2021 Nov.12

News Release

The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)

The following papers were presented at the The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021) main conference and workshop held online from November 7th to 11th.

11月7日からオンラインで開催される EMNLP 2021 および併催ワークショップにて、下記7件の発表をおこないました。

Main Conference:

• Kazuaki Hanawa, Ryo Nagata and Kentaro Inui.
  “Exploring Methods for Generating Feedback Comments for Writing Learning”
• Shun Kiyono, Sosuke Kobayashi, Jun Suzuki and Kentaro Inui.
  “Shifted Absolute Position Embeddings for Transformers”
• Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi and Kentaro Inui.
  “Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution”
• Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi and Kentaro Inui.
  “Incorporating Residual and Normalization Layers into Analysis of Masked Language Models”
• Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian and Kentaro Inui.
  “Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension”
• Kosuke Yamada, Yuta Hitomi, Hideaki Tamori, Ryohei Sasano, Naoaki Okazaki, Kentaro Inui and Koichi Takeda.
  “Transformer-based Lexically Constrained Headline Generation”

Workshop:

• The 8th Workshop on Argument Mining 2021 (ArgMining 2021)
  • Keshav Singh, Farjana Sultana Mim, Naoya Inoue, Shoichi Naito and Kentaro Inui.
    “Exploring Methodologies for Collecting High-Quality Implicit Reasoning in Arguments”