest when Humans are Fooled (ACL 2020)
- Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch, Douglas Eck
- Paper, Slides(revised)
- Automatic Detection of Generated Text isEasiest when Humans are Fooled (ACL 2020)
- Taniguchi
- Kuo
- chair
- Maruyama
2021-07-21(Wed) 18:05~
- presenter
- Niwa
- Glancing Transformer for Non-Autoregressive Neural Machine Translation (ACL2021)
- Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei Li
- paper, paper (one column ver.), slide
- Glancing Transformer for Non-Autoregressive Neural Machine Translation (ACL2021)
- Maruyama
- Niwa
- chair
- Taniguchi
2021-07-28(Wed) 18:05~
- presenter
Maeda- Ueki
- Meta Back-Translation (ICLR2021)
- Hieu Pham,, Xinyi Wang, Yiming Yang, Graham Neubig
- paper, slide
- chair
- Toyama
2021-08-04(Wed) 18:05~
- presenter
- Ishikawa
- All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
- Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, Noah A. Smith. ACL2021
- paper, slide
- All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
- Hiraoka
Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model AdaptationMinki Kang, Moonsu Han, Sung Ju Hwang. EMNLP 2020.paper, presentation- Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?
- Thang M. Pham, Trung Bui, Long Mai, Anh Nguyen. ACL2021-Findings.
- slide
- Ishikawa
- chair
- Maeda
2021-09-01(Wed) 18:05~
- presenter
- Loem
- Weight Distillation: Transferring the Knowledge in Neural Network Parameters
- Ye Lin, Yanyang Li, ZiyangWang, Bei Li, Quan Du, Tong Xiao, Jingbo Zhu. ACL-IJCNLP2021.
- slide
- Iida
- Autoregressive Entity Retrieval Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni
- video and paper
- supplement slides
- Loem
- chair
- Ishikawa
2021-09-08(Wed) 18:05~
- presenter
- Ma
- Examining the Inductive Bias of Neural Language Models with Artificial Languages (ACL2021)
- Jennifer C. White, Ryan Cotterell
- paper
- slides
- Sangwhan
- HTLM: Hyper-Text Pre-Training and Prompting of Language Models
- Armen Aghajanyan, Dmytro Okhonko, Mike Lewis, Mandar Joshi, Hu Xu, Gargi Ghosh, Luke Zettlemoyer
- paper
- slides
- Ma
- chair
- Loem
2021-09-15(Wed) 18:05~
- Loem
- presenter
- Erick
- UnNatural Language Inference.
- Koustuv Sinha, Prasanna Parthasarathi, Joelle Pineau and Adina Williams. In ACL-IJCNLP (2021)
- paper, slides
- Takase
- Efficient Content-Based Sparse Attention with Routing Transformers
- Aurko Roy, Mohammad Saffar, Ashish Vaswani, David Grangier. TACL 2021.
- paper, slide
- Efficient Content-Based Sparse Attention with Routing Transformers
- Erick
- chair
- Ueki
2021-09-22(Wed) 18:05~
- presenter
- Maeda
- Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger
- Conference : ACL2021
- Author : Fanchao Qi, Mukai Li, Yangyi Chen, Zhengyan Zhang, Zhiyuan Liu, Yasheng Wang, Maosong Sun
-
[slides] [paper]
Wiem
- Maeda
- chair
- Koyama
2021-09-29(Wed) 18:05~
- presenter
- Toyama
- Armen Aghajanyan et al., Intrinsic Dimensionality Explains the effectiveness of Language Model Fine-Tuning (ACL2021)
- paper, slide
Mizuki
- Toyama
- chair
- Maruyama
2021-10-08(Fri) 12:30~
- presenter
- Muraoka
- Wei-Ning Hsu, David Harwath, Tyler Miller, Christopher Song, James Glass. “Text-Free Image-to-Speech Synthesis Using Learned Segmental Units.” ACL-IJCNLP. 2021.
- paper, slides (7.7 MB) , demo, poster, video in NeurIPS2020-ws
- Mizuki
- MEISTER, Clara; FORSTER, Martina; COTTERELL, Ryan. Determinantal Beam Search. In: ACL2021. 2021.
