Paper Info
Title
Efficient determinization of tagged word lattices using categorial and lexicographic semirings
Abstract
Speech and language processing systems routinely face the need to apply finite state operations (e.g., POS tagging) on results from intermediate stages (e.g., ASR output) that are naturally represented in a compact lattice form. Currently, such needs are met by converting the lattices into linear sequences (n-best scoring sequences) before and after applying the finite state operations. In this paper, we eliminate the need for this unnecessary conversion by addressing the problem of picking only the single-best scoring output labels for every input sequence. For this purpose, we define a categorial semiring that allows determinzation over strings and incorporate it into a 〈Tropical, Categorial〉 lexicographic semiring. Through examples and empirical evaluations we show how determinization in this lexicographic semiring produces the desired output. The proposed solution is general in nature and can be applied to multi-tape weighted transducers that arise in many applications.
Year
DOI
Venue
2011
10.1109/ASRU.2011.6163945
Automatic Speech Recognition and Understanding
Keywords
Field
DocType
natural language processing,sequences,speech recognition,transducers,categorial semiring,language processing,lexicographic semiring,multitape weighted transducer,single best scoring output label,speech processing,tagged word lattice
Lattice (order),Computer science,Finite state,Speech recognition,Lexicographical order,Finite state transducer,Semiring
Conference
ISBN
Citations 
PageRank 
978-1-4673-0366-8
4
0.42
References 
Authors
7
4
Name
Order
Citations
PageRank
Izhak Shafran130030.44
Richard Sproat2133.11
Mahsa Yarmohammadi371.16
Brian Roark447948.82