• Publications
  • Influence
Latent-Variable Modeling of String Transductions with Finite-State Methods
TLDR
We present a conditional loglinear model for string-to-string transduction, which employs overlapping features over latent alignment sequences, and which learns latent classes and latent string pair regions from incomplete training data. Expand
  • 102
  • 16
  • PDF
LatticeRnn: Recurrent Neural Networks Over Lattices
TLDR
We present a new model called LATTICERNN, which generalizes recurrent neural networks (RNNs) to process weighted lattices as input, instead of sequences. Expand
  • 43
  • 5
  • PDF
HLTCOE Approaches to Knowledge Base Population at TAC 2009
TLDR
A machine learning-based approach to entity linking, operating over a wide range of feature types, yielded good performance on the entity linking task. Expand
  • 48
  • 4
  • PDF
Zero-Shot Learning Across Heterogeneous Overlapping Domains
TLDR
We present a zero-shot learning approach for text classification, predicting which natural language understanding domain can handle a given utterance. Expand
  • 19
  • 4
  • PDF
Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
TLDR
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK), which was the first Spoken Language Understanding (SLU) Software Development Kit (SDK) for a virtual digital assistant, as far as we are aware. Expand
  • 50
  • 3
  • PDF
Exploiting prosody for PCFGs with latent annotations
TLDR
We propose novel methods for integrating prosody in syntax using generative models. Expand
  • 13
  • 3
  • PDF
HyTER: Meaning-Equivalent Semantics for Translation Evaluation
TLDR
An annotation tool and process that enables us to create meaning-equivalent networks that encode an exponential number of translations for a sentence. Expand
  • 65
  • 2
  • PDF
Transfer Learning for Neural Semantic Parsing
TLDR
The goal of semantic parsing is to map natural language to a machine interpretable meaning representation language (MRL). Expand
  • 44
  • 2
  • PDF
Graphical Models over Multiple Strings
TLDR
We study graphical modeling in the case of string-valued random variables. Expand
  • 43
  • 2
  • PDF
Machine Translation System Combination using ITG-based Alignments
TLDR
This work was partially supported by the DARPA GALE program (Contract No HR0011-06-2-0001). Expand
  • 68
  • 1
  • PDF
...
1
2
3
...