Sciweavers

501 search results - page 70 / 101
» Improving Language Models by Clustering Training Sentences
Sort
View
NAACL
2003
13 years 10 months ago
Shallow Parsing with Conditional Random Fields
Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling...
Fei Sha, Fernando C. N. Pereira
NAACL
2010
13 years 7 months ago
Learning Translation Boundaries for Phrase-Based Decoding
Constrained decoding is of great importance not only for speed but also for translation quality. Previous efforts explore soft syntactic constraints which are based on constituent...
Deyi Xiong, Min Zhang, Haizhou Li
BIBE
2007
IEEE
169views Bioinformatics» more  BIBE 2007»
14 years 3 months ago
Combining Semantics, Context, and Statistical Evidence in Genomics Literature Search
—We present an information retrieval model for combining evidence from concept-based semantics, term statistics, and context for improving search precision of genomics literature...
Jay Urbain, Nazli Goharian, Ophir Frieder
ICASSP
2009
IEEE
14 years 3 months ago
Restoring punctuation and capitalization in transcribed speech
Adding punctuation and capitalization greatly improves the readability of automatic speech transcripts. We discuss an approach for performing both tasks in a single pass using a p...
Agustín Gravano, Martin Jansche, Michiel Ba...
SOCIALCOM
2010
13 years 7 months ago
Opinion Summarization in Bengali: A Theme Network Model
Theme network is a semantic network of document specific themes. So far Natural Language Processing (NLP) research patronized much of topic based summarizer system, unable to captu...
Amitava Das, Sivaji Bandyopadhyay