Lune

ACL Findings2023

A Robust Information-Masking Approach for Domain Counterfactual Generation

Pengfei Hong, Rishabh Bhardwaj, Navonil Majumder, Somak Aditya, Soujanya Poria

Abstract

Domain shift is a big challenge in NLP, thus, many approaches resort to learning domaininvariant features to mitigate the inference phase domain shift. Such methods, however, fail to leverage the domain-specific nuances relevant to the task at hand. To avoid such drawbacks, domain counterfactual generation aims to transform a text from the source domain to a given target domain. However, due to the limited availability of data, such frequency-based methods often miss and lead to some valid and spurious domain-token associations. Hence, we employ a three-step domain obfuscation approach that involves frequency and attention norm-based masking, to mask domain-specific cues, and unmasking to regain the domain generic context. Our experiments empirically show that the counterfactual samples sourced from our masked text lead to improved domain transfer on 10 out of 12 domain sentiment classification settings, with an average of 2% accuracy improvement over the state-of-the-art for unsupervised domain adaptation (UDA). Further, our model outperforms the state-of-the-art by achieving 1.4% average accuracy improvement in the adversarial domain adaptation (ADA) setting. Moreover, our model also shows its domain adaptation efficacy on a large multi-domain intent classification dataset where it attains state-of-the-art results. We release the codes publicly at https: //github.com/declare-lab/remask.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
  2. Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
  3. Attention is Not Only a Weight: Analyzing Transformers with Vector NormsGoro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro InuiEMNLP 2020 · 138 citations
  4. Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for TextNishtha Madaan, Inkit Padhi, Naveen Panwar, Diptikalyan SahaAAAI 2021 · 115 citations
  5. Uncovering Main Causalities for Long-tailed Information ExtractionGuoshun Nan, Jiaqi Zeng, Rui Qiao, Zhijiang Guo et al.EMNLP 2021 · 39 citations

Related papers

  1. DoCoGen: Domain Counterfactual Generation for Low Resource Domain AdaptationNitay Calderon, Eyal Ben-David, Amir Feder, Roi ReichartACL 2022
  2. Prompt-based Distribution Alignment for Domain Generalization in Text ClassificationChen Jia, Yue ZhangEMNLP 2022 · 4 citations
  3. Cross-Domain Review Generation for Aspect-Based Sentiment AnalysisJianfei Yu, Chenggong Gong, Rui XiaACL Findings 2021 · 47 citations
  4. Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment AnalysisYong Dai, Jian Liu, Xiancong Ren, Zenglin XuAAAI 2020 · 66 citations
  5. ToAlign: Task-Oriented Alignment for Unsupervised Domain AdaptationGuoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang et al.NeurIPS 2021 · 80 citations
Dusk over the sea between two cliffs drawn in fine vertical lines