arXiv subjects

Vineet John

Publications and source records attributed to Vineet John.

7 recordsLinked to original sources

arXiv2018

Generating lyrics with variational autoencoder and multi-modal artist embeddings

We present a system for generating song lyrics lines conditioned on the style of a specified artist. The system uses a variational autoencoder with artist embeddings. We propose the pre-training of artist embeddings with the representations learned by a CNN classifier, which is trained to predict artists based on MEL spectrograms of their song clips. This work is the first step towards combining audio and text modalities of songs for generating lyrics conditioned on the artist's style. Our preliminary results suggest that there is a benefit in initializing artists' embeddings with the representations learned by a spectrogram classifier.

cs.CL↗

arXiv2018

Disentangled Representation Learning for Non-Parallel Text Style Transfer

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label prediction and bag-of-words prediction, respectively. We show, both qualitatively and quantitatively, that the style and content are indeed disentangled in the latent space. This disentangled latent representation learning method is applied to style transfer on non-parallel corpora. We achieve substantially better results in terms of transfer accuracy, content preservation and language fluency, in comparison to previous state-of-the-art approaches.

cs.CL↗

arXiv2017

Sentiment Analysis on Financial News Headlines using Training Dataset Augmentation

This paper discusses the approach taken by the UWaterloo team to arrive at a solution for the Fine-Grained Sentiment Analysis problem posed by Task 5 of SemEval 2017. The paper describes the document vectorization and sentiment score prediction techniques used, as well as the design and implementation decisions taken while building the system for this task. The system uses text vectorization models, such as N-gram, TF-IDF and paragraph embeddings, coupled with regression model variants to predict the sentiment scores. Amongst the methods examined, unigrams and bigrams coupled with simple linear regression obtained the best baseline accuracy. The paper also explores data augmentation methods to supplement the training dataset. This system was designed for Subtask 2 (News Statements and Headlines).

cs.CL↗

arXiv2017

A Survey of Neural Network Techniques for Feature Extraction from Text

This paper aims to catalyze the discussions about text feature extraction techniques using neural network architectures. The research questions discussed in the paper focus on the state-of-the-art neural network techniques that have proven to be useful tools for language processing, language generation, text classification and other computational linguistics tasks.

cs.CL↗

arXiv2017

A Survey of Distributed Message Broker Queues

This paper surveys the message brokers that are in vogue today for distributed communication. Their primary goal is to facilitate the construction of decentralized topologies without single points of failure, enabling fault tolerance and high availability. These characteristics make them optimal for usage within distributed architectures. However, there are multiple protocols built to achieve this, and it would be beneficial to have a empirical comparison between their features and performance to determine their real-world applicability. This paper focuses on two popular protocols (Kafka and AMQP) and explores the divergence in their features as well as their performance under varied testing workloads.

cs.DC↗

arXiv2017

Rapid-Rate: A Framework for Semi-supervised Real-time Sentiment Trend Detection in Unstructured Big Data

Commercial establishments like restaurants, service centres and retailers have several sources of customer feedback about products and services, most of which need not be as structured as rated reviews provided by services like Yelp, or Amazon, in terms of sentiment conveyed. For instance, Amazon provides a fine-grained score on a numeric scale for product reviews. Some sources, however, like social media (Twitter, Facebook), mailing lists (Google Groups) and forums (Quora) contain text data that is much more voluminous, but unstructured and unlabelled. It might be in the best interests of a business establishment to assess the general sentiment towards their brand on these platforms as well. This text could be pipelined into a system with a built-in prediction model, with the objective of generating real-time graphs on opinion and sentiment trends. Although such tasks like the one described about have been explored with respect to document classification problems in the past, the implementation described in this paper, by virtue of learning a continuous function rather than a discrete one, offers a lot more depth of insight as compared to document classification approaches. This study aims to explore the validity of such a continuous function predicting model to quantify sentiment about an entity, without the additional overhead of manual labelling, and computational preprocessing & feature extraction. This research project also aims to design and implement a re-usable document regression pipeline as a framework, Rapid-Rate, that can be used to predict document scores in real-time.

cs.CL↗

arXiv2017

Redynis: Traffic-aware dynamic repartitioning for a distributed key-value store

Most modern data stores tend to be distributed, to enable the scaling of the data across multiple instances of commodity hardware. Although this ensures a near unlimited potential for storage, the data itself is not always ideally partitioned, and the cost of a network round-trip may cause a degradation of end-user experience with respect to response latency. The problem being solved is bringing the data objects closer to the frequent sources of requests using a dynamic repartitioning algorithm. This is important if the objective is to mitigate the overhead of network latency, and especially so if the partitions are widely geo-distributed. The intention is to bring these features to an existing distributed key-value store product, Redis.

cs.DB↗