1 |
Domain-Adaptive Pretraining Methods for Dialogue Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Instance-adaptive training with noise-robust losses against noisy labels ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.457/ Abstract: In order to alleviate the huge demand for annotated datasets for different tasks, many recent natural language processing datasets have adopted automated pipelines for fast-tracking usable data. However, model training with such datasets poses a challenge because popular optimization objectives are not robust to label noise induced in the annotation generation process. Several noise-robust losses have been proposed and evaluated on tasks in computer vision, but they generally use a single dataset-wise hyperparameter to control the strength of noise resistance. This work proposes novel instance-adaptive training frameworks to change dataset-wise hyperparameters of noise resistance in such losses to be instance-specific. Such instance-specific noise resistance hyperparameters are predicted by special instance-level label quality predictors, which are trained along with the main models. Experiments on noisy and corrupted NLP datasets ...
|
|
Keyword:
Computational Linguistics; Information Extraction; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://underline.io/lecture/37479-instance-adaptive-training-with-noise-robust-losses-against-noisy-labels https://dx.doi.org/10.48448/59p6-ak38
|
|
BASE
|
|
Hide details
|
|
3 |
Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
The Importance of Category Labels in Grammar Induction with Child-directed Utterances ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|