Association for Computational Linguistics. Cite (Informal):: Geo-Centric Language Models for Local Business Voice Search (Stent et al., NAACL 2009)

for building geo-centric language models for voice- driven business search that: gives a local language model for any user anywhere in the country; uses.

Our algorithm has several ad- vantages: it provides a language model for any user in any location; the geographic area covered by the language model is adapted ...

Our algorithm has several advantages: it provides a language model for any user in any location; the geographic area covered by the language model is adapted to ...

Geo-Centric Language Models For Local Business Voice Search ; Ask PDF upload a paper & ask questions about it ; Writing help you write, edit & cite sentence by ...

Geo-Centric Language Models for Local Business Voice Search. A. Stent, I. Zeljkovic, D. Caseiro, and J. Wilpon. HLT-NAACL, page 389-396.

Geo-Centric Language Models for Local Business Voice Search. Amanda Stent | Ilija Zeljković | Diamantino Caseiro | Jay Wilpon |. Paper Details: Month: June

The experiments show that the proposed Geo-Lm achieves an average of over 18 % relative word error rate (WER) reduction on the tasks of local POI search, ...

This paper presents a novel approach to language modeling for voice search based on the idea and method of statistical machine translation.

Stent et al "Geo centric language models for local business voice search", proc. NAACL 2009, p.389-396 , describes an algorithm for geo-centric language model ...