335 citations · 409 across the 20 of their papers we have counts for
23 papers
Reimagining Dance: Real-time Music Co-creation between Dancers and AI
Olga Vechtomova, Jeff Bos
Dance performance traditionally follows a unidirectional relationship where movement responds to music. While AI has advanced in various creative domains, its application in dance…
Computational Modeling of Artistic Inspiration: A Framework for Predicting Aesthetic Preferences in Lyrical Lines Using Linguistic and Stylistic Features
Gaurav Sahu, Olga Vechtomova
Artistic inspiration remains one of the least understood aspects of the creative process. It plays a crucial role in producing works that resonate deeply with audiences, but the co…
Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization
Gaurav Sahu, Olga Vechtomova, Issam H. Laradji
Semi-supervised learning (SSL) is a widely used technique in scenarios where labeled data is scarce and unlabeled data is abundant. While SSL is popular for image and text classifi…
PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation
Gaurav Sahu, Olga Vechtomova, Dzmitry Bahdanau +1
Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training data. Recent work often tackles this problem u…
Future Sight: Dynamic Story Generation with Large Pretrained Language Models
Brian D. Zimmerman, Gaurav Sahu, Olga Vechtomova
Recent advances in deep learning research, such as transformers, have bolstered the ability for automated agents to generate creative texts similar to those that a human would writ…
LyricJam Sonic: A Generative System for Real-Time Composition and Musical Improvisation
Olga Vechtomova, Gaurav Sahu
Electronic music artists and sound designers have unique workflow practices that necessitate specialized approaches for developing music information retrieval and creativity suppor…
LyricJam: A system for generating lyrics for live instrumental music
Olga Vechtomova, Gaurav Sahu, Dhruv Kumar
We describe a real-time system that receives a live audio stream from a jam session and generates lyric lines that are congruent with the live music being played. Two novel approac…
Towards A Multi-agent System for Online Hate Speech Detection
Gaurav Sahu, Robin Cohen, Olga Vechtomova
This paper envisions a multi-agent system for detecting the presence of hate speech in online social media platforms such as Twitter and Facebook. We introduce a novel framework em…
Deep Learning for Text Style Transfer: A Survey
Di Jin, Zhijing Jin, Zhiting Hu +2
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and man…
Generation of lyrics lines conditioned on music audio clips
Olga Vechtomova, Gaurav Sahu, Dhruv Kumar
We present a system for generating novel lyrics lines conditioned on music audio. A bimodal neural network model learns to generate lines conditioned on any given short audio clip.…
Iterative Edit-Based Unsupervised Sentence Simplification
Dhruv Kumar, Lili Mou, Lukasz Golab +1
We present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning pres…
Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction
Raphael Schumann, Lili Mou, Yao Lu +2
Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. A good summary is characterized by language fluency and…
Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation
Vikash Balasubramanian, Ivan Kobyzev, Hareesh Bahuleyan +2
Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute label…
Stylized Text Generation Using Wasserstein Autoencoders with a Mixture of Gaussian Prior
Amirpasha Ghabussi, Lili Mou, Olga Vechtomova
Wasserstein autoencoders are effective for text generation. They do not however provide any control over the style and topic of the generated sentences if the dataset has multiple…
Adaptive Fusion Techniques for Multimodal Data
Gaurav Sahu, Olga Vechtomova
Effective fusion of data from multiple modalities, such as video, speech, and text, is challenging due to the heterogeneous nature of multimodal data. In this paper, we propose ada…
Adversarial Learning on the Latent Space for Diverse Dialog Generation
Kashif Khan, Gaurav Sahu, Vikash Balasubramanian +2
Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation but also being able to generate fluent sentences duri…
Generating Sentences from Disentangled Syntactic and Semantic Spaces
Yu Bao, Hao Zhou, Shujian Huang +5
Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous lat…
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
Raphael Tang, Yao Lu, Linqing Liu +3
In the natural language processing literature, neural networks are becoming increasingly deeper and complex. The recent poster child of this trend is the deep language representati…
Generating lyrics with variational autoencoder and multi-modal artist embeddings
Olga Vechtomova, Hareesh Bahuleyan, Amirpasha Ghabussi +1
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 th…
Disentangled Representation Learning for Non-Parallel Text Style Transfer
Vineet John, Lili Mou, Hareesh Bahuleyan +1
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 auxilia…
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation
Hareesh Bahuleyan, Lili Mou, Hao Zhou +1
The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the post…
Variational Attention for Sequence-to-Sequence Models
Hareesh Bahuleyan, Lili Mou, Olga Vechtomova +1
The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural…
Sentiment Analysis on Financial News Headlines using Training Dataset Augmentation
Vineet John, Olga Vechtomova
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 des…