paper-with-me

홈 › Papers

E-VarM: Enhanced Variational Word Masks to Improve the Interpretability of Text Classification Models

2022-10-01 · COLING 2022 10 · Ling Ge, Chunming Hu, Guanghui Ma, Junshuang Wu, Junfan Chen, Jihong Liu, Hong Zhang, Wenyi Qin, Richong Zhang

Enhancing the interpretability of text classification models can help increase the reliability of these models in real-world applications. Currently, most researchers focus on extracting task-specific words from inputs to improve the interpretability of the model. The competitive approaches exploit the Variational Information Bottleneck (VIB) to improve the performance of word masking at the word embedding layer to obtain task-specific words. However, these approaches ignore the multi-level semantics of the text, which can impair the interpretability of the model, and do not consider the risk of representation overlap caused by the VIB, which can impair the classification performance. In this paper, we propose an enhanced variational word masks approach, named E-VarM, to solve these two issues effectively. The E-VarM combines multi-level semantics from all hidden layers of the model to mask out task-irrelevant words and uses contrastive learning to readjust the distances between representations. Empirical studies on ten benchmark text classification datasets demonstrate that our approach outperforms the SOTA methods in simultaneously improving the interpretability and accuracy of the model.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationContrastive Learningtext-classificationText Classification

Similar Papers 제목 키워드 기반

Variationally Mimetic Operator Networks

2022-09-26 · Dhruv Patel, Deep Ray, Michael R. A. Abdelmalik, Thomas J. R. Hughes 외

In recent years operator networks have emerged as promising deep learning tools for approximating the solution to partial differential equations (PDEs). These networks map input functions that describe material propertie…

VARMA-Enhanced Transformer for Time Series Forecasting

2025-09-05 · Jiajun Song, Xiaoou Liu arxiv

Transformer-based models have significantly advanced time series forecasting. Recent work, like the Cross-Attention-only Time Series transformer (CATS), shows that removing self-attention can make the model more accurate…

Time Series ForecastingTime Series Analysis

VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding

2022-11-01 · Dou Hu, Xiaolong Hou, Xiyang Du, Mengyuan Zhou 외

Pre-trained language models have achieved promising performance on general benchmarks, but underperform when migrated to a specific domain. Recent works perform pre-training from scratch or continual pre-training on doma…

Citation Intent ClassificationLanguage ModelingLanguage Modelling

Variational Structured Semantic Inference for Diverse Image Captioning

2019-12-01 · NeurIPS 2019 12 · Fuhai Chen, Rongrong Ji, Jiayi Ji, Xiaoshuai Sun 외

Despite the exciting progress in image captioning, generating diverse captions for a given image remains as an open problem. Existing methods typically apply generative models such as Variational Auto-Encoder to diversif…

DecoderDiversityImage Captioning

An optimal Petrov-Galerkin framework for operator networks

2025-03-06 · Philip Charles, Deep Ray, Yue Yu, Joost Prins 외

The optimal Petrov-Galerkin formulation to solve partial differential equations (PDEs) recovers the best approximation in a specified finite-dimensional (trial) space with respect to a suitable norm. However, the recover…