Pararth Shah

Learn More
We present Ringo, a system for analysis of large graphs. Graphs provide a way to represent and analyze systems of interacting objects (people, proteins, webpages) with edges between the objects denoting interactions (friendships, physical interactions, links). Mining graphs provides valuable insights about individual objects as well as the relationships(More)
We present an approach and a system for collective disambiguation of entity mentions occurring in natural language text. Given an input text, the system spots mentions and their candidate entities. Candidate entities across all mentions are jointly modeled as binary nodes in a Markov Random Field. Their edges correspond to the joint signal between pairs of(More)
In this work, we will investigate the task of building a Question Answering system using deep neural networks augmented with a memory component. Our goal is to implement the MemNN and its extensions described in [10] and [8] and apply it on the bAbI QA tasks introduced in [9]. Unlike simulated datasets like bAbI, the vanilla MemNN system is not sufficient(More)
Recently Kulkarni et al. [20] proposed an approach for collective disambiguation of entity mentions occurring in natural language text. Their model achieves disambiguation by efficiently computing exact MAP inference in a binary labeled Markov Random Field. Here, we build on their disambiguation model and propose an approach to jointly learn the node and(More)
The diversity of content on the web has exploded exponentially , while our vocabulary to parse it remains at a relative plateau. It is increasingly difficult for search engines to understand what the user really wants by considering only the query terms [1]. For instance, a wildlife photographer searching for " jaguar " is probably looking for information(More)
  • 1