# IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification

arXiv: https://arxiv.org/abs/2209.11407 · HTML: https://mlsanity.com/paper/2209.11407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 23 Sep 2022.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering](https://mlsanity.com/paper/1708.01471/) (2017)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [Joint Embedding of Words and Labels for Text Classification](https://mlsanity.com/paper/1805.04174/) (2018)
- [Text Classification Using Label Names Only: A Language Model Self-Training Approach](https://mlsanity.com/paper/2010.07245/) (2020)
- [GILE: A Generalized Input-Label Embedding for Text Classification](https://mlsanity.com/paper/1806.06219/) (2018)
- [Masked Siamese ConvNets](https://mlsanity.com/paper/2206.07700/) (2022)
- [Label Confusion Learning to Enhance Text Classification Models](https://mlsanity.com/paper/2012.04987/) (2020)

## Abstract (arXiv)

Current text classification methods typically encode the text merely into embedding before a naive or complicated classifier, which ignores the suggestive information contained in the label text. As a matter of fact, humans classify documents primarily based on the semantic meaning of the subcategories. We propose a novel model structure via siamese BERT and interactive double attentions named IDEA ( Interactive DoublE Attentions) to capture the information exchange of text and label names. Interactive double attentions enable the model to exploit the inter-class and intra-class information from coarse to fine, which involves distinguishing among all labels and matching the semantical subclasses of ground truth labels. Our proposed method outperforms the state-of-the-art methods using label texts significantly with more stable results.