Improve Text Classification Accuracy with Intent Information
- URL: http://arxiv.org/abs/2212.07649v1
- Date: Thu, 15 Dec 2022 08:15:32 GMT
- Title: Improve Text Classification Accuracy with Intent Information
- Authors: Yifeng Xie
- Abstract summary: Existing method does not consider the use of label information, which may weaken the performance of text classification systems in some token-aware scenarios.
We introduce the use of label information as label embedding for the task of text classification and achieve remarkable performance on benchmark dataset.
- Score: 0.38073142980733
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Text classification, a core component of task-oriented dialogue systems,
attracts continuous research from both the research and industry community, and
has resulted in tremendous progress. However, existing method does not consider
the use of label information, which may weaken the performance of text
classification systems in some token-aware scenarios. To address the problem,
in this paper, we introduce the use of label information as label embedding for
the task of text classification and achieve remarkable performance on benchmark
dataset.
Related papers
- Recent Advances in Hierarchical Multi-label Text Classification: A
Survey [11.709847202580505]
Hierarchical multi-label text classification aims to classify the input text into multiple labels, among which the labels are structured and hierarchical.
It is a vital task in many real world applications, e.g. scientific literature archiving.
arXiv Detail & Related papers (2023-07-30T16:13:00Z) - 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) - 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) - Out-of-Category Document Identification Using Target-Category Names as
Weak Supervision [64.671654559798]
Out-of-category detection aims to distinguish documents according to their semantic relevance to the inlier (or target) categories.
We present an out-of-category detection framework, which effectively measures how confidently each document belongs to one of the target categories.
arXiv Detail & Related papers (2021-11-24T21:01:25Z) - 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) - 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) - Adversarial Knowledge Transfer from Unlabeled Data [62.97253639100014]
We present a novel Adversarial Knowledge Transfer framework for transferring knowledge from internet-scale unlabeled data to improve the performance of a classifier.
An important novel aspect of our method is that the unlabeled source data can be of different classes from those of the labeled target data, and there is no need to define a separate pretext task.
arXiv Detail & Related papers (2020-08-13T08:04:27Z) - Label-guided Learning for Text Classification [47.15144153830845]
We propose a label-guided learning framework LguidedLearn for text representation and classification.
Our method is novel but simple that we only insert a label-guided encoding layer into the commonly used text representation learning schemas.
In our proposed framework, the label-guided layer can be easily and directly applied with a contextual encoding method to perform jointly learning.
arXiv Detail & Related papers (2020-02-25T10:05:56Z) - Description Based Text Classification with Reinforcement Learning [34.18824470728299]
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.
arXiv Detail & Related papers (2020-02-08T02:14:28Z)
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.