Lune

EMNLP2023顶会

Using Interpretation Methods for Model Enhancement

Zhuo Chen, Chengyue Jiang, Kewei Tu

摘要

In the age of neural natural language processing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales. However, this intuitive idea has not been fully explored. In this paper, we propose a framework of utilizing interpretation methods and gold rationales to enhance models. Our framework is very general in the sense that it can incorporate various interpretation methods. Previously proposed gradient-based methods can be shown as an instance of our framework. We also propose two novel instances utilizing two other types of interpretation methods, erasure/replace-based and extractor-based methods, for model enhancement. We conduct comprehensive experiments on a variety of tasks. Experimental results show that our framework is effective especially in low-resource settings in enhancing models with various interpretation methods, and our two newly-proposed methods outperform gradient-based methods in most settings. Code is available at https://github. com/Chord-Chen-30/UIMER .

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

可以从这些问题问起

Lune 可以查阅

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

它引用的引用它的从左到右按年份排列,引用越多,位置越高。

它引用的 Paper3

  1. Interpretation of NLP models through input marginalizationSiwon Kim, Jihun Yi, Eunji Kim, Sungroh YoonEMNLP 2020 · 41 次引用
  2. How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable MaskingNicola De Cao, Michael Sejr Schlichtkrull, Wilker Aziz, Ivan TitovEMNLP 2020 · 13 次引用
  3. Exploring Distantly-Labeled Rationales in Neural Network ModelsQuzhe Huang, Shengqi Zhu, Yansong Feng, Dongyan ZhaoACL 2021

相关 Paper

  1. A Reasoning Paradigm for Named Entity RecognitionHui Huang, Yanping Chen, Ruizhang Huang, Chuan Lin 等AAAI 2026
  2. QUASER: Question Answering with Scalable Extractive RationalizationAsish Ghoshal, Srinivasan Iyer, Bhargavi Paranjape, Kushal Lakhotia 等SIGIR 2022 · 2 次引用
  3. Making a (Counterfactual) Difference One Rationale at a TimeMitchell Plyler, Michael Green, Min ChiNeurIPS 2021 · 12 次引用
  4. Blocker and Matcher Can Mutually Benefit: A Co-Learning Framework for Low-Resource Entity ResolutionShiwen Wu, Qiyu Wu, Honghua Dong, Wen Hua 等VLDB 2024 · 10 次引用
  5. ERASER: A Benchmark to Evaluate Rationalized NLP ModelsJay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric P. Lehman 等ACL 2020 · 36 次引用
黄昏的海面,两侧是细线勾勒的悬崖