2018 Oct.31

News Release

EMNLP 2018 発表

The following papers are presented at the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)and co-located workshops.

10月31日からベルギーで開催されたThe 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) および併催WSで下記の発表を行いました。

Main Conference

• Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, and Kentaro Inui.
  “Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions”.
• Hiroki Ouchi, Hiroyuki Shindo, and Yuji Matsumoto.
  “A Span Selection Model for Semantic Role Labeling”.
• Saku Sugawara, Kentaro Inui, Satoshi Sekine, and Akiko Aizawa.
  “What Makes Reading Comprehension Questions Easier?”.
• Sho Takase, Jun Suzuki, and Masaaki Nagata.
  “Direct Output Connection for a High-Rank Language Model”.

Workshops

The 4th Workshop on Noisy User-generated Text (W-NUT)

• Ryo Nagata, Tomoya Mizumoto, Yuta Kikuchi, Yoshifumi Kawasaki and Kotaro Funakoshi.
  “A POS Tagging Model Designed for Learner English”.

The 5th Workshop on Argument Mining (Argmining 2018)

• Paul Reisert, Naoya Inoue, Tatsuki Kuribayashi and Kentaro Inui.
  “Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates”.

The Ninth International Workshop on Health Text Mining and Information Analysis (LOUHI 2018)

• Diana Galvan, Naoaki Okazaki, Koji Matsuda and Kentaro Inui.
  “Investigating the Challenges of Temporal Relation Extraction from Clinical Text”.

Analyzing and interpreting neural networks for NLP (BlackboxNLP)

• Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui and Masaaki Nagata.
  “Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder models”.