Wat 2014

3 papers

Top Research Directions

The 12 research directions with Wat 2014 papers, ranked by paper count, next to 2009. Share is the fraction of the edition’s papers in the direction.

#Direction20142009Share 2014Share 20092009 rank
1Neural Language Model Rescoring2066.7%0.0%—
2Source-Side Syntactic Reordering2066.7%0.0%—
3Adapting to Domain Specific Semantic Shift1033.3%0.0%—
4Cross-Lingual Transfer for Low-Resource Dependency Parsing1033.3%0.0%—
5Log-Linear Feature Integration for Sequence Generation1033.3%0.0%—
6Modeling Long Distance Word Reordering in Translation1033.3%0.0%—
7Overcoming Parallel Data Scarcity in Specialized Translation1033.3%0.0%—
8Packed Forest Representations for Syntactic Ambiguity1033.3%0.0%—
9Parser Error Propagation in Machine Translation Preordering1033.3%0.0%—
10Syntactic Parser Degradation Under Domain Shift1033.3%0.0%—
11The Bag of Words Bottleneck in Text Encoders1033.3%0.0%—
12Vector Averaging and Mean Pooling for Text Representation1033.3%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Wat 2014 papers: a paper credits every institution named in its affiliations, once. 3 institutions share 3 credited papers.

#InstitutionPapersShare20092009 rank
1Nara Institute of Science and Technology 133.3%0—
2National Institute of Informatics 133.3%0—
3Waseda University 133.3%0—

Download all institutions as CSV

About this data

Papers. Wat 2014 lists 3 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.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. Comparisons with 2009 use shares, since the edition went from 2 to 3 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 2014”, https://lacuna.tiptreesystems.com/venue/wat/2014.

Top Authors

AuthorPapers
Akiko Aizawa1
Graham Neubig1
Sho Hoshino1
Yusuke Miyao1

Impactful Papers

Papers from Wat 2014 that shaped research clusters.

Influential

Papers

Title
Consistent Improvement in Translation Quality of Chinese-Japanese Technical Texts by Adding Additional Quasi-parallel Training Data
Forest-to-String SMT for Asian Language Translation: NAIST at WAT 2014
Japanese to English Machine Translation using Preordering and Compositional Distributed Semantics