Like most natural language disambiguation tasks, word sense disambiguation (WSD) requires world knowledge for accurate predictions. Several proxies for this knowledge have been investigated, including labeled corpora, user-contributed knowledge, and machine readable dictionaries, but each of these proxies requires significant manual effort to create, and they do not cover all of the ambiguous t...

The objective of this work is to design a translation machine which can translate English text to Indian Sign Language glosses. A number of rule based approaches are identified in this regard, but our approach is based on statistical machine translation for ISL by using a corpus. The corpus is prepared by collecting glosses and sentences used in Indian Railways for announcement and conversation...

This paper presents few extensions to the logic form representation and a method for transforming WordNet glosses into logic forms using a set of high-precision rules combined with a set of high recall heuristics. An almost 3% increase in POS tagging accuracy is achieved over state-of-the art results at the expense of user intervention on only 7.52% of words. We apply a nearest neighbor solutio...

2 Abbreviations used in the glosses: dem = demonstrative pronoun, n = neuter, nn = nonneuter, sg = singular, pl = plural, inv = inversion form, pcple = past participle.

THE composite character of the two chapters--Leviticus 13 and 14--comprising the laws and regulations for the diagnosis and treatment of various skin diseases, and of suspicious spots appearing in garments and houses, together with the purification rites, has long been recognized. Indeed, the mere enumeration of the variety of subjects treated of in these two chapters, which form a little code ...

We propose and evaluate a new paradigm for machine translation of low resource languages via the learned surface transduction and paraphrase of multilingual glosses.