Lune

EMNLP Findings2020

Weakly- and Semi-supervised Evidence Extraction

Danish Pruthi, Bhuwan Dhingra, Graham Neubig, Zachary C. Lipton

Abstract

For many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness.However, in practice, evidence annotations may only be available for a minority of training examples (if available at all).In this paper, we propose new methods to combine few evidence annotations (strong semisupervision) with abundant document-level labels (weak supervision) for the task of evidence extraction.Evaluating on two classification tasks that feature evidence annotations, we find that our methods outperform baselines adapted from the interpretability literature to our task.Our approach yields gains with as few as hundred evidence annotations. 1 Explanations Evidence Objective Elucidate "the reasons behind predictions".Enable users to quickly verify the predictions. EvaluationExplanations are specific to the model.No ground truth explanations to compare against.Evidence is a characteristic of the task.Can be compared against human-labeled evidence. ExampleA horror movie that lacks cohesion.A horror movie that lacks cohesion.

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.

8 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction cites Learning to Faithfully Rationalize by Construction
  • Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction cites An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
  • FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation cites Learning to Faithfully Rationalize by Construction
  • FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation cites An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
  • Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery cites Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction
  • Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery cites FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation
  • Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery cites An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
  • An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction cites Learning to Faithfully Rationalize by Construction
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers8

  1. Human Rationales as Attribution Priors for Explainable Stance DetectionSahil Jayaram, Emily AllawayEMNLP 2021 · 17 citations
  2. Unifying Model Explainability and Robustness for Joint Text Classification and Rationale ExtractionDongfang Li, Baotian Hu, Qingcai Chen, Tujie Xu et al.AAAI 2022 · 16 citations
  3. FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale GenerationKushal Lakhotia, Bhargavi Paranjape, Asish Ghoshal, Scott Yih et al.EMNLP 2021 · 15 citations
  4. MDACE: MIMIC Documents Annotated with Code EvidenceHua Cheng, Rana Jafari, April Russell, Russell Klopfer et al.ACL 2023 · 11 citations
  5. Towards Faithful Explanations: Boosting Rationalization with Shortcuts DiscoveryLinan Yue, Qi Liu, Yichao Du, Li Wang et al.ICLR 2024 · 10 citations

Builds on3

  1. Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
  2. An Information Bottleneck Approach for Controlling Conciseness in Rationale ExtractionBhargavi Paranjape, Mandar Joshi, John Thickstun, Hannaneh Hajishirzi et al.EMNLP 2020 · 13 citations
  3. Learning to Faithfully Rationalize by ConstructionSarthak Jain, Sarah Wiegreffe, Yuval Pinter, Byron C. WallaceACL 2020

Related papers

  1. Strength from Weakness: Fast Learning Using Weak SupervisionJoshua Robinson, Stefanie Jegelka, Suvrit SraICML 2020 · 35 citations
  2. Right for the Right Reason: Evidence Extraction for Trustworthy Tabular ReasoningVivek Gupta, Shuo Zhang, Alakananda Vempala, Yujie He et al.ACL 2022
  3. Few-Shot Document-Level Event Argument ExtractionXianjun Yang, Yujie Lu, Linda R. PetzoldACL 2023 · 5 citations
  4. Disambiguation of Weak Supervision leading to Exponential Convergence ratesVivien A. Cabannes, Francis R. Bach, Alessandro RudiICML 2021 · 6 citations
  5. Plausible Extractive Rationalization through Semi-Supervised Entailment SignalWei Jie Yeo, Ranjan Satapathy, Erik CambriaACL Findings 2024 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines