Knowledge-Aware Debiased Inference Model Integrating Intervention and Counter-factual
The abductive natural language inference task (Abductive NLI) seeks to select more plausible hypothetical events based on given antecedent events and consequent events. However, inherent biases such as “logical defects” and “single-sentence label leakage” stemming from mediator and confounding varia...
Saved in:
| Main Author: | SUN Shengjie, MA Tinghuai, HUANG Kai |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2024-12-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2403018.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Label-aware debiased causal reasoning for Natural Language Inference
by: Kun Zhang, et al.
Published: (2024-01-01) -
Causal Inference for Modality Debiasing in Multimodal Emotion Recognition
by: Juyeon Kim, et al.
Published: (2024-12-01) -
Causal estimation of FTX collapse on cryptocurrency: a counterfactual prediction analysis
by: Khalid Khan, et al.
Published: (2025-01-01) -
TurkMedNLI: a Turkish medical natural language inference dataset through large language model based translation
by: İskender Ülgen Oğul, et al.
Published: (2025-01-01) -
Guider des stratégies de compréhension de l'oral en ALAO : le cas de l'inférence
by: Cécile Poussard
Published: (2003-06-01)