Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Jun Suzuki

An Investigation Between Schema Linking and Text-to-SQL Performance


Feb 03, 2021
Yasufumi Taniguchi, Hiroki Nakayama, Kubo Takahiro, Jun Suzuki


  Access Paper or Ask Questions

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned


Jan 01, 2021
Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, Hannaneh Hajishirzi, Kenton Lee, Jennimaria Palomaki, Colin Raffel, Adam Roberts, Tom Kwiatkowski, Patrick Lewis, Yuxiang Wu, Heinrich Küttler, Linqing Liu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Sohee Yang, Minjoon Seo, Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Edouard Grave, Ikuya Yamada, Sonse Shimaoka, Masatoshi Suzuki, Shumpei Miyawaki, Shun Sato, Ryo Takahashi, Jun Suzuki, Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz, Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih

* 26 pages 

  Access Paper or Ask Questions

Efficient Estimation of Influence of a Training Instance


Dec 08, 2020
Sosuke Kobayashi, Sho Yokoi, Jun Suzuki, Kentaro Inui

* This is an extended version of the paper presented at SustaiNLP 2020 

  Access Paper or Ask Questions

PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents


Nov 04, 2020
Ryo Fujii, Masato Mita, Kaori Abe, Kazuaki Hanawa, Makoto Morishita, Jun Suzuki, Kentaro Inui

* 15 pages, 4 figures, accepted at COLING 2020 

  Access Paper or Ask Questions

Langsmith: An Interactive Academic Text Revision System


Oct 09, 2020
Takumi Ito, Tatsuki Kuribayashi, Masatoshi Hidaka, Jun Suzuki, Kentaro Inui

* Accepted at EMNLP 2020 (system demonstrations) 

  Access Paper or Ask Questions

A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction


Oct 07, 2020
Masato Mita, Shun Kiyono, Masahiro Kaneko, Jun Suzuki, Kentaro Inui

* accepted by EMNLP 2020 (Findings) 

  Access Paper or Ask Questions

Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition


Jun 04, 2020
Takuma Kato, Kaori Abe, Hiroki Ouchi, Shumpei Miyawaki, Jun Suzuki, Kentaro Inui

* Accepted by ACL SRW 2020 

  Access Paper or Ask Questions

Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction


May 31, 2020
Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, Kentaro Inui

* Association for Computational Linguistics (ACL-2020) 
* Accepted as a short paper to the 58th Annual Conference of the Association for Computational Linguistics (ACL-2020) 

  Access Paper or Ask Questions

Single Model Ensemble using Pseudo-Tags and Distinct Vectors


May 02, 2020
Ryosuke Kuwabara, Jun Suzuki, Hideki Nakayama

* Accepted by ACL2020 

  Access Paper or Ask Questions

Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese


May 02, 2020
Tatsuki Kuribayashi, Takumi Ito, Jun Suzuki, Kentaro Inui

* Accepted by ACL2020 

  Access Paper or Ask Questions

Word Rotator's Distance: Decomposing Vectors Gives Better Representations


Apr 30, 2020
Sho Yokoi, Ryo Takahashi, Reina Akama, Jun Suzuki, Kentaro Inui


  Access Paper or Ask Questions

Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition


Apr 29, 2020
Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno, Kentaro Inui

* Accepted by ACL2020 

  Access Paper or Ask Questions

Evaluating Dialogue Generation Systems via Response Selection


Apr 29, 2020
Shiki Sato, Reina Akama, Hiroki Ouchi, Jun Suzuki, Kentaro Inui

* accepted by ACL 2020 

  Access Paper or Ask Questions

Utterance Pair Scoring for Noisy Dialogue Data Filtering


Apr 29, 2020
Reina Akama, Sho Yokoi, Jun Suzuki, Kentaro Inui

* 10 pages 

  Access Paper or Ask Questions

JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus


Nov 25, 2019
Makoto Morishita, Jun Suzuki, Masaaki Nagata

* http://www.kecl.ntt.co.jp/icl/lirg/jparacrawl/ 

  Access Paper or Ask Questions

Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance


Oct 21, 2019
Takumi Ito, Tatsuki Kuribayashi, Hayato Kobayashi, Ana Brassard, Masato Hagiwara, Jun Suzuki, Kentaro Inui

* Proceedings of the 12th International Conference on Natural Language Generation (INLG 2019) 

  Access Paper or Ask Questions

Select and Attend: Towards Controllable Content Selection in Text Generation


Sep 10, 2019
Xiaoyu Shen, Jun Suzuki, Kentaro Inui, Hui Su, Dietrich Klakow, Satoshi Sekine

* EMNLP 2019 

  Access Paper or Ask Questions

TEASPN: Framework and Protocol for Integrated Writing Assistance Environments


Sep 05, 2019
Masato Hagiwara, Takumi Ito, Tatsuki Kuribayashi, Jun Suzuki, Kentaro Inui

* Accepted at EMNLP 2019 (system demonstrations) 

  Access Paper or Ask Questions

An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction


Sep 02, 2019
Shun Kiyono, Jun Suzuki, Masato Mita, Tomoya Mizumoto, Kentaro Inui

* Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019) 

  Access Paper or Ask Questions

Character n-gram Embeddings to Improve RNN Language Models


Jun 13, 2019
Sho Takase, Jun Suzuki, Masaaki Nagata

* AAAI 2019 paper 

  Access Paper or Ask Questions

Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework


Oct 13, 2018
Shun Kiyono, Jun Suzuki, Kentaro Inui


  Access Paper or Ask Questions

Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions


Sep 04, 2018
Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui

* Accepted by EMNLP 2018 

  Access Paper or Ask Questions

Direct Output Connection for a High-Rank Language Model


Aug 31, 2018
Sho Takase, Jun Suzuki, Masaaki Nagata

* EMNLP 2018 paper 

  Access Paper or Ask Questions

Interpretable Adversarial Perturbation in Input Embedding Space for Text


May 08, 2018
Motoki Sato, Jun Suzuki, Hiroyuki Shindo, Yuji Matsumoto

* IJCAI-ECAI-2018 
* 8 pages, 4 figures 

  Access Paper or Ask Questions

Source-side Prediction for Neural Headline Generation


Dec 22, 2017
Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, Masaaki Nagata

* 19 pages 

  Access Paper or Ask Questions

Input-to-Output Gate to Improve RNN Language Models


Sep 28, 2017
Sho Takase, Jun Suzuki, Masaaki Nagata

* Accepted as a conference paper in IJCNLP 2017 

  Access Paper or Ask Questions

Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization


Feb 13, 2017
Jun Suzuki, Masaaki Nagata

* 7 pages, a draft version of EACL-2017 

  Access Paper or Ask Questions

Enumeration of Extractive Oracle Summaries


Jan 06, 2017
Tsutomu Hirao, Masaaki Nishino, Jun Suzuki, Masaaki Nagata

* 12 pages 

  Access Paper or Ask Questions