paper-with-me

홈 › Papers

Roles of Words: What Should (n’t) Be Augmented in Text Augmentation on Text Classification Tasks?

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Text augmentation techniques are widely used in text classification problems to improve the performance of classifiers, especially in low-resource scenarios. Previous text-editing-based methods augment the text in a non-selective manner: the words in the text are treated without difference during augmentation, which may result in unsatisfactory augmented samples. In this work, we present four kinds of roles of words (ROWs) which have different functions in text classification tasks, and design effective methods to automatically extract these ROWs based on statistical and semantic perspectives. Systematic experiments are conducted on what ROWs should (n't) be augmented during augmentation for classification tasks. Based on these experiments, we discover some interesting and instructive potential patterns that certain ROWs are especially suitable or unsuitable for certain augmentation operations. Guided by these patterns, we propose a set of Selective Text Augmentation (STA) operations, which significantly outperform traditional methods and show outstanding generalization performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationText Augmentationtext-classificationText Classification

Similar Papers 제목 키워드 기반

What Have Been Learned & What Should Be Learned? An Empirical Study of How to Selectively Augment Text for Classification

2021-09-01 · Biyang Guo, Sonqiao Han, Hailiang Huang

Text augmentation techniques are widely used in text classification problems to improve the performance of classifiers, especially in low-resource scenarios. Whilst lots of creative text augmentation methods have been de…

ClassificationText Augmentationtext-classificationText Classification

Selective Text Augmentation with Word Roles for Low-Resource Text Classification

2022-09-04 · Biyang Guo, Songqiao Han, Hailiang Huang

Data augmentation techniques are widely used in text classification tasks to improve the performance of classifiers, especially in low-resource scenarios. Most previous methods conduct text augmentation without consideri…

ClassificationData AugmentationLanguage ModellingLarge Language Model+5

MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval

2026-08-26 · Zihao Zhang, Dayan Wu, Xinze Liu, Hengjie Zhu 외 arxiv

Training-free zero-shot composed image retrieval finds a target image in a gallery from a reference image and a text edit without learning from task-specific image triplets. Existing methods typically describe the target…

Image Retrieval

Unsupervised Learning of Entailment-Vector Word Embeddings

2018-01-01 · ICLR 2018 1 · James Henderson

Entailment vectors are a principled way to encode in a vector what information is known and what is unknown. They are designed to model relations where one vector should include all the information in another vector, ca…

Word Embeddings

Joint Learning Templates and Slots for Event Schema Induction

2016-03-04 · NAACL 2016 6 · Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui

Automatic event schema induction (AESI) means to extract meta-event from raw text, in other words, to find out what types (templates) of event may exist in the raw text and what roles (slots) may exist in each event type…

Image SegmentationSemantic SegmentationSentence