Curriculum Learning Strategies for Hindi-English Code-Mixed Sentiment Analysis
Anirudh Dahiya,Neeraj Battan,Manish Shrivastava,Dipti Mishra Sharma +3 more
- pp 177-189
Reads0
Chats0
TLDR
This work introduces curriculum learning strategies for semantic tasks in code-mixed Hindi-English (Hi-En) texts, and investigates various training strategies for enhancing model performance.Abstract:
Sentiment Analysis and other semantic tasks are commonly used for social media textual analysis to gauge public opinion and make sense from the noise on social media. The language used on social media not only commonly diverges from the formal language, but is compounded by code-mixing between languages, especially in large multilingual societies like India.read more
Citations
More filters
Journal ArticleDOI
KL-NF technique for sentiment classification
Kanika Garg,D. K. Lobiyal +1 more
TL;DR: The authors proposed a novel approach for calculating feature values using Kullback-Leibler (KL) divergence method for sentiment analysis for low-resource languages like Hindi using Neuro-Fuzzy Technique.
Proceedings ArticleDOI
Effective Distributed Representation of Code-Mixed Text
Aditya Malte,Sheetal S. Sonawane +1 more
TL;DR: A large scale code-mixed corpus is generated that would aid in further research of code mixed text on social media and machine learning models that improve upon the previous state-of-the-art using a much lighter and explainable architecture are trained.
Proceedings Article
Homophobia, Transphobia Detection in Tamil, Malayalam, English Languages using Logistic Regression and Code-Mixed Data using AWD-LSTM
TL;DR: In this article , the authors proposed the AWD-LSTM model for the code-mixed(Tamil-English) language data set and Logistic Regression for Tamil, Malayalam, and English languages.
References
More filters
Proceedings ArticleDOI
Neural Machine Translation of Rare Words with Subword Units
TL;DR: This paper introduces a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units, and empirically shows that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English-German and English-Russian by 1.3 BLEU.
Posted Content
How transferable are features in deep neural networks
TL;DR: This paper quantifies the generality versus specificity of neurons in each layer of a deep convolutional neural network and reports a few surprising results, including that initializing a network with transferred features from almost any number of layers can produce a boost to generalization that lingers even after fine-tuning to the target dataset.
Proceedings ArticleDOI
Curriculum learning
TL;DR: It is hypothesized that curriculum learning has both an effect on the speed of convergence of the training process to a minimum and on the quality of the local minima obtained: curriculum learning can be seen as a particular form of continuation method (a general strategy for global optimization of non-convex functions).
Proceedings Article
Semantic Compositionality through Recursive Matrix-Vector Spaces
TL;DR: A recursive neural network model that learns compositional vector representations for phrases and sentences of arbitrary syntactic type and length and can learn the meaning of operators in propositional logic and natural language is introduced.
Book
Bilingual Speech: A Typology of Code-Mixing
TL;DR: The study of code-mixing revealed differences and similarities between languages, as well asVariation in mixing patterns, which led to bilingual speech and language contact.