Page: 1... 46 47 48 49 50 51 52
Hits 981 – 1.000 of 1.029
982 |
Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
983 |
A Corpus-based Syntactic Analysis of Two-termed Unlike Coordination ...
|
|
|
|
BASE
|
|
Show details
|
|
984 |
A Fine-grained Annotated Corpus for Target-Based Opinion Analysis in Economy - Finance ...
|
|
|
|
BASE
|
|
Show details
|
|
985 |
Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations ...
|
|
|
|
BASE
|
|
Show details
|
|
986 |
On the Relation between Syntactic Divergence and Zero-Shot Performance ...
|
|
|
|
BASE
|
|
Show details
|
|
987 |
Discovering Representation Sprachbund For Multilingual Pre-Training ...
|
|
|
|
BASE
|
|
Show details
|
|
988 |
AESOP: Paraphrase Generation with Adaptive Syntactic Control ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.420/ Abstract: We propose to control paraphrase generation with carefully chosen target syntactic structures to generate more proper and higher-quality paraphrases. Our model, AESOP, leverages a pretrained language model and purposefully selected syntactical control via a retrieval-based selection module to generate fluent paraphrases. Experiments show that AESOP achieves state-of-the-art performances on semantic preservation and syntactic conformation on two benchmark datasets with ground-truth syntactic control from human-annotated exemplars. Moreover, with the retrieval-based target syntax selection module, AESOP generates paraphrases with even better qualities than the current best model using human-annotated target syntactic parses according to human evaluation. We further demonstrate the effectiveness of AESOP to improve classification models' robustness to syntactic perturbation by data augmentation on two GLUE tasks. ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://underline.io/lecture/37911-aesop-paraphrase-generation-with-adaptive-syntactic-control https://dx.doi.org/10.48448/4d09-em33
|
|
BASE
|
|
Hide details
|
|
989 |
Anatomy of OntoGUM---Adapting GUM to the OntoNotes Scheme to Evaluate Robustness of SOTA Coreference Algorithms ...
|
|
|
|
BASE
|
|
Show details
|
|
991 |
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results ...
|
|
|
|
BASE
|
|
Show details
|
|
992 |
Discovering Representation Sprachbund For Multilingual Pre-Training ...
|
|
|
|
BASE
|
|
Show details
|
|
994 |
How much pretraining data do language models need to learn syntax? ...
|
|
|
|
BASE
|
|
Show details
|
|
995 |
Probing Pre-trained Language Models for Semantic Attributes and their Values ...
|
|
|
|
BASE
|
|
Show details
|
|
996 |
Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
997 |
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
998 |
Improving Text Generation via Neural Discourse Planning ...
|
|
|
|
BASE
|
|
Show details
|
|
999 |
The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
1000 |
Test Harder than You Train: Probing with Extrapolation Splits ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1... 46 47 48 49 50 51 52
|
|