CodeSwitch @ EMNLP 2016

6 papers

Top Research Directions

The 15 research directions with CodeSwitch @ EMNLP 2016 papers, ranked by paper count, next to 2014. Share is the fraction of the edition’s papers in the direction.

#Direction20162014Share 2016Share 20142014 rank
1Constrained Sequence Decoding for Neural Labeling2033.3%0.0%—
2End-to-End Representation Learning in Natural Language Processing2033.3%0.0%—
3Sub-Word Morphological Modeling with Character Convolutions2033.3%0.0%—
4Cross-Lingual Transfer via Linguistic Proximity1016.7%0.0%—
5Discriminating Between Closely Related Languages and Dialects1216.7%22.2%1
6Multi-Granular Representation Fusion in Language Models1016.7%0.0%—
7Multi-Scale Convolutional Filters for Text Representation1016.7%0.0%—
8Named Entity Recognition in Code-Switched Text1116.7%11.1%10
9Overcoming Vocabulary Sparsity in Morphologically Rich Languages1016.7%0.0%—
10Robust Speech Recognition for Intra-Sentential Code-Switching1116.7%11.1%16
11Stacked Generalization for Heterogeneous Ensemble Learning1016.7%0.0%—
12Subword Modeling for Intra Word Code Switching1016.7%0.0%—
13The Challenge of Rare Phenomena in Natural Language Processing1016.7%0.0%—
14Why Transformers Struggle with Code Mixed Social Media Text1116.7%11.1%19
15Why Universal Hyperparameters Fail Across Languages1016.7%0.0%—

Download all directions as CSV

Institutions

Institutions credited by CodeSwitch @ EMNLP 2016 papers: a paper credits every institution named in its affiliations, once. 6 institutions share 4 credited papers.

#InstitutionPapersShare20142014 rank
1University of Houston 375.0%111
2George Washington University 250.0%32
3Columbia University 125.0%31
4Google (United States) 125.0%0—
5Heinrich Heine University Düsseldorf 125.0%0—
6University of Washington 125.0%0—

Download all institutions as CSV

About this data

Papers. CodeSwitch @ EMNLP 2016 lists 6 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.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 2014 use shares, since the edition went from 9 to 6 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 4 of 6 papers (66.7%) 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, “CodeSwitch @ EMNLP 2016”, https://lacuna.tiptreesystems.com/venue/codeswitch-emnlp/2016.

Top Authors

AuthorPapers
Mona T. Diab3
Thamar Solorio2
Julia Hirschberg1
Mari Ostendorf1
Noah A. Smith1

Impactful Papers

Papers from CodeSwitch @ EMNLP 2016 that shaped research clusters.

Foundational

Influential

Papers

Title
Accurate Pinyin-English Codeswitched Language Identification
A Neural Model for Language Identification in Code-Switched Tweets
Multilingual Code-switching Identification via LSTM Recurrent Neural Networks
Overview for the Second Shared Task on Language Identification in Code-Switched Data
Part of Speech Tagging for Code Switched Data
The George Washington University System for the Code-Switching Workshop Shared Task 2016