Papers by Zebin Ou
On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work uses linear models and neural networks for word ordering, yet pre-trained language models have not been studied in word ordering. |
| Approach: | They propose a constrained language generation task using unordered words as input. |
| Outcome: | The proposed model is able to perform better than existing models and proves to be reliable. |
GEMINI: Controlling The Sentence-Level Summary Style in Abstractive Text Summarization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that mimic human summarization techniques are difficult to imitate. |
| Approach: | They propose an adaptive model that integrates a rewriter and a generator to mimic the sentence rewriting and abstracting techniques. |
| Outcome: | The proposed model outperforms baselines on WikiHow and on other datasets. |