Luke Vilnis

Generating Sentences from a Continuous Space

2016

The standard recurrent neural network language model (rnnlm) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an rnn-based variational …

Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

2017 · arXiv (Cornell University)

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new …

Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking

2018

Extraction from raw text to a knowledge base of entities and fine-grained types is often cast as prediction into a flat set of entity and type labels, neglecting the rich hierarchies over types and entities …

Word Representations via Gaussian Embedding

2015 · arXiv (Cornell University)

Abstract: Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation and its …