- paper, video presentation (requires conference login), presentation by Prof. Miyao at SNLP2021
- Muraoka
- chair
- Taniguchi
2021-10-15(Fri) 12:30~
- presenter
- Taniguchi
- Daniel Grießhaber, Johannes Maucher
- Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning
- COLING 2020
- paper, slide
YangLiu (video presentation)- Xinnuo Xu, Guoyin Wang, Young-Bum Kim, Sungjin Lee. AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation. ACL-IJCNLP 2021.
- Paper; Video (requires conference login) ; Slide
- Taniguchi
- chair
- Kuo
2021-10-29(Fri) 12:30~
- presenter
LiuYang- Kuo
- How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction (ACL-IJCNLP 2021)
- Zikun Hu, Yixin Cao, Lifu Huang, Tat-Seng Chua
- paper, slides, video (login required)
- How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction (ACL-IJCNLP 2021)
- chair
- Maeda
2021-11-05(Fri) 12:30~
- presenter
MaruyamaYang- Multimodal Transformer for Multimodal Machine Translation Shaowei Yao, Xiaojun Wan ACL 2020 paper multimodal_transformer_multimodal_machine_translation.pdf (646.4 kB)
- Niwa
- Probing Pretrained Language Models for Lexical Semantics (EMNLP 2020)
- Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, Goran Glavaš, Anna Korhonen
- paper, video, supplementary information
- Probing Pretrained Language Models for Lexical Semantics (EMNLP 2020)
- chair
- Loem
2021-11-12(Fri) 12:30~
- presenter
- Hiraoka
- Fast WordPiece Tokenization
- Xinying Song, Alex Salcianu, Yang Song, Dave Dopson, Denny Zhou
- EMNLP2021 main. paper, slides.
- Sangwhan
- UNKs Everywhere: Adapting Multilingual Language Models to New Scripts
- Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych and Sebastian Ruder
- EMNLP2021 main. Paper, Official Slides, Slides
- Hiraoka
- chair
- Ishikawa
2021-11-19(Fri) 12:30~
- Ishikawa
- presenter
- Erick: Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining. EMNLP 2021
- Lei Yu, Yang Xu
- paper
- Authors presentation
- Supporting slides
- Koyama: Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation
- Tong Zhang, Long Zhang, Wei Ye, Bo Li, Jinan Sun, Xiaoyu Zhu, Wen Zhao, Shikun Zhang
- ACL 2021
- paper
- slide
- Erick: Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining. EMNLP 2021
- chair
- Ueki
2021-11-26(Fri) 12:30~
- presenter
- Iida
- Ueki
- Prefix-Tuning: Optimizing Continuous Prompts for Generation(ACL-IJCNLP2021)
- Xiang Lisa Li, Percy Liang
- paper,author-presentation (youtube)
- slide
- Prefix-Tuning: Optimizing Continuous Prompts for Generation(ACL-IJCNLP2021)
- chair
- Maeda
2021-12-03(Fri) 12:30~
- presenter
- chair
- Koyama
2021-12-10(Fri) 12:30~
- presenter
- Yoshikawa
- (tentative) SituatedQA: Incorporating Extra-Linguistic Contexts into QA (EMNLP2021 main; Outstanding Paper Award)
- Michael Zhang and Eunsol Choi
-
paper slides
- Ma
- Yoshikawa
- chair
- Taniguchi
2021-12-17(Fri) 12:30~
- presenter
- Ishikawa
- Evidence-based Factual Error Correction
- James Thorne, Andreas Vlachos. ACL2021
- paper, slide
- Evidence-based Factual Error Correction
- Ishikawa
- chair
- Maruyama
2021-12-24(Fri) 12:30~
- presenter
-
Maeda [slides] [paper] - Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding (ACL2021)
- Author : Xin Sun et al.
-
- chair
- Kuo
2021-01-21(Fri) 12:30~
- presenter
* Vijay
* Aspect-Controllable Opinion Summarization - ACL Anthology
* Underline | Aspect-Controllable Opinion Summarization
- Maruyama
- chair
- Loem