133
click to vote
ACL
2015
10 years 3 months ago
2015
The usefulness of translation quality estimation (QE) to increase productivity in a computer-assisted translation (CAT) framework is a widely held assumption (Specia, 2011; Huang ...
141
click to vote
ACL
2015
10 years 3 months ago
2015
Recent work on supertagging using a feedforward neural network achieved significant improvements for CCG supertagging and parsing (Lewis and Steedman, 2014). However, their archi...
161
click to vote
ACL
2015
10 years 3 months ago
2015
Many queries in web search are ambiguous or multifaceted. Identifying the major senses or facets of queries is very important for web search. In this paper, we represent the major...
161
click to vote
ACL
2015
10 years 3 months ago
2015
There is a growing interest in researching null instantiations, which are those implicit semantic arguments. Many of these implicit arguments can be linked to referents in context...
139
click to vote
ACL
2015
10 years 3 months ago
2015
This paper is concerned with building CCG-grounded, semantics-oriented deep dependency structures with a data-driven, factorization model. Three types of factorization together wi...
152
click to vote
ACL
2015
10 years 3 months ago
2015
We study the event detection problem using convolutional neural networks (CNNs) that overcome the two fundamental limitations of the traditional feature-based approaches to this t...
149
click to vote
ACL
2015
2015
Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding
10 years 3 months ago
Spoken dialogue systems (SDS) typically require a predefined semantic ontology to train a spoken language understanding (SLU) module. In addition to the annotation cost, a key ch...
134
click to vote
ACL
2015
10 years 3 months ago
2015
In this paper, we present our Crossword Puzzle Resolution System (SACRY), which exploits syntactic structures for clue reranking and answer extraction. SACRY uses a database (DB) ...
134
click to vote
ACL
2015
10 years 3 months ago
2015
We exploit the visual properties of concepts for lexical entailment detection by examining a concept’s generality. We introduce three unsupervised methods for determining a conc...