K. Stevens

Publications24
h-index9
Citations3,875
Highly Influential Citations310
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • B. Strope
  • 53 Publications, 2,104 Citations
  • Yun-Hsuan Sung
  • 22 Publications, 1,128 Citations
  • R. Kurzweil
  • 54 Publications, 1,484 Citations
  • Yinfei Yang
  • 43 Publications, 1,444 Citations
  • Publications
  • Influence
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
TLDR
Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Expand
  • 3,297
  • 268
  • PDF
Exploring Topic Coherence over Many Models and Many Topics
TLDR
We apply two new automated semantic evaluations to three distinct latent topic models to evaluate their coherence metrics. Expand
  • 241
  • 17
  • PDF
The S-Space Package: An Open Source Package for Word Space Models
TLDR
We present the S-Space Package, an open source framework for developing and evaluating word space algorithms. Expand
  • 125
  • 8
  • PDF
Event Detection in Blogs using Temporal Random Indexing
TLDR
We propose a new algorithm that makes use of a temporally-annotated semantic space for tracking how words change semantics. Expand
  • 41
  • 7
  • PDF
Distillate water quality of a single-basin solar still: laboratory and field studies
Abstract Solar water distillation has long been used to provide potable water in locations where the quality of the local water is poor, especially in remote areas where other treatment options are… Expand
  • 79
  • 5
Effective Parallel Corpus Mining using Bilingual Sentence Embeddings
TLDR
We propose a novel method for training bilingual sentence embeddings that proves useful for parallel corpus mining of parallel data. Expand
  • 47
  • 3
  • PDF
Hierarchical Document Encoder for Parallel Corpus Mining
TLDR
We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Expand
  • 9
  • 1
  • PDF
Measuring the Impact of Sense Similarity on Word Sense Induction
TLDR
We present a new WSI evaluation that quantifies the relationship between the relatedness of a word's senses and the ability of a WSI algorithm to distinguish between them. Expand
  • 10
  • 1
  • PDF
HERMIT: Flexible Clustering for the SemEval-2 WSI Task
TLDR
We propose a new method for identifying the different senses that uses a flexible clustering strategy to automatically determine the number of senses, rather than predefining it. Expand
  • 15
  • PDF
VALGANCICLOVIR-ASSOCIATED NEUTROPENIA IN LUNG TRANSPLANT RECIPIENTS
  • 2