Papers with Tamil-English
Improving Pretraining Techniques for Code-Switched NLP (2023.acl-long)
Copied to clipboard
| Challenge: | Multilingual pretraining models for code-switched inputs are a key component of NLP applications. |
| Approach: | They propose to use masked language modeling techniques to mask code-switched text that are cognizant of language boundaries prior to masking. |
| Outcome: | The proposed techniques improve performance on two downstream tasks, Question Answering (QA) and Sentiment Analysis (SA), compared to standard pretraining techniques. |
A Dataset for Building Code-Mixed Goal Oriented Conversation Systems (C18-1)
Copied to clipboard
| Challenge: | Existing data on goal-oriented conversation systems focus on monolingual conversations and there is hardly any work on multilingual and/or code-mixed conversations. |
| Approach: | They build a goal-oriented dialog dataset containing code-mixed conversations using monolingual text from a restaurant reservation dataset. |
| Outcome: | The proposed model is based on a restaurant reservation dataset and will be made publicly available for research purposes. |