• Publications
  • Influence
Does String-Based Neural MT Learn Source Syntax?
We investigate whether a neural, encoderdecoder translation system learns syntactic information on the source side as a by-product of training. We propose two methods to detect whether the encoderExpand
  • 202
  • 24
  • PDF
Generating Topical Poetry
We describe Hafez, a program that generates any number of distinct poems on a usersupplied topic. Poems obey rhythmic and rhyme constraints. We describe the poetrygeneration algorithm, giveExpand
  • 80
  • 7
  • PDF
Hafez: an Interactive Poetry Generation System
Hafez is an automatic poetry generation system that integrates a Recurrent Neural Network (RNN) with a Finite State Acceptor (FSA). It generates sonnets given arbitrary topics. Furthermore, HafezExpand
  • 45
  • 4
  • PDF
Why Neural Translations are the Right Length
We investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement thisExpand
  • 36
  • 4
  • PDF
Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary
We speed up Neural Machine Translation (NMT) decoding by shrinking run-time target vocabulary. We experiment with two shrinking approaches: Locality Sensitive Hashing (LSH) and word alignments. UsingExpand
  • 12
  • 1
  • PDF
Temporal learning and sequence modeling for a job recommender system
We present our solution to the job recommendation task for RecSys Challenge 2016. The main contribution of our work is to combine temporal learning with sequence modeling to capture complex user-itemExpand
  • 14
  • 1
  • PDF
Incident-Driven Machine Translation and Name Tagging for Low-resource Languages
We describe novel approaches to tackling the problem of natural language processing for low-resource languages. The approaches are embodied in systems for name tagging and machine translation (MT)Expand
  • 7
  • 1
  • PDF
Using First-Order Logic to Compress Sentences
Sentence compression is one of the most challenging tasks in natural language processing, which may be of increasing interest to many applications such as abstractive summarization and textExpand
  • 12
How to Speak a Language without Knowing It
We develop a system that lets people overcome language barriers by letting them speak a language they do not know. Our system accepts text entered by a user, translates the text, then converts theExpand
  • 6
  • PDF
A Sequential Embedding Approach for Item Recommendation with Heterogeneous Attributes
Attributes, such as metadata and profile, carry useful information which in principle can help improve accuracy in recommender systems. However, existing approaches have difficulty in fullyExpand
  • 4
  • PDF