Piyush Rai

Small-Variance Asymptotics for Nonparametric Bayesian Overlapping\n Stochastic Blockmodels

2018 · arXiv (Cornell University)

The latent feature relational model (LFRM) is a generative model for\ngraph-structured data to learn a binary vector representation for each node in\nthe graph. The binary vector denotes the node's membership in one or more\ncommunities. At …

A Deep Generative Framework for Paraphrase Generation

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed …

Distributional Semantics Meets Multi-Label Learning

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a label embedding based approach to large-scale multi-label learning, drawing inspiration from ideas rooted in distributional semantics, specifically the Skip Gram Negative Sampling (SGNS) approach, widely used to learn word embeddings. Besides leading …

A Deep Generative Framework for Paraphrase Generation

2017 · arXiv (Cornell University)

Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed …