• Publications
  • Influence
Generating Sentences from a Continuous Space
TLDR
This work introduces and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences that allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Expand
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
TLDR
A new algorithm MINERVA is proposed, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity, and significantly outperforms prior methods. Expand
Adding Gradient Noise Improves Learning for Very Deep Networks
TLDR
This paper explores the low-overhead and easy-to-implement optimization technique of adding annealed Gaussian noise to the gradient, which it is found surprisingly effective when training these very deep architectures. Expand
Word Representations via Gaussian Embedding
TLDR
This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions, and investigates the ability of these embedDings to model entailment and other asymmetric relationships, and explores novel properties of the representation. Expand
Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking
TLDR
New methods using real and complex bilinear mappings for integrating hierarchical information are presented, yielding substantial improvement over flat predictions in entity linking and fine-grained entity typing, and achieving new state-of-the-art results for end-to-end models on the benchmark FIGER dataset. Expand
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
TLDR
Distributional inclusion vector embedding (DIVE) is introduced, a simple-to-implement unsupervised method of hypernym discovery via per-word non-negative vector embeddings which preserve the inclusion property of word contexts. Expand
Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures
TLDR
It is shown that a broad class of models that assign probability measures to OE can never capture negative correlation, which motivates the construction of a novel box lattice and accompanying probability measure to capture anticorrelation and even disjoint concepts. Expand
Dynamic Knowledge-Base Alignment for Coreference Resolution
TLDR
This approach performs joint inference between within-document coreference and entity linking, maintaining ranked lists of candidate entities that are dynamically merged and reranked during inference. Expand
Bethe Projections for Non-Local Inference
TLDR
This work presents a method to discriminatively learn broad families of inference objectives, capturing powerful non-local statistics of the latent variables, while maintaining tractable and provably fast inference using non-Euclidean projected gradient descent with a distance-generating function given by the Bethe entropy. Expand
...
1
2
3
...