ACL
2010
2010
Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons
13 years 2 months ago
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...
ACL
2010
13 years 2 months ago
2010
In this paper, we present a simple and effective method to address the issue of how to generate diversified translation systems from a single Statistical Machine Translation (SMT)...
ACL
2010
13 years 2 months ago
2010
Extracting knowledge from unstructured text is a long-standing goal of NLP. Although learning approaches to many of its subtasks have been developed (e.g., parsing, taxonomy induc...
ACL
2010
13 years 2 months ago
2010
In-vehicle dialogue systems often contain more than one application, e.g. a navigation and a telephone application. This means that the user might, for example, interrupt the inte...
ACL
2010
13 years 2 months ago
2010
Probabilistic latent topic models have recently enjoyed much success in extracting and analyzing latent topics in text in an unsupervised way. One common deficiency of existing to...
ACL
2010
13 years 2 months ago
2010
For languages with (semi-) free word order (such as German), labelling grammatical functions on top of phrase-structural constituent analyses is crucial for making them interpreta...
ACL
2010
13 years 2 months ago
2010
We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed ed...
ACL
2010
13 years 2 months ago
2010
We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic representations. A simp...
ACL
2010
13 years 2 months ago
2010
The computation of selectional preferences, the admissible argument values for a relation, is a well-known NLP task with broad applicability. We present LDA-SP, which utilizes Lin...
ACL
2010
13 years 2 months ago
2010
We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural ...