In this paper we investigate named entity transliteration based on a phonetic scoring method. The phonetic method is computed using phonetic features and carefully designed pseudo...
It has always been difficult for language understanding systems to handle spontaneous speech with satisfactory robustness, primarily due to such problems as the fragments, disflue...
Bor-shen Lin, Berlin Chen, Hsin-Min Wang, Lin-Shan...
Taxonomies are an important resource for a variety of Natural Language Processing (NLP) applications. Despite this, the current stateof-the-art methods in taxonomy learning have d...
Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the ...
This paper proposes a general learning framework for a class of problems that require learning over latent intermediate representations. Many natural language processing (NLP) dec...
Ming-Wei Chang, Dan Goldwasser, Dan Roth, Vivek Sr...