Page: 1 2 3 4 5 6 7 8 9... 63
81 |
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
|
|
82 |
How effective is BERT without word ordering? Implications for language understanding and data privacy ...
|
|
|
|
BASE
|
|
Show details
|
|
83 |
GEM: Natural Language Generation, Evaluation, and Metrics - Part 4 ...
|
|
|
|
BASE
|
|
Show details
|
|
84 |
The statistical advantage of automatic NLG metrics at the system level ...
|
|
|
|
BASE
|
|
Show details
|
|
86 |
Supporting Cognitive and Emotional Empathic Writing of Students ...
|
|
|
|
BASE
|
|
Show details
|
|
87 |
What's in the Box? An Analysis of Undesirable Content in the Common Crawl Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
88 |
Are Pretrained Convolutions Better than Pretrained Transformers? ...
|
|
|
|
BASE
|
|
Show details
|
|
89 |
Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards? ...
|
|
|
|
BASE
|
|
Show details
|
|
90 |
Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring ...
|
|
|
|
BASE
|
|
Show details
|
|
91 |
Hate Speech Detection Based on Sentiment Knowledge Sharing ...
|
|
|
|
BASE
|
|
Show details
|
|
92 |
Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation ...
|
|
|
|
BASE
|
|
Show details
|
|
93 |
Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
94 |
WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
95 |
An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization ...
|
|
|
|
BASE
|
|
Show details
|
|
97 |
Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance ...
|
|
|
|
BASE
|
|
Show details
|
|
98 |
Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities ...
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Neural Machine Translation with Monolingual Translation Memory ...
|
|
|
|
BASE
|
|
Show details
|
|
100 |
Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Conversational Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 63
|
|