Papers by Long Mai
Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models? (2022.aacl-main)
Copied to clipboard
| Challenge: | Input Marginalization (IM) is a method that takes the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. |
| Approach: | They propose to use a BERT-based method to replace a token with a feature to give more plausible counterfactuals. |
| Outcome: | The proposed method is effective, but the Deletion-BERT metric is biased towards IM, and the results are not convincing. |
I already said that! Degenerating redundant questions in open-domain dialogue systems. (2023.acl-srw)
Copied to clipboard
| Challenge: | Neural text generation models have been successful in short open-domain conversations, but their performance degrades significantly in the long term. |
| Approach: | They propose a method to generate training data without crowdsourcing . they adapt negative training, decoding, and classification methods to mitigate redundancy problem . |
| Outcome: | The proposed method reduces the rate of redundant questions from 27.2% to 8.7% while improving the quality of the original model. |
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks? (2021.findings-acl)
Copied to clipboard
| Challenge: | In July 2019, RoBERTa was the first to surpass a human baseline on GLUE . since then, 13 more methods have outperformed humans on the GLu leaderboard . |
| Approach: | They found that 75% to 90% of correct predictions of BERT-based classifiers remain constant after input words are randomly shuffled. |
| Outcome: | The proposed model outperforms humans on GLUE and SQuAD 2.0. |