GLUECoS : An Evaluation Benchmark for Code-Switched NLP
This addresses the problem of evaluating NLP systems for code-switched languages, which is important for multilingual communities, but it is incremental as it builds on existing multilingual models and benchmarks.
The authors tackled the lack of evaluation benchmarks for code-switched NLP by introducing GLUECoS, a benchmark spanning tasks like sentiment analysis and question answering for English-Hindi and English-Spanish, and found that multilingual models fine-tuned on code-switched data performed best across most tasks.
Code-switching is the use of more than one language in the same conversation or utterance. Recently, multilingual contextual embedding models, trained on multiple monolingual corpora, have shown promising results on cross-lingual and multilingual tasks. We present an evaluation benchmark, GLUECoS, for code-switched languages, that spans several NLP tasks in English-Hindi and English-Spanish. Specifically, our evaluation benchmark includes Language Identification from text, POS tagging, Named Entity Recognition, Sentiment Analysis, Question Answering and a new task for code-switching, Natural Language Inference. We present results on all these tasks using cross-lingual word embedding models and multilingual models. In addition, we fine-tune multilingual models on artificially generated code-switched data. Although multilingual models perform significantly better than cross-lingual models, our results show that in most tasks, across both language pairs, multilingual models fine-tuned on code-switched data perform best, showing that multilingual models can be further optimized for code-switching tasks.