# Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction

arXiv: https://arxiv.org/abs/2305.03503 · HTML: https://mlsanity.com/paper/2305.03503/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 2 May 2023.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [Deep Learning for Sentiment Analysis : A Survey](https://mlsanity.com/paper/1801.07883/) (2018)
- [Interpretable Neural Predictions with Differentiable Binary Variables](https://mlsanity.com/paper/1905.08160/) (2019)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://mlsanity.com/paper/2303.13547/) (2023)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction](https://mlsanity.com/paper/2004.02438/) (2020)
- [Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation](https://mlsanity.com/paper/2108.06468/) (2021)
- [Semi-supervised Relation Extraction via Incremental Meta Self-Training](https://mlsanity.com/paper/2010.16410/) (2020)
- [Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction](https://mlsanity.com/paper/2109.06415/) (2021)
- [UNIREX: A Unified Learning Framework for Language Model Rationale Extraction](https://mlsanity.com/paper/2112.08802/) (2021)
- [HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction](https://mlsanity.com/paper/2205.02225/) (2022)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution](https://mlsanity.com/paper/2210.17004/) (2022)
- [LargeEA: Aligning Entities for Large-scale Knowledge Graphs](https://mlsanity.com/paper/2108.05211/) (2021)
- [Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph](https://mlsanity.com/paper/2208.03903/) (2022)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities](https://mlsanity.com/paper/2205.10312/) (2022)
- [Unsupervised Entity Alignment for Temporal Knowledge Graphs](https://mlsanity.com/paper/2302.00796/) (2023)
- [LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction](https://mlsanity.com/paper/2001.04437/) (2020)
- [Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation](https://mlsanity.com/paper/2109.02046/) (2021)
- [Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation](https://mlsanity.com/paper/2206.02115/) (2022)
- [Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space](https://mlsanity.com/paper/2304.00241/) (2023)
- [Knowledge-aware Neural Networks with Personalized Feature Referencing for Cold-start Recommendation](https://mlsanity.com/paper/2209.13973/) (2022)
- [Scene Graph Modification as Incremental Structure Expanding](https://mlsanity.com/paper/2209.09093/) (2022)

## Built on by (most cited first, 6 of 6)

- [GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks](https://mlsanity.com/paper/2305.16663/) (2023)
- [Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis](https://mlsanity.com/paper/2305.16166/) (2023)
- [Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction](https://mlsanity.com/paper/2310.16822/) (2023)
- [Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models](https://mlsanity.com/paper/2310.11085/) (2023)
- [Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery](https://mlsanity.com/paper/2401.06327/) (2024)
- [Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin](https://mlsanity.com/paper/2410.20320/) (2024)

## Abstract (arXiv)

Relation extraction (RE) aims to extract potential relations according to the context of two entities, thus, deriving rational contexts from sentences plays an important role. Previous works either focus on how to leverage the entity information (e.g., entity types, entity verbalization) to inference relations, but ignore context-focused content, or use counterfactual thinking to remove the model's bias of potential relations in entities, but the relation reasoning process will still be hindered by irrelevant content. Therefore, how to preserve relevant content and remove noisy segments from sentences is a crucial task. In addition, retained content needs to be fluent enough to maintain semantic coherence and interpretability. In this work, we propose a novel rationale extraction framework named RE2, which leverages two continuity and sparsity factors to obtain relevant and coherent rationales from sentences. To solve the problem that the gold rationales are not labeled, RE2 applies an optimizable binary mask to each token in the sentence, and adjust the rationales that need to be selected according to the relation label. Experiments on four datasets show that RE2 surpasses baselines.