2020 |
Aguilar, Gustavo; Kar, Sudipta; Solorio, Thamar LinCE: A Centralized Linguistic Code-Switching Evaluation Benchmark Conference Proceedings of the Twelfth International Conference on Language Resources and Evaluation, LREC, 2020. Abstract | Links | BibTeX | Tags: benchmark, Code-Switching @conference{aguilar20_lince, title = {LinCE: A Centralized Linguistic Code-Switching Evaluation Benchmark}, author = {Gustavo Aguilar and Sudipta Kar and Thamar Solorio}, editor = {LREC}, url = {https://www.aclweb.org/anthology/2020.lrec-1.223.pdf}, year = {2020}, date = {2020-05-11}, booktitle = {Proceedings of the Twelfth International Conference on Language Resources and Evaluation}, publisher = {LREC}, abstract = {Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly generalizable to different code-switched languages. In addition, it is unclear whether a model architecture is applicable for a different task while still being compatible with the code-switching setting. This is mainly because of the lack of a centralized benchmark and the sparse corpora that researchers employ based on their specific needs and interests. To facilitate research in this direction, we propose a centralized benchmark for textbf{Lin}guistic textbf{C}ode-switching textbf{E}valuation (textbf{LinCE}) that combines ten corpora covering four different code-switched language pairs (i.e., Spanish-English, Nepali-English, Hindi-English, and Modern Standard Arabic-Egyptian Arabic) and four tasks (i.e., language identification, named entity recognition, part-of-speech tagging, and sentiment analysis). As part of the benchmark centralization effort, we provide an online platform at texttt{ritual.uh.edu/lince}, where researchers can submit their results while comparing with others in real-time. In addition, we provide the scores of different popular models, including LSTM, ELMo, and multilingual BERT so that the NLP community can compare against state-of-the-art systems. LinCE is a continuous effort, and we will expand it with more low-resource languages and tasks.}, keywords = {benchmark, Code-Switching}, pubstate = {published}, tppubtype = {conference} } Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly generalizable to different code-switched languages. In addition, it is unclear whether a model architecture is applicable for a different task while still being compatible with the code-switching setting. This is mainly because of the lack of a centralized benchmark and the sparse corpora that researchers employ based on their specific needs and interests. To facilitate research in this direction, we propose a centralized benchmark for textbf{Lin}guistic textbf{C}ode-switching textbf{E}valuation (textbf{LinCE}) that combines ten corpora covering four different code-switched language pairs (i.e., Spanish-English, Nepali-English, Hindi-English, and Modern Standard Arabic-Egyptian Arabic) and four tasks (i.e., language identification, named entity recognition, part-of-speech tagging, and sentiment analysis). As part of the benchmark centralization effort, we provide an online platform at texttt{ritual.uh.edu/lince}, where researchers can submit their results while comparing with others in real-time. In addition, we provide the scores of different popular models, including LSTM, ELMo, and multilingual BERT so that the NLP community can compare against state-of-the-art systems. LinCE is a continuous effort, and we will expand it with more low-resource languages and tasks. |