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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Sentiment": models, code, and papers

Dual Adversarial Co-Learning for Multi-Domain Text Classification

Sep 18, 2019
Yuan Wu, Yuhong Guo

In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance.

  Access Paper or Ask Questions

Learning to Repair Software Vulnerabilities with Generative Adversarial Networks

Oct 28, 2018
Jacob Harer, Onur Ozdemir, Tomo Lazovich, Christopher P. Reale, Rebecca L. Russell, Louis Y. Kim, Peter Chin

Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial learning approach is an effective technique for repairing software vulnerabilities, performing close to seq2seq approaches that require labeled pairs. The proposed Generative Adversarial Network approach is application-agnostic in that it can be applied to other problems similar to code repair, such as grammar correction or sentiment translation.

* Presented at 32nd Conference on Neural Information Processing Systems (nips 2018), Montreal Canada 

  Access Paper or Ask Questions

Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding

Nov 01, 2015
Rie Johnson, Tong Zhang

This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from unlabeled data for integration into a supervised CNN. The proposed scheme for embedding learning is based on the idea of two-view semi-supervised learning, which is intended to be useful for the task of interest even though the training is done on unlabeled data. Our models achieve better results than previous approaches on sentiment classification and topic classification tasks.

* v1 has a different title, and the results there are obsolete. The current version is to appear in NIPS 2015 

  Access Paper or Ask Questions

Minimally Supervised Learning of Affective Events Using Discourse Relations

Sep 02, 2019
Jun Saito, Yugo Murawaki, Sadao Kurohashi

Recognizing affective events that trigger positive or negative sentiment has a wide range of natural language processing applications but remains a challenging problem mainly because the polarity of an event is not necessarily predictable from its constituent words. In this paper, we propose to propagate affective polarity using discourse relations. Our method is simple and only requires a very small seed lexicon and a large raw corpus. Our experiments using Japanese data show that our method learns affective events effectively without manually labeled data. It also improves supervised learning results when labeled data are small.

* 8 pages, 1 figure, EMNLP2019 

  Access Paper or Ask Questions

Twitter Dataset for 2022 Russo-Ukrainian Crisis

Mar 06, 2022
Ehsan-Ul Haq, Gareth Tyson, Lik-Hang Lee, Tristan Braud, Pan Hui

Online Social Networks (OSNs) play a significant role in information sharing during a crisis. The data collected during such a crisis can reflect the large scale public opinions and sentiment. In addition, OSN data can also be used to study different campaigns that are employed by various entities to engineer public opinions. Such information sharing campaigns can range from spreading factual information to propaganda and misinformation. We provide a Twitter dataset of the 2022 Russo-Ukrainian conflict. In the first release, we share over 1.6 million tweets shared during the 1st week of the crisis.

  Access Paper or Ask Questions

Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming

Jun 24, 2019
Caio Corro, Ivan Titov

We treat projective dependency trees as latent variables in our probabilistic model and induce them in such a way as to be beneficial for a downstream task, without relying on any direct tree supervision. Our approach relies on Gumbel perturbations and differentiable dynamic programming. Unlike previous approaches to latent tree learning, we stochastically sample global structures and our parser is fully differentiable. We illustrate its effectiveness on sentiment analysis and natural language inference tasks. We also study its properties on a synthetic structure induction task. Ablation studies emphasize the importance of both stochasticity and constraining latent structures to be projective trees.

* Accepted at ACL 2019 

  Access Paper or Ask Questions

Do Convolutional Networks need to be Deep for Text Classification ?

Jul 13, 2017
Hoa T. Le, Christophe Cerisara, Alexandre Denis

We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered. We show on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters. However, a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs. Our shallow word model further establishes new state-of-the-art performances on two datasets: Yelp Binary (95.9\%) and Yelp Full (64.9\%).

  Access Paper or Ask Questions

SetConv: A New Approach for Learning from Imbalanced Data

Apr 03, 2021
Yang Gao, Yi-Fan Li, Yu Lin, Charu Aggarwal, Latifur Khan

For many real-world classification problems, e.g., sentiment classification, most existing machine learning methods are biased towards the majority class when the Imbalance Ratio (IR) is high. To address this problem, we propose a set convolution (SetConv) operation and an episodic training strategy to extract a single representative for each class, so that classifiers can later be trained on a balanced class distribution. We prove that our proposed algorithm is permutation-invariant despite the order of inputs, and experiments on multiple large-scale benchmark text datasets show the superiority of our proposed framework when compared to other SOTA methods.

* Accepted by EMNLP 2020 (11 pages, 9 figures) 

  Access Paper or Ask Questions

NUAA-QMUL at SemEval-2020 Task 8: Utilizing BERT and DenseNet for Internet Meme Emotion Analysis

Nov 09, 2020
Xiaoyu Guo, Jing Ma, Arkaitz Zubiaga

This paper describes our contribution to SemEval 2020 Task 8: Memotion Analysis. Our system learns multi-modal embeddings from text and images in order to classify Internet memes by sentiment. Our model learns text embeddings using BERT and extracts features from images with DenseNet, subsequently combining both features through concatenation. We also compare our results with those produced by DenseNet, ResNet, BERT, and BERT-ResNet. Our results show that image classification models have the potential to help classifying memes, with DenseNet outperforming ResNet. Adding text features is however not always helpful for Memotion Analysis.

  Access Paper or Ask Questions