Search Results for author:
Found 11 papers, 3 papers with code
Harnessing Code Switching to Transcend the Linguistic Barrier
Code mixing (or code switching) is a common phenomenon observed in social-media content generated by a linguistically diverse user-base.
Voice for the Voiceless: Active Sampling to Detect Comments Supporting the Rohingyas
The Rohingya refugee crisis is one of the biggest humanitarian crises of modern times with more than 600, 000 Rohingyas rendered homeless according to the United Nations High Commissioner for Refugees.
Hope Speech Detection: A Computational Analysis of the Voice of Peace
The recent Pulwama terror attack (February 14, 2019, Pulwama, Kashmir) triggered a chain of escalating events between India and Pakistan adding another episode to their 70-year-old dispute over Kashmir.
A Little Annotation does a Lot of Good: A Study in Bootstrapping Low-resource Named Entity Recognizers
Most state-of-the-art models for named entity recognition (NER) rely on the availability of large amounts of labeled data, making them challenging to extend to new, lower-resourced languages.
CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology
This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context.
Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization
Motivated by our sales prediction problem, we propose a factor-based algorithm that is able to take time into account.
Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging.
The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks
Via an extensive empirical study, we show that the NLC is a powerful predictor of test error and that attaining a right-sized NLC is essential for optimal performance.
Gradients explode - Deep Networks are shallow - ResNet explained
Whereas it is believed that techniques such as Adam, batch normalization and, more recently, SeLU nonlinearities ``solve'' the exploding gradient problem, we show that this is not the case and that in a range of popular MLP architectures, exploding gradients exist and that they limit the depth to which networks can be effectively trained, both in theory and in practice.
The exploding gradient problem demystified - definition, prevalence, impact, origin, tradeoffs, and solutions
Whereas it is believed that techniques such as Adam, batch normalization and, more recently, SeLU nonlinearities "solve" the exploding gradient problem, we show that this is not the case in general and that in a range of popular MLP architectures, exploding gradients exist and that they limit the depth to which networks can be effectively trained, both in theory and in practice.
Nonparametric Neural Networks
Automatically determining the optimal size of a neural network for a given task without prior information currently requires an expensive global search and training many networks from scratch.
