Label Semantic Aware Pre-training for Few-shot Text Classification
- URL: http://arxiv.org/abs/2204.07128v1
- Date: Thu, 14 Apr 2022 17:33:34 GMT
- Title: Label Semantic Aware Pre-training for Few-shot Text Classification
- Authors: Aaron Mueller, Jason Krone, Salvatore Romeo, Saab Mansour, Elman
Mansimov, Yi Zhang, Dan Roth
- Abstract summary: 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.
- Score: 53.80908620663974
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In text classification tasks, useful information is encoded in the label
names. Label semantic aware systems have leveraged this information for
improved text classification performance during fine-tuning and prediction.
However, use of label-semantics during pre-training has not been extensively
explored. We therefore 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. As domain-general pre-training requires large amounts of data, we
develop a filtering and labeling pipeline to automatically create
sentence-label pairs from unlabeled text. We perform experiments on intent
(ATIS, Snips, TOPv2) and topic classification (AG News, Yahoo! Answers). LSAP
obtains significant accuracy improvements over state-of-the-art models for
few-shot text classification while maintaining performance comparable to state
of the art in high-resource settings.
Related papers
- Leveraging Label Semantics and Meta-Label Refinement for Multi-Label Question Classification [11.19022605804112]
This paper introduces RR2QC, a novel Retrieval Reranking method To multi-label Question Classification.
It uses label semantics and meta-label refinement to enhance personalized learning and resource recommendation.
Experimental results demonstrate that RR2QC outperforms existing classification methods in Precision@k and F1 scores.
arXiv Detail & Related papers (2024-11-04T06:27:14Z) - Co-training for Low Resource Scientific Natural Language Inference [65.37685198688538]
We propose a novel co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels.
By assigning importance weights instead of filtering out examples based on an arbitrary threshold on the predicted confidence, we maximize the usage of automatically labeled data.
The proposed method obtains an improvement of 1.5% in Macro F1 over the distant supervision baseline, and substantial improvements over several other strong SSL baselines.
arXiv Detail & Related papers (2024-06-20T18:35:47Z) - Substituting Data Annotation with Balanced Updates and Collective Loss
in Multi-label Text Classification [19.592985329023733]
Multi-label text classification (MLTC) is the task of assigning multiple labels to a given text.
We study the MLTC problem in annotation-free and scarce-annotation settings in which the magnitude of available supervision signals is linear to the number of labels.
Our method follows three steps, (1) mapping input text into a set of preliminary label likelihoods by natural language inference using a pre-trained language model, (2) calculating a signed label dependency graph by label descriptions, and (3) updating the preliminary label likelihoods with message passing along the label dependency graph.
arXiv Detail & Related papers (2023-09-24T04:12:52Z) - 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) - Rank-Aware Negative Training for Semi-Supervised Text Classification [3.105629960108712]
Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training.
This paper presents a Rank-aware Negative Training (RNT) framework to address SSTC in learning with noisy label manner.
arXiv Detail & Related papers (2023-06-13T08:41:36Z) - Exploring Structured Semantic Prior for Multi Label Recognition with
Incomplete Labels [60.675714333081466]
Multi-label recognition (MLR) with incomplete labels is very challenging.
Recent works strive to explore the image-to-label correspondence in the vision-language model, ie, CLIP, to compensate for insufficient annotations.
We advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior.
arXiv Detail & Related papers (2023-03-23T12:39:20Z) - Like a Good Nearest Neighbor: Practical Content Moderation and Text
Classification [66.02091763340094]
Like a Good Nearest Neighbor (LaGoNN) is a modification to SetFit that introduces no learnable parameters but alters input text with information from its nearest neighbor.
LaGoNN is effective at flagging undesirable content and text classification, and improves the performance of SetFit.
arXiv Detail & Related papers (2023-02-17T15:43:29Z) - LST: Lexicon-Guided Self-Training for Few-Shot Text Classification [3.7277082975620806]
We introduce LST, a simple self-training method that uses a lexicon to guide the pseudo-labeling mechanism.
We demonstrate that this simple yet well-crafted lexical knowledge achieves 1.0-2.0% better performance on 30 labeled samples per class for five benchmark datasets.
arXiv Detail & Related papers (2022-02-05T14:33:12Z) - GUDN A novel guide network for extreme multi-label text classification [12.975260278131078]
This paper constructs a novel guide network (GUDN) to help fine-tune the pre-trained model to instruct classification later.
We also use the raw label semantics to effectively explore the latent space between texts and labels, which can further improve predicted accuracy.
arXiv Detail & Related papers (2022-01-10T07:33:36Z) - Unsupervised Label Refinement Improves Dataless Text Classification [48.031421660674745]
Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description.
While promising, it crucially relies on accurate descriptions of the label set for each downstream task.
This reliance causes dataless classifiers to be highly sensitive to the choice of label descriptions and hinders the broader application of dataless classification in practice.
arXiv Detail & Related papers (2020-12-08T03:37:50Z)
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.