Interventional training for out-of-distribution natural language understanding
Out-of-distribution (OOD) settings are used to measure a model’s performance when the distribution of the test data is different from that of the training data. NLU models are known to suffer in OOD settings (Utama et al., 2020b). We study this issue from the perspective of causality, which sees con...
Saved in:
Main Authors: | YU, Sicheng, JIANG, Jing, ZHANG, Hao, NIU, Yulei, SUN, Qianru, BING, Lidong |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7548 https://ink.library.smu.edu.sg/context/sis_research/article/8551/viewcontent/Debias_Sicheng.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Class name guided out-of-scope intent classification
by: GAUTAM, Chandan, et al.
Published: (2024) -
Balancing visual context understanding in dialogue for image retrieval
by: WEI, Zhaohui, et al.
Published: (2024) -
Domain identification for intention posts on online social media
by: Luong, Thai Le, et al.
Published: (2016) -
Toward holistic scene understanding: Feedback enabled cascaded classification models
by: Li C., et al.
Published: (2018) -
COSY: COunterfactual SYntax for cross-lingual understanding
by: YU, Sicheng, et al.
Published: (2021)