Papers with multilingual transformer model
Improving Sentiment Analysis over non-English Tweets using Multilingual Transformers and Automatic Translation for Data-Augmentation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models for sentiment analysis over tweets require a substantial amount of text to adapt to a domain where the syntax is different. |
| Approach: | They propose to use a multilingual transformer model to train over tweets in five different languages to adapt the model to non-English languages. |
| Outcome: | The proposed model improves over small corpora of tweets in non-English languages. |
Automatic Partitioning of a Code-Switched Speech Corpus Using Mixed-Integer Programming (2024.lrec-main)
Copied to clipboard
| Challenge: | Currently, partitioning speech corpora is done by hand, but this is not feasible for the dataset under investigation. |
| Approach: | They propose to partition a 41.6-hour corpus of code-switched speech into training, development and testing partitions using mixed-integer linear programming. |
| Outcome: | The proposed method allows to partition a 41.6-hour corpus of code-switched speech into training, development and testing partitions while maintaining a fixed number of speakers and a specific amount of codeswitching speech in the development and test partitions. |