Nitish Gupta

We present a neural, modular entity linking system that learns a unified dense representation for each entity using multiple sources of information, such as its description, contexts around its mentions, and its fine-grained types. Expand

We propose XELMS (XEL with Multilingual Supervision) (§2), the first XEL approach that combines supervision from multiple languages jointly. Expand

Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Expand

We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. Expand

In this paper, we present a generic approach to factorization of relational data that collectively models all the relations in the database. Expand

We introduce an end-to-end differentiable model for interpreting questions about a knowledge graph (KG), which is inspired by formal approaches to semantics. Expand

We revisit the evaluation for CDEC, and discover that past works have adopted different, often inconsistent, evaluation settings, which either overlook certain mistakes in coreference decisions, or make assumptions that simplify the coreference task considerably. Expand

We address the problem of robustness of NER systems in data with noisy or uncertain casing, using a pretraining objective that predicts casing in text, or a truecaser, leveraging unlabeled data. Expand

We introduce the concept of module-wise faithfulness, a systematic evaluation of faithfulness in neural module networks (NMNs) for visual and textual reasoning. Expand

We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. Expand