Wat@ijcnlp 2017

3 papers

Top Research Directions

The 9 research directions with Wat@ijcnlp 2017 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Algorithmic Length Bias in Sequence Generation266.7%
2Back-Translation for Synthetic Data Augmentation133.3%
3Evaluating Language Systems Through Downstream Task Utility133.3%
4Filtering Noisy Parallel Corpora for Machine Translation133.3%
5Hybrid Metrics for Machine Translation Evaluation133.3%
6Shared Subword Vocabularies for Cross-Lingual Transfer133.3%
7The Encoder-Decoder Architecture for Sequence-to-Sequence Mapping133.3%
8Tracking Input Coverage in Attention Mechanisms133.3%
9Unified Evaluation Frameworks for Reproducible Machine Learning133.3%

Download all directions as CSV

Institutions

Institutions credited by Wat@ijcnlp 2017 papers: a paper credits every institution named in its affiliations, once. 8 institutions share 3 credited papers.

#InstitutionPapersShare
1Nara Institute of Science and Technology 266.7%
2National Institute of Information and Communications Technology 266.7%
3Carnegie Mellon University 133.3%
4Google (United States) 133.3%
5Japan Science and Technology Agency 133.3%
6Kyoto University 133.3%
7NTT (Japan) 133.3%
8NTT Basic Research Laboratories 133.3%

Download all institutions as CSV

About this data

Papers. Wat@ijcnlp 2017 lists 3 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 3 of 3 papers (100.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Wat@ijcnlp 2017”, https://lacuna.tiptreesystems.com/venue/wat-ijcnlp/2017.

Top Authors

AuthorPapers
Yusuke Oda2
Graham Neubig1
Hideya Mino1
Jun Suzuki1
Katsuhito Sudoh1
Makoto Morishita1
Masaaki Nagata1

Impactful Papers

Papers from Wat@ijcnlp 2017 that shaped research clusters.

Influential

Papers

Title
A Simple and Strong Baseline: NAIST-NICT Neural Machine Translation System for WAT2017 English-Japanese Translation Task
NTT Neural Machine Translation Systems at WAT 2017
Overview of the 4th Workshop on Asian Translation