ACL
2007
14 years 1 months ago
2007
We present a Minimum Bayes Risk (MBR) decoder for statistical machine translation. The approach aims to minimize the expected loss of translation errors with regard to the BLEU sc...
ACL
2008
14 years 1 months ago
2008
For centuries, the deep connection between languages has brought about major discoveries about human communication. In this paper we investigate how this powerful source of inform...
ACL
2007
14 years 1 months ago
2007
This paper presents pipeline iteration, an approach that uses output from later stages of a pipeline to constrain earlier stages of the same pipeline. We demonstrate significant ...
ACL
2008
14 years 1 months ago
2008
Word lattice decoding has proven useful in spoken language translation; we argue that it provides a compelling model for translation of text genres, as well. We show that prior wo...
ACL
2007
14 years 1 months ago
2007
This paper addresses the issue of text normalization, an important yet often overlooked problem in natural language processing. By text normalization, we mean converting ‘inform...
ACL
2008
14 years 1 months ago
2008
This paper explores the relationship between discourse structure and coverbal gesture. Using the idea of gestural cohesion, we show that coherent topic segments are characterized ...
ACL
2007
14 years 1 months ago
2007
Obtaining large volumes of inference knowledge, such as entailment rules, has become a major factor in achieving robust semantic processing. While there has been substantial resea...
ACL
2008
14 years 1 months ago
2008
We present a novel framework for the discovery and representation of general semantic relationships that hold between lexical items. We propose that each such relationship can be ...
ACL
2007
14 years 1 months ago
2007
A minimally supervised machine learning framework is described for extracting relations of various complexity. Bootstrapping starts from a small set of n-ary relation instances as...
ACL
2008
14 years 1 months ago
2008
This paper presents a semi-supervised training method for linear-chain conditional random fields that makes use of labeled features rather than labeled instances. This is accompli...