Description Based Text Classification with Reinforcement Learning
- URL: http://arxiv.org/abs/2002.03067v3
- Date: Thu, 4 Jun 2020 13:18:34 GMT
- Title: Description Based Text Classification with Reinforcement Learning
- Authors: Duo Chai, Wei Wu, Qinghong Han, Fei Wu, Jiwei Li
- Abstract summary: We propose a new framework for text classification, in which each category label is associated with a category description.
We observe significant performance boosts over strong baselines on a wide range of text classification tasks.
- Score: 34.18824470728299
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The task of text classification is usually divided into two stages: {\it text
feature extraction} and {\it classification}. In this standard formalization
categories are merely represented as indexes in the label vocabulary, and the
model lacks for explicit instructions on what to classify. Inspired by the
current trend of formalizing NLP problems as question answering tasks, we
propose a new framework for text classification, in which each category label
is associated with a category description. Descriptions are generated by
hand-crafted templates or using abstractive/extractive models from
reinforcement learning. The concatenation of the description and the text is
fed to the classifier to decide whether or not the current label should be
assigned to the text. The proposed strategy forces the model to attend to the
most salient texts with respect to the label, which can be regarded as a hard
version of attention, leading to better performances. We observe significant
performance boosts over strong baselines on a wide range of text classification
tasks including single-label classification, multi-label classification and
multi-aspect sentiment analysis.
Related papers
- Gen-Z: Generative Zero-Shot Text Classification with Contextualized
Label Descriptions [50.92702206798324]
We propose a generative prompting framework for zero-shot text classification.
GEN-Z measures the LM likelihood of input text conditioned on natural language descriptions of labels.
We show that zero-shot classification with simple contextualization of the data source consistently outperforms both zero-shot and few-shot baselines.
arXiv Detail & Related papers (2023-11-13T07:12:57Z) - XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak
Supervision [6.406111099707549]
XAI-CLASS is a novel explanation-enhanced weakly-supervised text classification method.
It incorporates word saliency prediction as an auxiliary task.
XAI-CLASS outperforms other weakly-supervised text classification methods significantly.
arXiv Detail & Related papers (2023-10-31T23:24:22Z) - Description-Enhanced Label Embedding Contrastive Learning for Text
Classification [65.01077813330559]
Self-Supervised Learning (SSL) in model learning process and design a novel self-supervised Relation of Relation (R2) classification task.
Relation of Relation Learning Network (R2-Net) for text classification, in which text classification and R2 classification are treated as optimization targets.
external knowledge from WordNet to obtain multi-aspect descriptions for label semantic learning.
arXiv Detail & Related papers (2023-06-15T02:19:34Z) - IDEA: Interactive DoublE Attentions from Label Embedding for Text
Classification [4.342189319523322]
We propose a novel model structure via siamese BERT and interactive double attentions named IDEA to capture the information exchange of text and label names.
Our proposed method outperforms the state-of-the-art methods using label texts significantly with more stable results.
arXiv Detail & Related papers (2022-09-23T04:50:47Z) - Label Semantic Aware Pre-training for Few-shot Text Classification [53.80908620663974]
We propose Label Semantic Aware Pre-training (LSAP) to improve the generalization and data efficiency of text classification systems.
LSAP incorporates label semantics into pre-trained generative models (T5 in our case) by performing secondary pre-training on labeled sentences from a variety of domains.
arXiv Detail & Related papers (2022-04-14T17:33:34Z) - MotifClass: Weakly Supervised Text Classification with Higher-order
Metadata Information [47.44278057062421]
We study the problem of weakly supervised text classification, which aims to classify text documents into a set of pre-defined categories with category surface names only.
To be specific, we model the relationships between documents and metadata via a heterogeneous information network.
We propose a novel framework, named MotifClass, which selects category-indicative motif instances, retrieves and generates pseudo-labeled training samples based on category names and indicative motif instances.
arXiv Detail & Related papers (2021-11-07T07:39:10Z) - TF-CR: Weighting Embeddings for Text Classification [6.531659195805749]
We introduce a novel weighting scheme, Term Frequency-Category Ratio (TF-CR), which can weight high-frequency, category-exclusive words higher when computing word embeddings.
Experiments on 16 classification datasets show the effectiveness of TF-CR, leading to improved performance scores over existing weighting schemes.
arXiv Detail & Related papers (2020-12-11T19:23:28Z) - Text Classification Using Label Names Only: A Language Model
Self-Training Approach [80.63885282358204]
Current text classification methods typically require a good number of human-labeled documents as training data.
We show that our model achieves around 90% accuracy on four benchmark datasets including topic and sentiment classification.
arXiv Detail & Related papers (2020-10-14T17:06:41Z) - Exploring the Hierarchy in Relation Labels for Scene Graph Generation [75.88758055269948]
The proposed method can improve several state-of-the-art baselines by a large margin (up to $33%$ relative gain) in terms of Recall@50.
Experiments show that the proposed simple yet effective method can improve several state-of-the-art baselines by a large margin.
arXiv Detail & Related papers (2020-09-12T17:36:53Z) - Joint Embedding of Words and Category Labels for Hierarchical
Multi-label Text Classification [4.2750700546937335]
hierarchical text classification (HTC) has received extensive attention and has broad application prospects.
We propose a joint embedding of text and parent category based on hierarchical fine-tuning ordered neurons LSTM (HFT-ONLSTM) for HTC.
arXiv Detail & Related papers (2020-04-06T11:06:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.