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

Dual Projection Generative Adversarial Networks for Conditional Image Generation

Aug 20, 2021
Ligong Han, Martin Renqiang Min, Anastasis Stathopoulos, Yu Tian, Ruijiang Gao, Asim Kadav, Dimitris Metaxas

Conditional Generative Adversarial Networks (cGANs) extend the standard unconditional GAN framework to learning joint data-label distributions from samples, and have been established as powerful generative models capable of generating high-fidelity imagery. A challenge of training such a model lies in properly infusing class information into its generator and discriminator. For the discriminator, class conditioning can be achieved by either (1) directly incorporating labels as input or (2) involving labels in an auxiliary classification loss. In this paper, we show that the former directly aligns the class-conditioned fake-and-real data distributions $P(\text{image}|\text{class})$ ({\em data matching}), while the latter aligns data-conditioned class distributions $P(\text{class}|\text{image})$ ({\em label matching}). Although class separability does not directly translate to sample quality and becomes a burden if classification itself is intrinsically difficult, the discriminator cannot provide useful guidance for the generator if features of distinct classes are mapped to the same point and thus become inseparable. Motivated by this intuition, we propose a Dual Projection GAN (P2GAN) model that learns to balance between {\em data matching} and {\em label matching}. We then propose an improved cGAN model with Auxiliary Classification that directly aligns the fake and real conditionals $P(\text{class}|\text{image})$ by minimizing their $f$-divergence. Experiments on a synthetic Mixture of Gaussian (MoG) dataset and a variety of real-world datasets including CIFAR100, ImageNet, and VGGFace2 demonstrate the efficacy of our proposed models.

* Accepted at ICCV-21 
Access Paper or Ask Questions

Knowledge Guided Metric Learning for Few-Shot Text Classification

Apr 04, 2020
Dianbo Sui, Yubo Chen, Binjie Mao, Delai Qiu, Kang Liu, Jun Zhao

The training of deep-learning-based text classification models relies heavily on a huge amount of annotation data, which is difficult to obtain. When the labeled data is scarce, models tend to struggle to achieve satisfactory performance. However, human beings can distinguish new categories very efficiently with few examples. This is mainly due to the fact that human beings can leverage knowledge obtained from relevant tasks. Inspired by human intelligence, we propose to introduce external knowledge into few-shot learning to imitate human knowledge. A novel parameter generator network is investigated to this end, which is able to use the external knowledge to generate relation network parameters. Metrics can be transferred among tasks when equipped with these generated parameters, so that similar tasks use similar metrics while different tasks use different metrics. Through experiments, we demonstrate that our method outperforms the state-of-the-art few-shot text classification models.

Access Paper or Ask Questions

Establishing Baselines for Text Classification in Low-Resource Languages

May 05, 2020
Jan Christian Blaise Cruz, Charibeth Cheng

While transformer-based finetuning techniques have proven effective in tasks that involve low-resource, low-data environments, a lack of properly established baselines and benchmark datasets make it hard to compare different approaches that are aimed at tackling the low-resource setting. In this work, we provide three contributions. First, we introduce two previously unreleased datasets as benchmark datasets for text classification and low-resource multilabel text classification for the low-resource language Filipino. Second, we pretrain better BERT and DistilBERT models for use within the Filipino setting. Third, we introduce a simple degradation test that benchmarks a model's resistance to performance degradation as the number of training samples are reduced. We analyze our pretrained model's degradation speeds and look towards the use of this method for comparing models aimed at operating within the low-resource setting. We release all our models and datasets for the research community to use.

* We release all our models, finetuning code, and data at 
Access Paper or Ask Questions

Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information

May 26, 2022
Shijing Si, Jianzong Wang, Ruiyi Zhang, Qinliang Su, Jing Xiao

Non-negative matrix factorization (NMF) based topic modeling is widely used in natural language processing (NLP) to uncover hidden topics of short text documents. Usually, training a high-quality topic model requires large amount of textual data. In many real-world scenarios, customer textual data should be private and sensitive, precluding uploading to data centers. This paper proposes a Federated NMF (FedNMF) framework, which allows multiple clients to collaboratively train a high-quality NMF based topic model with locally stored data. However, standard federated learning will significantly undermine the performance of topic models in downstream tasks (e.g., text classification) when the data distribution over clients is heterogeneous. To alleviate this issue, we further propose FedNMF+MI, which simultaneously maximizes the mutual information (MI) between the count features of local texts and their topic weight vectors to mitigate the performance degradation. Experimental results show that our FedNMF+MI methods outperform Federated Latent Dirichlet Allocation (FedLDA) and the FedNMF without MI methods for short texts by a significant margin on both coherence score and classification F1 score.

* IJCNN 2022 
* 7 pages, 4 figures, accepted by IJCNN 2022 
Access Paper or Ask Questions

Cluster & Tune: Boost Cold Start Performance in Text Classification

Mar 20, 2022
Eyal Shnarch, Ariel Gera, Alon Halfon, Lena Dankin, Leshem Choshen, Ranit Aharonov, Noam Slonim

In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as BERT, for a target classification task, is prone to produce poor performance. We suggest a method to boost the performance of such models by adding an intermediate unsupervised classification task, between the pre-training and fine-tuning phases. As such an intermediate task, we perform clustering and train the pre-trained model on predicting the cluster labels. We test this hypothesis on various data sets, and show that this additional classification phase can significantly improve performance, mainly for topical classification tasks, when the number of labeled instances available for fine-tuning is only a couple of dozen to a few hundred.

