NAACL
2010
13 years 9 months ago
2010
We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduc...
NAACL
2010
13 years 9 months ago
2010
NAACL
2010
13 years 9 months ago
2010
For extractive meeting summarization, previous studies have shown performance degradation when using speech recognition transcripts because of the relatively high speech recogniti...
NAACL
2010
13 years 9 months ago
2010
Word Segmentation is the foremost obligatory task in almost all the NLP applications where the initial phase requires tokenization of input into words. Urdu is amongst the Asian l...
NAACL
2010
13 years 9 months ago
2010
We suggest improvements to a previously proposed framework for integrating Conditional Random Fields and Hidden Markov Models, dubbed a Crandem system (2009). The previous authors...
NAACL
2010
13 years 9 months ago
2010
Deploying an automatic speech recognition system with reasonable performance requires expensive and time-consuming in-domain transcription. Previous work demonstrated that non-pro...
NAACL
2010
13 years 9 months ago
2010
We present a novel approach to metaphor interpretation and a system that produces literal paraphrases for metaphorical expressions. Such a representation is directly transferable ...
NAACL
2010
13 years 9 months ago
2010
Current statistical parsers tend to perform well only on their training domain and nearby genres. While strong performance on a few related domains is sufficient for many situatio...
NAACL
2010
13 years 9 months ago
2010
We treat the text summarization problem as maximizing a submodular function under a budget constraint. We show, both theoretically and empirically, a modified greedy algorithm can...
NAACL
2010
13 years 9 months ago
2010
Factorization is the operation of transforming a production in a Linear Context-Free Rewriting System (LCFRS) into two simpler productions by factoring out a subset of the nonterm...