Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"Text Classification": models, code, and papers

Rank over Class: The Untapped Potential of Ranking in Natural Language Processing

Sep 10, 2020
Amir Atapour-Abarghouei, Stephen Bonner, Andrew Stephen McGough

Text classification has long been a staple in natural language processing with applications spanning across sentiment analysis, online content tagging, recommender systems and spam detection. However, text classification, by nature, suffers from a variety of issues stemming from dataset imbalance, text ambiguity, subjectivity and the lack of linguistic context in the data. In this paper, we explore the use of text ranking, commonly used in information retrieval, to carry out challenging classification-based tasks. We propose a novel end-to-end ranking approach consisting of a Transformer network responsible for producing representations for a pair of text sequences, which are in turn passed into a context aggregating network outputting ranking scores used to determine an ordering to the sequences based on some notion of relevance. We perform numerous experiments on publicly-available datasets and investigate the possibility of applying our ranking approach to certain problems often addressed using classification. In an experiment on a heavily-skewed sentiment analysis dataset, converting ranking results to classification labels yields an approximately 22% improvement over state-of-the-art text classification, demonstrating the efficacy of text ranking over text classification in certain scenarios.

Access Paper or Ask Questions

Constructing Contrastive samples via Summarization for Text Classification with limited annotations

Apr 11, 2021
Yangkai Du, Tengfei Ma, Lingfei Wu, Fangli Xu, Xuhong Zhang, Shouling Ji

Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its success. Unlike vision tasks, the data augmentation method for contrastive learning has not been investigated sufficiently in language tasks. In this paper, we propose a novel approach to constructing contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representations which greatly benefit text classification tasks with limited annotations. To further improve the method, we mix up samples from different classes and add an extra regularization, named mix-sum regularization, in addition to the cross-entropy-loss. Experiments on real-world text classification datasets (Amazon-5, Yelp-5, AG News) demonstrate the effectiveness of the proposed contrastive learning framework with summarization-based data augmentation and mix-sum regularization.

Access Paper or Ask Questions

TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification

Jun 21, 2021
Andrés Villa, Juan-Manuel Perez-Rua, Vladimir Araujo, Juan Carlos Niebles, Victor Escorcia, Alvaro Soto

Recently, few-shot learning has received increasing interest. Existing efforts have been focused on image classification, with very few attempts dedicated to the more challenging few-shot video classification problem. These few attempts aim to effectively exploit the temporal dimension in videos for better learning in low data regimes. However, they have largely ignored a key characteristic of video which could be vital for few-shot recognition, that is, videos are often accompanied by rich text descriptions. In this paper, for the first time, we propose to leverage these human-provided textual descriptions as privileged information when training a few-shot video classification model. Specifically, we formulate a text-based task conditioner to adapt video features to the few-shot learning task. Our model follows a transductive setting where query samples and support textual descriptions can be used to update the support set class prototype to further improve the task-adaptation ability of the model. Our model obtains state-of-the-art performance on four challenging benchmarks in few-shot video action classification.

* 10 pages including references, 7 figures, and 4 tables 
Access Paper or Ask Questions

Incorporating Visual Layout Structures for Scientific Text Classification

Jun 01, 2021
Zejiang Shen, Kyle Lo, Lucy Lu Wang, Bailey Kuehl, Daniel S. Weld, Doug Downey

Classifying the core textual components of a scientific paper-title, author, body text, etc.-is a critical first step in automated scientific document understanding. Previous work has shown how using elementary layout information, i.e., each token's 2D position on the page, leads to more accurate classification. We introduce new methods for incorporating VIsual LAyout structures (VILA), e.g., the grouping of page texts into text lines or text blocks, into language models to further improve performance. We show that the I-VILA approach, which simply adds special tokens denoting boundaries between layout structures into model inputs, can lead to +1~4.5 F1 Score improvements in token classification tasks. Moreover, we design a hierarchical model H-VILA that encodes these layout structures and record a up-to 70% efficiency boost without hurting prediction accuracy. The experiments are conducted on a newly curated evaluation suite, S2-VLUE, with a novel metric measuring VILA awareness and a new dataset covering 19 scientific disciplines with gold annotations. Pre-trained weights, benchmark datasets, and source code will be available at}{

* 13 pages, 5 figures, 6 tables 
Access Paper or Ask Questions

Multimodal Depression Classification Using Articulatory Coordination Features And Hierarchical Attention Based Text Embeddings

Feb 13, 2022
Nadee Seneviratne, Carol Espy-Wilson

Multimodal depression classification has gained immense popularity over the recent years. We develop a multimodal depression classification system using articulatory coordination features extracted from vocal tract variables and text transcriptions obtained from an automatic speech recognition tool that yields improvements of area under the receiver operating characteristics curve compared to uni-modal classifiers (7.5% and 13.7% for audio and text respectively). We show that in the case of limited training data, a segment-level classifier can first be trained to then obtain a session-wise prediction without hindering the performance, using a multi-stage convolutional recurrent neural network. A text model is trained using a Hierarchical Attention Network (HAN). The multimodal system is developed by combining embeddings from the session-level audio model and the HAN text model

* Accepted to ICASSP 2022. arXiv admin note: text overlap with arXiv:2104.04195 
Access Paper or Ask Questions

