2021
DOI: 10.1609/aaai.v35i14.17547
|View full text |Cite
|
Sign up to set email alerts
|

Distribution Matching for Rationalization

Abstract: The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks. By definition, rationales represent key text pieces used for prediction and thus should have similar classification feature distribution compared to the original input text. However, previous methods mainly focused on maximizing the mutual information between rationales and labels while neglecting the relationship between rationales and input text. To address this i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
1

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(8 citation statements)
references
References 26 publications
0
7
1
Order By: Relevance
“…with respect to the selections where the first term penalizes the number of selections, and the second one encourages continuity of selections. The specific form may be a different subject to the different architecture of the rationale model (Bastings, Aziz, and Titov 2019;Huang et al 2021;Sha, Camburu, and Lukasiewicz 2022). For example, many methods replace the first term of the above regularizer with…”
Section: Methodology Preliminarymentioning
confidence: 99%
See 4 more Smart Citations
“…with respect to the selections where the first term penalizes the number of selections, and the second one encourages continuity of selections. The specific form may be a different subject to the different architecture of the rationale model (Bastings, Aziz, and Titov 2019;Huang et al 2021;Sha, Camburu, and Lukasiewicz 2022). For example, many methods replace the first term of the above regularizer with…”
Section: Methodology Preliminarymentioning
confidence: 99%
“…Some researchers have accomplished this by adding extra modules to the rationalization process. Huang et al (2021) matched the distributions of rationales and input text in both the feature and output spaces. Sha, Camburu, and Lukasiewicz (2022) introduced an adversarial-based technique to make the select-then-predict model learn from an extra predictor.…”
Section: Selective Rationalizationmentioning
confidence: 99%
See 3 more Smart Citations