no code implementations • 20 Dec 2018 • Olga Vechtomova, Hareesh Bahuleyan, Amirpasha Ghabussi, Vineet John
We present a system for generating song lyrics lines conditioned on the style of a specified artist.
3 code implementations • ACL 2019 • Vineet John, Lili Mou, Hareesh Bahuleyan, Olga Vechtomova
This paper tackles the problem of disentangling the latent variables of style and content in language models.
no code implementations • WS 2017 • Vineet John, Olga Vechtomova
This paper describes the UWaterloo affect prediction system developed for EmoInt-2017.
1 code implementation • SEMEVAL 2017 • Vineet John, Olga Vechtomova
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.
1 code implementation • 29 Jul 2017 • Vineet John, Olga Vechtomova
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.
no code implementations • 27 Apr 2017 • Vineet John
This paper aims to catalyze the discussions about text feature extraction techniques using neural network architectures.
no code implementations • 23 Mar 2017 • Vineet John
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.