CALCS @ NAACL

9 papers28 directions

Papers by Year

2021 9

Top Research Directions

Research directions most represented by papers from this venue.

Bridging the Orthographic Gap in Multilingual Transfer 3
Overcoming Data Scarcity in Code-Switched Language Modeling 3
Progressive Domain Adaptation via Multi-Stage Fine-Tuning 2
Orthographic Inconsistency in Low Resource Language Processing 2
Metrics for Quantifying Code Switching Structure 1
Text Normalization as Sequence to Sequence Translation 1
Adversarial Robustness in Generative Language Tasks 1
Decoupling Encoders for Extensible Multimodal Learning 1
Cross-Lingual Gender Mapping in Machine Translation 1
Augmenting Word Embeddings with Explicit Linguistic Features 1
Subword Modeling for Intra Word Code Switching 1
Why Subword Tokenization Fails on Noisy Text 1
Adversarial Training for Robust Machine Learning 1
Multi-Granular Representation Fusion in Language Models 1
The Cross-Platform Generalization Gap in Social Media NLP 1

Top Authors

AuthorPapers
Manish Shrivastava2
Akshat Gupta1
Alan Black1
Andrea Madotto1
Anmol Goel1
Chihiro Taguchi1
Genta Indra Winata1
Khyathi Chandu1
Laks V. S. Lakshmanan1
Pascale Fung1
Prashant Kodali1
Sai Muralidhar Jayanthi1
Samson Tan1
Samuel Cahyawijaya1
Sargam Menghani1
Shafiq Joty1
Taro Watanabe1
Yusuke Sakai1
Zhaojiang Lin1
Zihan Liu1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Are Multilingual Models Effective in Code-Switching?2021
CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing2021
Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots2021
CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences2021
Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing2021
Normalization and Back-Transliteration for Code-Switched Data2021
Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data2021
Transliteration for Low-Resource Code-Switching Texts: Building an Automatic Cyrillic-to-Latin Converter for Tatar2021
Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data2021