Finding Good Representations of Emotions for Text Classification

Aug 22, 2018
Ji Ho Park

It is important for machines to interpret human emotions properly for better human-machine communications, as emotion is an essential part of human-to-human communications. One aspect of emotion is reflected in the language we use. How to represent emotions in texts is a challenge in natural language processing (NLP). Although continuous vector representations like word2vec have become the new norm for NLP problems, their limitations are that they do not take emotions into consideration and can unintentionally contain bias toward certain identities like different genders. This thesis focuses on improving existing representations in both word and sentence levels by explicitly taking emotions inside text and model bias into account in their training process. Our improved representations can help to build more robust machine learning models for affect-related text classification like sentiment/emotion analysis and abusive language detection. We first propose representations called emotional word vectors (EVEC), which is learned from a convolutional neural network model with an emotion-labeled corpus, which is constructed using hashtags. Secondly, we extend to learning sentence-level representations with a huge corpus of texts with the pseudo task of recognizing emojis. Our results show that, with the representations trained from millions of tweets with weakly supervised labels such as hashtags and emojis, we can solve sentiment/emotion analysis tasks more effectively. Lastly, as examples of model bias in representations of existing approaches, we explore a specific problem of automatic detection of abusive language. We address the issue of gender bias in various neural network models by conducting experiments to measure and reduce those biases in the representations in order to build more robust classification models.

* HKUST MPhil Thesis, 2018 
* HKUST MPhil Thesis, 87 pages 
Access Paper or Ask Questions

A Fuzzy Similarity Based Concept Mining Model for Text Classification

Apr 10, 2012
Shalini Puri

Text Classification is a challenging and a red hot field in the current scenario and has great importance in text categorization applications. A lot of research work has been done in this field but there is a need to categorize a collection of text documents into mutually exclusive categories by extracting the concepts or features using supervised learning paradigm and different classification algorithms. In this paper, a new Fuzzy Similarity Based Concept Mining Model (FSCMM) is proposed to classify a set of text documents into pre - defined Category Groups (CG) by providing them training and preparing on the sentence, document and integrated corpora levels along with feature reduction, ambiguity removal on each level to achieve high system performance. Fuzzy Feature Category Similarity Analyzer (FFCSA) is used to analyze each extracted feature of Integrated Corpora Feature Vector (ICFV) with the corresponding categories or classes. This model uses Support Vector Machine Classifier (SVMC) to classify correctly the training data patterns into two groups; i. e., + 1 and - 1, thereby producing accurate and correct results. The proposed model works efficiently and effectively with great performance and high - accuracy results.

* Volume 2, Number 11, pp. 115 - 121, November, 2011 
* 7 Pages, 3 Figures, 2 Tables, International Journal of Advanced Computer Science and Applications(IJACSA) 
Access Paper or Ask Questions

Co-training for Demographic Classification Using Deep Learning from Label Proportions

Sep 13, 2017
Ehsan Mohammady Ardehaly, Aron Culotta

Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we introduce a deep neural network for the Learning from Label Proportion (LLP) setting, in which the training data consist of bags of unlabeled instances with associated label distributions for each bag. We introduce a new regularization layer, Batch Averager, that can be appended to the last layer of any deep neural network to convert it from supervised learning to LLP. This layer can be implemented readily with existing deep learning packages. To further support domains in which the data consist of two conditionally independent feature views (e.g. image and text), we propose a co-training algorithm that iteratively generates pseudo bags and refits the deep LLP model to improve classification accuracy. We demonstrate our models on demographic attribute classification (gender and race/ethnicity), which has many applications in social media analysis, public health, and marketing. We conduct experiments to predict demographics of Twitter users based on their tweets and profile image, without requiring any user-level annotations for training. We find that the deep LLP approach outperforms baselines for both text and image features separately. Additionally, we find that co-training algorithm improves image and text classification by 4% and 8% absolute F1, respectively. Finally, an ensemble of text and image classifiers further improves the absolute F1 measure by 4% on average.

Access Paper or Ask Questions

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

Sep 08, 2020
Devendra Singh Sachan, Manzil Zaheer, Ruslan Salakhutdinov

In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semi-supervised approaches. Several prior works have suggested that either complex pretraining schemes using unsupervised methods such as language modeling (Dai and Le 2015; Miyato, Dai, and Goodfellow 2016) or complicated models (Johnson and Zhang 2017) are necessary to achieve a high classification accuracy. However, we develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results compared with more complex approaches. Furthermore, in addition to cross-entropy loss, by using a combination of entropy minimization, adversarial, and virtual adversarial losses for both labeled and unlabeled data, we report state-of-the-art results for text classification task on several benchmark datasets. In particular, on the ACL-IMDB sentiment analysis and AG-News topic classification datasets, our method outperforms current approaches by a substantial margin. We also show the generality of the mixed objective function by improving the performance on relation extraction task.

* Published at AAAI 2019 
Access Paper or Ask Questions

Semantic Term "Blurring" and Stochastic "Barcoding" for Improved Unsupervised Text Classification

Nov 06, 2018
Robert Frank Martorano III

The abundance of text data being produced in the modern age makes it increasingly important to intuitively group, categorize, or classify text data by theme for efficient retrieval and search. Yet, the high dimensionality and imprecision of text data, or more generally language as a whole, prove to be challenging when attempting to perform unsupervised document clustering. In this thesis, we present two novel methods for improving unsupervised document clustering/classification by theme. The first is to improve document representations. We look to exploit "term neighborhoods" and "blur" semantic weight across neighboring terms. These neighborhoods are located in the semantic space afforded by "word embeddings." The second method is for cluster revision, based on what we deem as "stochastic barcoding", or "S- Barcode" patterns. Text data is inherently high dimensional, yet clustering typically takes place in a low dimensional representation space. Our method utilizes lower dimension clustering results as initial cluster configurations, and iteratively revises the configuration in the high dimensional space. We show with experimental results how both of the two methods improve the quality of document clustering. While this thesis elaborates on the two new conceptual contributions, a joint thesis by David Yan details the feature transformation and software architecture we developed for unsupervised document classification.

Access Paper or Ask Questions