* 9 pages, 6 figures; To be published in ACL 2022 
Access Paper or Ask Questions

EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

Jan 31, 2019
Jason W. Wei, Kai Zou

We present EDA: easy data augmentation techniques for boosting performance on text classification tasks. EDA consists of four simple but powerful operations: synonym replacement, random insertion, random swap, and random deletion. On five text classification tasks, we show that EDA improves performance for both convolutional and recurrent neural networks. EDA demonstrates particularly strong results for smaller datasets; on average, across five datasets, training with EDA while using only 50% of the available training set achieved the same accuracy as normal training with all available data. We also performed extensive ablation studies and suggest parameters for practical use.

Access Paper or Ask Questions

Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition

Sep 23, 2020
Bingcong Li, Xin Tang, Xianbiao Qi, Yihao Chen, Rong Xiao

Recently, inspired by Transformer, self-attention-based scene text recognition approaches have achieved outstanding performance. However, we find that the size of model expands rapidly with the lexicon increasing. Specifically, the number of parameters for softmax classification layer and output embedding layer are proportional to the vocabulary size. It hinders the development of a lightweight text recognition model especially applied for Chinese and multiple languages. Thus, we propose a lightweight scene text recognition model named Hamming OCR. In this model, a novel Hamming classifier, which adopts locality sensitive hashing (LSH) algorithm to encode each character, is proposed to replace the softmax regression and the generated LSH code is directly employed to replace the output embedding. We also present a simplified transformer decoder to reduce the number of parameters by removing the feed-forward network and using cross-layer parameter sharing technique. Compared with traditional methods, the number of parameters in both classification and embedding layers is independent on the size of vocabulary, which significantly reduces the storage requirement without loss of accuracy. Experimental results on several datasets, including four public benchmaks and a Chinese text dataset synthesized by SynthText with more than 20,000 characters, shows that Hamming OCR achieves competitive results.

* 9 Pages, 4 Figure 
Access Paper or Ask Questions

Joint Sentiment/Topic Modeling on Text Data Using Boosted Restricted Boltzmann Machine

Nov 10, 2017
Masoud Fatemi, Mehran Safayani

Recently by the development of the Internet and the Web, different types of social media such as web blogs become an immense source of text data. Through the processing of these data, it is possible to discover practical information about different topics, individuals opinions and a thorough understanding of the society. Therefore, applying models which can automatically extract the subjective information from the documents would be efficient and helpful. Topic modeling methods, also sentiment analysis are the most raised topics in the natural language processing and text mining fields. In this paper a new structure for joint sentiment-topic modeling based on Restricted Boltzmann Machine (RBM) which is a type of neural networks is proposed. By modifying the structure of RBM as well as appending a layer which is analogous to sentiment of text data to it, we propose a generative structure for joint sentiment topic modeling based on neutral networks. The proposed method is supervised and trained by the Contrastive Divergence algorithm. The new attached layer in the proposed model is a layer with the multinomial probability distribution which can be used in text data sentiment classification or any other supervised application. The proposed model is compared with existing models in the experiments such as evaluating as a generative model, sentiment classification, information retrieval and the corresponding results demonstrate the efficiency of the method.

Access Paper or Ask Questions

Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification

Sep 26, 2019
Jianming Zheng, Fei Cai, Honghui Chen, Maarten de Rijke

Text representation can aid machines in understanding text. Previous work on text representation often focuses on the so-called forward implication, i.e., preceding words are taken as the context of later words for creating representations, thus ignoring the fact that the semantics of a text segment is a product of the mutual implication of words in the text: later words contribute to the meaning of preceding words. We introduce the concept of interaction and propose a two-perspective interaction representation, that encapsulates a local and a global interaction representation. Here, a local interaction representation is one that interacts among words with parent-children relationships on the syntactic trees and a global interaction interpretation is one that interacts among all the words in a sentence. We combine the two interaction representations to develop a Hybrid Interaction Representation (HIR). Inspired by existing feature-based and fine-tuning-based pretrain-finetuning approaches to language models, we integrate the advantages of feature-based and fine-tuning-based methods to propose the Pre-train, Interact, Fine-tune (PIF) architecture. We evaluate our proposed models on five widely-used datasets for text classification tasks. Our ensemble method, outperforms state-of-the-art baselines with improvements ranging from 2.03% to 3.15% in terms of error rate. In addition, we find that, the improvements of PIF against most state-of-the-art methods is not affected by increasing of the length of the text.

* 32 pages, 5 figures 
Access Paper or Ask Questions

Training with reduced precision of a support vector machine model for text classification

Jul 17, 2020
Dominik Żurek, Marcin Pietroń

This paper presents the impact of using quantization on the efficiency of multi-class text classification in the training process of a support vector machine (SVM). This work is focused on comparing the efficiency of SVM model trained using reduced precision with its original form. The main advantage of using quantization is decrease in computation time and in memory footprint on the dedicated hardware platform which supports low precision computation like GPU (16-bit) or FPGA (any bit-width). The paper presents the impact of a precision reduction of the SVM training process on text classification accuracy. The implementation of the CPU was performed using the OpenMP library. Additionally, the results of the implementation of the GPU using double, single and half precision are presented.

Access Paper or Ask Questions