An Iterative Similarity based Adaptation Technique for Cross-domain Text Classification

Bhatt, Himanshu; Semwal, Deepali; Roy, Shourya

doi:10.18653/v1/k15-1006

Cited by 15 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…should be classified as the topic 'Apple' although it does not contain the keyword 'Apple' and the keyword 'Tim Cook' is not contained in the training samples. In other words, the reliable classifier should learn decision rules that generalize across domains (Fei and Liu 2015;Bhatt, Semwal, and Roy 2015;Bhatt, Sinha, and Roy 2016). This problematic phenomenon frequently happens in realworld datasets.…”

Section: Class : Applementioning

confidence: 99%

MASKER: Masked Keyword Regularization for Reliable Text Classification

Moon

Lee

et al. 2021

AAAI

View full text Add to dashboard Cite

Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned text classifiers is an often underlooked performance criterion. For instance, one may desire a model that can detect out-of-distribution (OOD) samples (drawn far from training distribution) or be robust against domain shifts. We claim that one central obstacle to the reliability is the over-reliance of the model on a limited number of keywords, instead of looking at the whole context. In particular, we find that (a) OOD samples often contain in-distribution keywords, while (b) cross-domain samples may not always contain keywords; over-relying on the keywords can be problematic for both cases. In light of this observation, we propose a simple yet effective fine-tuning method, coined masked keyword regularization (MASKER), that facilitates context-based prediction. MASKER regularizes the model to reconstruct the keywords from the rest of the words and make low-confidence predictions without enough context. When applied to various pre-trained language models (e.g., BERT, RoBERTa, and ALBERT), we demonstrate that MASKER improves OOD detection and cross-domain generalization without degrading classification accuracy. Code is available at https://github.com/alinlab/MASKER.

show abstract

Section: Class : Applementioning

confidence: 99%

MASKER: Masked Keyword Regularization for Reliable Text Classification

Moon

Lee

et al. 2021

AAAI

View full text Add to dashboard Cite

show abstract

“…Zhuang et al [42] presented a probabilistic model, by which both the shared and distinct concepts in different domains can be learned by the Expectation-Maximization process which optimizes the data likelihood. In [1], an algorithm to adapt a classification model by iteratively learning domain-specific features from the unlabeled test data is described. Cross-domain polarity classification.…”

Section: Cross-domain Classificationmentioning

confidence: 99%

“…In recent years, cross-domain sentiment (polarity) classification has gained popularity due to the advances in domain adaptation on one side, and to the abundance of documents from various domains available on the Web, expressing positive or negative opinion, on the other side. Some of the general domain adaptation frameworks have been applied to polarity classification [1,6,42], but there are some approaches that have been specifically designed for the cross-domain sentiment classification task [2, 11-13, 26, 30-33]. To the best of our knowledge, Blitzer et al [2] were the first to report results on cross-domain classification proposing the structural correspondence learning (SCL) method, and its variant based on mutual information (SCL-MI).…”

Section: Cross-domain Classificationmentioning

confidence: 99%

Transductive Learning with String Kernels for Cross-Domain Text Classification

Ionescu

Butnaru

2018

Neural Information Processing

View full text Add to dashboard Cite

For many text classification tasks, there is a major problem posed by the lack of labeled data in a target domain. Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of such classifiers is usually lower in the cross-domain setting. Recently, string kernels have obtained state-ofthe-art results in various text classification tasks such as native language identification or automatic essay scoring. Moreover, classifiers based on string kernels have been found to be robust to the distribution gap between different domains. In this paper, we formally describe an algorithm composed of two simple yet effective transductive learning approaches to further improve the results of string kernels in cross-domain settings. By adapting string kernels to the test set without using the ground-truth test labels, we report significantly better accuracy rates in cross-domain English polarity classification.

show abstract

“…For example, Lui and Baldwin (2011) chose to select cross-domain features to help domain adaption; Axelrod, He, and Gao (2011) chose to select pseudo in-domain data; Wen (2016) chose to train on multi-domain data. Sun, Kashima, and Ueda (2013) used Gaussian RBF and polynomial kernels to compute task similarity; Bhatt, Semwal, and Roy (2015) used cosine similarity measure to compute similarity for domain adaption.…”

Section: Cross-domain Learningmentioning

confidence: 99%

“…For cross-domain learning, a lot of previous work focuses on domain similarity (Sun, Kashima, and Ueda 2013;Bhatt, Semwal, and Roy 2015;Bhatt, Sinha, and Roy 2016). Sun, Kashima, and Ueda (2013) propose a multitask learning method to automatically discover task relationships from real-world data.…”

Section: Introductionmentioning

confidence: 99%

A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media

Sun

2017

AAAI

102

View full text Add to dashboard Cite

Named entity recognition (NER) in Chinese social media is important but difficult because of its informality and strong noise. Previous methods only focus on in-domain supervised learning which is limited by the rare annotated data. However, there are enough corpora in formal domains and massive in-domain unannotated texts which can be used to improve the task. We propose a unified model which can learn from out-of-domain corpora and in-domain unannotated texts. The unified model contains two major functions. One is for cross-domain learning and another for semi-supervised learning. Cross-domain learning function can learn out-of-domain information based on domain similarity. Semi-Supervised learning function can learn in-domain unannotated information by self-training. Both learning functions outperform existing methods for NER in Chinese social media. Finally, our unified model yields nearly 11% absolute improvement over previously published results.

show abstract

An Iterative Similarity based Adaptation Technique for Cross-domain Text Classification

Cited by 15 publications

References 15 publications

MASKER: Masked Keyword Regularization for Reliable Text Classification

MASKER: Masked Keyword Regularization for Reliable Text Classification

Transductive Learning with String Kernels for Cross-Domain Text Classification

A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media

Contact Info

Product

Resources

About