Abstract. In many applications of natural language processing (NLP) it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may ne...
This paper presents a new method to automatically add n-grams containing out-of-vocabulary (OOV) words to a baseline language model (LM), where these n-grams are sought to be gram...
e by placing terms in an abstract ‘information space’ based on their occurrences in text corpora, and then allowing a user to visualize local regions of this information space....
This paper describes a method of systematically generating visual sensing strategies based on knowledge of the assembly task to be performed. Since visual sensing is usually perfo...
This article describes an algorithm called HyperLex that is capable of automatically determining word uses in a textbase without recourse to a dictionary. The algorithm makes use ...