Sciweavers

55 search results - page 5 / 11
» Near-Synonymy and Lexical Choice
Sort
View
SPEECH
2010
89views more  SPEECH 2010»
13 years 5 months ago
Which words are hard to recognize? Prosodic, lexical, and disfluency factors that increase speech recognition error rates
Despite years of speech recognition research, little is known about which words tend to be misrecognized and why. Previous work has shown that errors increase for infrequent words...
Sharon Goldwater, Daniel Jurafsky, Christopher D. ...
ACL
1997
14 years 6 days ago
Sentence Planning as Description Using Tree Adjoining Grammar
We present an algorithm for simultaneously constructing both the syntax and semantics of a sentence using a Lexicalized Tree Adjoining Grammar (LTAG). This approach captures natur...
Matthew Stone, Christine Doran
AAAI
2008
14 years 1 months ago
Using Wiktionary for Computing Semantic Relatedness
We introduce Wiktionary as an emerging lexical semantic resource that can be used as a substitute for expert-made resources in AI applications. We evaluate Wiktionary on the perva...
Torsten Zesch, Christof Müller, Iryna Gurevyc...
AUSAI
1997
Springer
14 years 3 months ago
Integrated Correction of Ill-Formed Sentences
This paper describes a system that performs hierarchical error recovery, and detects and corrects a single error in a sentence at the lexical, syntactic, and/or semantic levels. I...
Kyongho Min, William H. Wilson
EMNLP
2009
13 years 8 months ago
Graded Word Sense Assignment
Word sense disambiguation is typically phrased as the task of labeling a word in context with the best-fitting sense from a sense inventory such as WordNet. While questions have o...
Katrin Erk, Diana McCarthy