Emotions are Universal: Learning Sentiment Based Representations of Resource-Poor Languages using Siamese Networks

04/03/2018
by   Nurendra Choudhary, et al.
0

Machine learning approaches in sentiment analysis principally rely on the abundance of resources. To limit this dependence, we propose a novel method called Siamese Network Architecture for Sentiment Analysis (SNASA) to learn representations of resource-poor languages by jointly training them with resource-rich languages using a siamese network. SNASA model consists of twin Bi-directional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM RNN) with shared parameters joined by a contrastive loss function, based on a similarity metric. The model learns the sentence representations of resource-poor and resource-rich language in a common sentiment space by using a similarity metric based on their individual sentiments. The model, hence, projects sentences with similar sentiment closer to each other and the sentences with different sentiment farther from each other. Experiments on large-scale datasets of resource-rich languages - English and Spanish and resource-poor languages - Hindi and Telugu reveal that SNASA outperforms the state-of-the-art sentiment analysis approaches based on distributional semantics, semantic rules, lexicon lists and deep neural network representations without sh

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/03/2018

Contrastive Learning of Emoji-based Representations for Resource-Poor Languages

The introduction of emojis (or emoticons) in social media platforms has ...
research
06/10/2018

Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages

Neural network models have shown promising results for text classificati...
research
04/03/2018

Sentiment Analysis of Code-Mixed Languages leveraging Resource Rich Languages

Code-mixed data is an important challenge of natural language processing...
research
06/08/2018

Multilingual Sentiment Analysis: An RNN-Based Framework for Limited Data

Sentiment analysis is a widely studied NLP task where the goal is to det...
research
04/18/2021

Chinese Sentences Similarity via Cross-Attention Based Siamese Network

Measuring sentence similarity is a key research area nowadays as it allo...
research
04/21/2019

UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages

In this paper, we introduce UniSent a universal sentiment lexica for 100...
research
06/06/2016

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

In recent years deep neural networks have achieved great success in sent...

Please sign up or login with your details

Forgot password? Click here to reset