One of the most desired information types when planning a trip to some place is the knowledge of transport, roads and geographical connectedness of prominent sites in this place. ...
Recently system combination has been shown to be an effective way to improve translation quality over single machine translation systems. In this paper, we present a simple and ef...
This paper describes an empirical study of high-performance dependency parsers based on a semi-supervised learning approach. We describe an extension of semisupervised structured ...
Jun Suzuki, Hideki Isozaki, Xavier Carreras, Micha...
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
Most existing systems for Chinese Semantic Role Labeling (SRL) make use of full syntactic parses. In this paper, we evaluate SRL methods that take partial parses as inputs. We fir...