Lune

EMNLP Findings2022

Context-aware Information-theoretic Causal De-biasing for Interactive Sequence Labeling

Junda Wu, Rui Wang, Tong Yu, Ruiyi Zhang, Handong Zhao, Shuai Li, Ricardo Henao, Ani Nenkova

Abstract

Supervised training of existing deep learning models for sequence labeling relies on large scale labeled datasets. Such datasets are generally created with crowd-source labeling. However, crowd-source labeling for tasks of sequence labeling can be expensive and timeconsuming. Further, crowd-source labeling by external annotators may not be appropriate for data that contains user private information. Considering the above limitations of crowd-source labeling, we study interactive sequence labeling that allows training directly with the user feedback, which alleviates the annotation cost and maintains the user privacy. We identify two biases, namely, context bias and feedback bias, by formulating interactive sequence labeling via a Structural Causal Model (SCM). To alleviate the context and feedback bias based on the SCM, we identify the frequent context tokens as confounders in the backdoor adjustment and further propose an entropy-based modulation that is inspired by information theory. With extensive experiments, we validate that our approach can effectively alleviate the biases and our models can be efficiently learnt with the user feedback.

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 on14

  1. Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationYongming Rao, Guangyi Chen, Jiwen Lu, Jie ZhouICCV 2021 · 330 citations
  2. Interventional Few-Shot LearningZhongqi Yue, Hanwang Zhang, Qianru Sun, Xian-Sheng HuaNeurIPS 2020 · 284 citations
  3. Unbiased Sequential Recommendation with Latent ConfoundersZhenlei Wang, Shiqi Shen, Zhipeng Wang, Bo Chen et al.WWW 2022 · 75 citations
  4. Multi-Scale Self-Attention for Text ClassificationQipeng Guo, Xipeng Qiu, Pengfei Liu, Xiangyang Xue et al.AAAI 2020 · 69 citations
  5. DeVLBert: Learning Deconfounded Visio-Linguistic RepresentationsShengyu Zhang, Tan Jiang, Tan Wang, Kun Kuang et al.ACM MM 2020 · 66 citations

Related papers

  1. De-biasing Distantly Supervised Named Entity Recognition via Causal InterventionWenkai Zhang, Hongyu Lin, Xianpei Han, Le SunACL 2021
  2. Meta Self-training for Few-shot Neural Sequence LabelingYaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu et al.KDD 2021 · 56 citations
  3. Debiasing NLU Models via Causal Intervention and Counterfactual ReasoningBing Tian, Yixin Cao, Yong Zhang, Chunxiao XingAAAI 2022 · 45 citations
  4. DeCoT: Debiasing Chain-of-Thought for Knowledge-Intensive Tasks in Large Language Models via Causal InterventionJunda Wu, Tong Yu, Xiang Chen, Haoliang Wang et al.ACL 2024
  5. De-biased Attention Supervision for Text Classification with CausalityYiquan Wu, Yifei Liu, Ziyu Zhao, Weiming Lu et al.AAAI 2024 · 10 citations
Dusk over the sea between two cliffs drawn in fine vertical lines