WAT @ EMNLP 2019

10 papers

Top Research Directions

The 26 research directions with WAT @ EMNLP 2019 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Back-Translation for Synthetic Data Augmentation330.0%
2Overcoming Structural Divergence in Cross-Lingual Transfer220.0%
3The Quality Bottleneck of Synthetic Data Augmentation220.0%
4Cross Architecture Generalization of Attention Mechanisms110.0%
5Deceptive Fluency and Hallucination in Machine Translation110.0%
6Filtering Noisy Parallel Corpora for Machine Translation110.0%
7Hybrid Machine Translation Architectures110.0%
8Injecting Sentiment Polarity into Word Embeddings110.0%
9Joint Multilingual Training for Cross-Lingual Transfer110.0%
10Machine Translation Failures in Specialized Technical Domains110.0%
11Machine Translation Without Massive Parallel Corpora110.0%
12Morphological Misalignment in Subword Tokenization110.0%
13Multi-Prototype Word Representations110.0%
14Overcoming Frequency Bias in Machine Translation110.0%
15Overcoming Parallel Data Scarcity in Specialized Translation110.0%
16Resolving the Semantic Conflation Bottleneck in Word Embeddings110.0%
17Right to Left Reranking for Sequence Generation110.0%
18Scaling Subword Granularity for Data Efficiency110.0%
19Shared Subword Vocabularies for Cross-Lingual Transfer110.0%
20Structure Preserving Machine Translation110.0%
21Target Language Signaling for Multilingual Sequence Generation110.0%
22The Encoder-Decoder Architecture for Sequence-to-Sequence Mapping110.0%
23The Limits of Automated Metrics for Machine Translation110.0%
24The Mechanics of Learning Rate Warmup110.0%
25The Mechanics of Subword Tokenization110.0%

Download all directions as CSV

Institutions

Institutions credited by WAT @ EMNLP 2019 papers: a paper credits every institution named in its affiliations, once. 13 institutions share 8 credited papers.

#InstitutionPapersShare
1Charles University 112.5%
2Harbin Institute of Technology 112.5%
3Idiap Research Institute 112.5%
4Institute for Infocomm Research 112.5%
5International Institute of Information Technology, Hyderabad 112.5%
6Meta (United States) 112.5%
7Microsoft (United States) 112.5%
8National Institute of Information and Communications Technology 112.5%
9National University of Singapore 112.5%
10NTT (Japan) 112.5%
11NTT Basic Research Laboratories 112.5%
12Tohoku University 112.5%
13Tokyo Metropolitan University 112.5%

Download all institutions as CSV

About this data

Papers. WAT @ EMNLP 2019 lists 10 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. 8 of 10 papers (80.0%) 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 2026-11-20 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “WAT @ EMNLP 2019”, https://lacuna.tiptreesystems.com/venue/wat-emnlp/2019.

Top Authors

AuthorPapers
Ahmed El-Kishky1
Aizhan Imankulova1
Akiko I. Eriguchi1
Haipeng Sun1
Jun Suzuki1
Kehai Chen1
Makoto Morishita1
Mamoru Komachi1
Masaaki Nagata1
Masahiro Kaneko1
Min-Yen Kan1
Ondřej Bojar1
Petr Motlicek1
Rui Wang1
Shantipriya Parida1
Vinay P. Namboodiri1
Vishrav Chaudhary1

Impactful Papers

Papers from WAT @ EMNLP 2019 that shaped research clusters.

Influential

Papers

Title
Combining Translation Memory with Neural Machine Translation.
CVIT's submissions to WAT-2019
English-Myanmar Supervised and Unsupervised NMT: NICT's Machine Translation Systems at WAT-2019
Facebook AI's WAT19 Myanmar-English Translation Task Submission
Idiap NMT System for WAT 2019 Multimodal Translation Task
Japanese-Russian TMU Neural Machine Translation System using Multilingual Model for WAT 2019
NTT Neural Machine Translation Systems at WAT 2019
Our Neural Machine Translation Systems for WAT 2019
Sentiment Aware Neural Machine Translation
SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task