DE eng

Search in the Catalogues and Directories

Hits 1 – 7 of 7

1
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation ...
BASE
Show details
2
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms ...
BASE
Show details
3
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models ...
BASE
Show details
4
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning ...
BASE
Show details
5
Discretized Integrated Gradients for Explaining Language Models ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.805/ Abstract: As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation. It measures feature importance by averaging the model’s output gradient interpolated along a straight-line path in the input data space. However, such straight-line interpolated points are not representative of text data due to the inherent discreteness of the word embedding space. This questions the faithfulness of the gradients computed at the interpolated points and consequently, the quality of the generated explanations. Here we propose Discretized Integrated Gradients (DIG), which allows effective attribution along non-linear interpolation paths. We develop two interpolation strategies for the discrete word embedding space that generates interpolation points that lie close to actual words in the embedding space, yielding more faithful gradient ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
URL: https://underline.io/lecture/37729-discretized-integrated-gradients-for-explaining-language-models
https://dx.doi.org/10.48448/9zkk-rz92
BASE
Hide details
6
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources ...
BASE
Show details
7
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
7
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern