Papers with paraphrase recognition
Assessing Out-of-Domain Language Model Performance from Few Examples (2023.eacl-main)
Copied to clipboard
| Challenge: | Pretrained language models exhibit impressive generalization capabilities, but behave unpredictably under certain domain shifts. |
| Approach: | They propose to incorporate attributions into a few-shot model predicting out-of-domain (OOD) performance task to find out if models agree with pathological heuristics that may indicate worse generalization capabilities. |
| Outcome: | The proposed model-based model-learning model can perform better on a few-shot example set, and incorporate feature attributions to improve it. |
Lexical and Semantic Features for Cross-lingual Text Reuse Classification: an Experiment in English and Latin Paraphrases (L18-1)
Copied to clipboard
| Challenge: | Analyzing historical languages is challenging because they lack primary material for certain time periods . under-resourced languages such as Ancient Greek and Latin lack advanced natural-language processing (NLP) techniques . |
| Approach: | They propose to use machine learning to detect and classify paraphrastic text reuse in historical texts. |
| Outcome: | The proposed method improves the accuracy of paraphrastic text reuse detection in historical languages. |
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation (N19-1)
Copied to clipboard
| Challenge: | Previous work focused on generating semantically similar paraphrases without considering diversity. |
| Approach: | They propose a method to obtain highly diverse paraphrases without compromising on paraphrasing quality by using monotone submodular function maximization. |
| Outcome: | The proposed method is effective on multiple tasks such as intent classification and paraphrase recognition. |