We show that categories induced by unsupervised word clustering can surpass the performance of gold part-of-speech tags in dependency grammar induction. Unlike classic clustering ...
Valentin I. Spitkovsky, Hiyan Alshawi, Angel X. Ch...
This work describes an online application that uses Natural Language Generation (NLG) methods to generate walking directions in combination with dynamic 2D visualisation. We make ...
In this paper we present a reference generation model based on Reference Domain Theory which gives a dynamic account of reference. This reference model assumes that each referring...
Locality Conditions (LCs) on (unbounded) dependencies have played a major role in the development of generative syntax ever since the seminal work by Ross [22]. Descriptively, they...
The problem of Named Entity Generation is expressed as a conditional probability model over a structured domain. By defining a factor-graph model over the mentions of a text, we o...