• Publications
  • Influence
DeepWalk: online learning of social representations
TLDR
We present DeepWalk, a novel approach for learning latent representations of vertices in a network. Expand
  • 3,989
  • 1152
  • PDF
Theano: A Python framework for fast computation of mathematical expressions
TLDR
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Expand
  • 1,893
  • 141
  • PDF
Polyglot: Distributed Word Representations for Multilingual NLP
TLDR
We train word embeddings for more than 100 languages using Wikipedias using state-of-the-art techniques. Expand
  • 405
  • 47
  • PDF
Statistically Significant Detection of Linguistic Change
TLDR
We propose a new computational approach for tracking and detecting statistically significant linguistic shifts in the meaning and usage of words. Expand
  • 280
  • 43
  • PDF
Character-Level Language Modeling with Deeper Self-Attention
TLDR
In this paper, we show that a deep (64-layer) transformer model with fixed context outperforms RNN variants by a large margin, achieving state of the art on two popular benchmarks. Expand
  • 128
  • 17
  • PDF
Watch Your Step: Learning Node Embeddings via Graph Attention
TLDR
We propose a novel attention model on the power series of the transition matrix, which guides the random walk to optimize an upstream objective. Expand
  • 73
  • 11
  • PDF
POLYGLOT-NER: Massive Multilingual Named Entity Recognition
TLDR
We describe a system that builds Named Entity Recognition (NER) annotators for 40 major languages using Wikipedia and Freebase. Expand
  • 104
  • 10
  • PDF
Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
TLDR
We investigate the task of modeling open-domain, multi-turn, unstructured, multiparticipant, conversational dialogue. Expand
  • 52
  • 8
  • PDF
Efficient Natural Language Response Suggestion for Smart Reply
TLDR
This paper presents a computationally efficient machine-learned method for natural language response suggestion. Expand
  • 80
  • 7
  • PDF
Learning Edge Representations via Low-Rank Asymmetric Projections
TLDR
We propose a new method for embedding graphs while preserving directed edge information. Expand
  • 43
  • 5
  • PDF