HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text
This addresses the problem of understudied text generation and evaluation for code-mixed languages, particularly Hinglish, for the computational linguistics community, though it is incremental as it focuses on dataset creation.
The authors tackled the scarcity of high-quality resources for code-mixed languages by creating HinGE, a dataset for Hinglish (Hindi-English code-mixing), which includes human-generated and rule-based sentences, and they demonstrated that widely-used evaluation metrics are ineffective on this data.
Text generation is a highly active area of research in the computational linguistic community. The evaluation of the generated text is a challenging task and multiple theories and metrics have been proposed over the years. Unfortunately, text generation and evaluation are relatively understudied due to the scarcity of high-quality resources in code-mixed languages where the words and phrases from multiple languages are mixed in a single utterance of text and speech. To address this challenge, we present a corpus (HinGE) for a widely popular code-mixed language Hinglish (code-mixing of Hindi and English languages). HinGE has Hinglish sentences generated by humans as well as two rule-based algorithms corresponding to the parallel Hindi-English sentences. In addition, we demonstrate the inefficacy of widely-used evaluation metrics on the code-mixed data. The HinGE dataset will facilitate the progress of natural language generation research in code-mixed languages.