Collective Entity Resolution with Multi-Focal Attention

no code implementations • ACL 2016 • Amir Globerson, Nevena Lazic, Soumen Chakrabarti, Amarnag Subramanya, Michael Ringgaard, Fern Pereira, o

Entity Resolution Topic Models

Multilingual Language Processing From Bytes

no code implementations • NAACL 2016 • Dan Gillick, Cliff Brunk, Oriol Vinyals, Amarnag Subramanya

We describe an LSTM-based model which we call Byte-to-Span (BTS) that reads text as bytes and outputs span annotations of the form [start, length, label] where start positions, lengths, and labels are separate entries in our vocabulary.

named-entity-recognition Named Entity Recognition +2

Plato: A Selective Context Model for Entity Resolution

no code implementations • TACL 2015 • Nevena Lazic, Amarnag Subramanya, Michael Ringgaard, Fern Pereira, o

We present Plato, a probabilistic model for entity resolution that includes a novel approach for handling noisy or uninformative features, and supplements labeled training data derived from Wikipedia with a very large unlabeled text corpus.

Entity Linking Entity Resolution

Reading The Web with Learned Syntactic-Semantic Inference Rules

no code implementations • EMNLP 2012 • Ni Lao, Amarnag Subramanya, Fern Pereira, o, William W. Cohen

Link Prediction Relational Reasoning +1

Entropic Graph Regularization in Non-Parametric Semi-Supervised Classification

no code implementations • NeurIPS 2009 • Amarnag Subramanya, Jeff A. Bilmes

We prove certain theoretical properties of a graph-regularized transductive learning objective that is based on minimizing a Kullback-Leibler divergence based loss.

Classification General Classification +1