Page: 1 2 3 4 5 6 7 8... 59
61 |
Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
62 |
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
63 |
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
64 |
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ...
|
|
|
|
BASE
|
|
Show details
|
|
66 |
SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images ...
|
|
|
|
BASE
|
|
Show details
|
|
67 |
A DQN-based Approach to Finding Precise Evidences for Fact Verification ...
|
|
|
|
BASE
|
|
Show details
|
|
68 |
Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event ...
|
|
|
|
BASE
|
|
Show details
|
|
69 |
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
70 |
Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
71 |
2A: Sentiment Analysis, Stylistic Analysis, and Argument Mining #1 ...
|
|
|
|
BASE
|
|
Show details
|
|
72 |
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.419 Abstract: In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness. In this work, for the first time, we can improve the interpretability of explanations by allowing arbitrary text sequences as the explanation unit. On top of this, we implement a hessian-free method with a model faithfulness guarantee. Finally, to compare our method with the others, we propose a semantic-based evaluation metric that can better align with humans' judgment of explanations than the widely adopted diagnostic or re-training measures. The empirical results on multiple real data sets demonstrate the proposed method's superior performance to popular explanation techniques such as Influence Function or TracIn on semantic evaluation. ...
|
|
Keyword:
Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://underline.io/lecture/25843-on-sample-based-explanation-methods-for-nlp-faithfulness,-efficiency-and-semantic-evaluation https://dx.doi.org/10.48448/zffx-yb03
|
|
BASE
|
|
Hide details
|
|
73 |
How effective is BERT without word ordering? Implications for language understanding and data privacy ...
|
|
|
|
BASE
|
|
Show details
|
|
74 |
GEM: Natural Language Generation, Evaluation, and Metrics - Part 4 ...
|
|
|
|
BASE
|
|
Show details
|
|
75 |
The statistical advantage of automatic NLG metrics at the system level ...
|
|
|
|
BASE
|
|
Show details
|
|
77 |
Supporting Cognitive and Emotional Empathic Writing of Students ...
|
|
|
|
BASE
|
|
Show details
|
|
78 |
What's in the Box? An Analysis of Undesirable Content in the Common Crawl Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
79 |
Are Pretrained Convolutions Better than Pretrained Transformers? ...
|
|
|
|
BASE
|
|
Show details
|
|
80 |
Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards? ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8... 59
|
|