Language software applications encounter new words, e.g., acronyms, technical terminology, loan words, names or compounds of such words. Looking at English, one might assume that t...
The trigram-based noisy-channel model of real-word spelling-error correction that was presented by Mays, Damerau, and Mercer in 1991 has never been adequately evaluated or compare...
L. Amber Wilcox-O'Hearn, Graeme Hirst, Alexander B...
This paper analyzes two joint inference approaches for semantic role labeling: re-ranking of candidate semantic frames generated by one local model and combination of two distinct ...
Abstract. Text interpretation can be considered as the process of extracting deep-level semantics from unstructured text documents. Deeplevel semantics represent abstract index str...
Irma Sofia Espinosa Peraldi, Atila Kaya, Sylvia Me...
Abstract. Automatic document summarization has become increasingly important due to the quantity of written material generated worldwide. Generating good quality summaries enables ...
Judith D. Schlesinger, Dianne P. O'Leary, John M. ...
This paper proposes a non-interactive system for reducing the level of OCR-induced typographical variation in large text collections, contemporary and historical. Text-Induced Corp...
Nowadays there exist several kinds of question answering systems. According to recent evaluation results, most of these systems are complementary (i.e., each one is better than the...
Abstract. This paper is concerned with the task of preposition generation in the context of a grammar checker. Relevant features for this task can range from lexical features, such...
In this paper we propose a new approach to the description of Arabic morphology using 2-tape finite state transducers, based on a particular and systematic use of the operation of ...
Abstract. We present an approach for knowledge-free and unsupervised recognition of compound nouns for languages that use one-wordcompounds such as Germanic and Scandinavian langua...