Proceedings Article10.3115/1699705.1699729
Substring-based Transliteration with Conditional Random Fields
Sravana Reddy,Sonjia Waxmonsky +1 more
- 07 Aug 2009
- pp 92-95
TL;DR: This work presents a transliteration system where characters are grouped into substrings to be mapped atomically into the target language and shows how this substring representation can be incorporated into a Conditional Random Field model that uses local context and phonemic information.
read more
Abstract: Motivated by phrase-based translation research, we present a transliteration system where characters are grouped into substrings to be mapped atomically into the target language. We show how this substring representation can be incorporated into a Conditional Random Field model that uses local context and phonemic information.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Conditional Random Field Autoencoders for Unsupervised Structured Prediction
TL;DR: Competitive results with instantiations of the framework for unsupervised learning of structured predictors with overlapping, global features are shown, and it is shown that training the proposed model can be substantially more efficient than a comparable feature-rich baseline.
73
•Proceedings Article
Conditional Random Field Autoencoders for Unsupervised Structured Prediction
Waleed Ammar,Chris Dyer,Noah A. Smith +2 more
- 08 Dec 2014
TL;DR: This article introduced a framework for unsupervised learning of structured predictors with overlapping, global features, which enables efficient exact inference without resorting to unrealistic independence assumptions or restricting the kinds of features that can be used.
Whitepaper of NEWS 2015 Shared Task on Machine Transliteration
Min Zhang,Haizhou Li,Rafael E. Banchs,Alaganandam Kumaran +3 more
- 01 Jul 2015
TL;DR: The objective of the shared task is to promote machine transliteration research by providing a common benchmarking platform for the community to evaluate the state-of-the-art technologies.
A Sequence-to-Sequence based Approach For the double Transliteration of Tunisian Dialect
TL;DR: A deep learning based Sequence-to-Sequence approach is proposed to perform a word-level transliteration of the user generated Tunisian dialect on the social web, in both Latin to Arabic and Arabic to Latin senses.
21
•Proceedings Article
Transliteration by Sequence Labeling with Lattice Encodings and Reranking
Waleed Ammar,Chris Dyer,Noah A. Smith +2 more
- 12 Jul 2012
TL;DR: This paper presents results on the Arabic-English transliteration task of the NEWS 2012 workshop with two innovations: a training objective that optimizes toward any of a set of possible correct labels, and a k-best reranking stage to incorporate nonlocal features.
References
A systematic comparison of various statistical alignment models
Franz Josef Och,Hermann Ney +1 more
TL;DR: An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models.
Text Chunking Using Transformation-Based Learning
Lance Ramshaw,Mitchell Marcus +1 more
- 01 Jan 1999
TL;DR: This work has shown that the transformation-based learning approach can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including non-recursive “baseNP” chunks.
1.6K
•Posted Content
Text Chunking using Transformation-Based Learning
Lance Ramshaw,Mitchell Marcus +1 more
TL;DR: The authors used transformation-based learning for part-of-speech tagging with fairly high accuracy, achieving recall and precision rates of roughly 92% for base NP chunks and 88% for more complex chunks.
1.3K
•Proceedings Article
Substring-Based Transliteration
Tarek Sherif,Grzegorz Kondrak +1 more
- 01 Jun 2007
TL;DR: It is shown that the substring-based transducer not only outperforms a state-of-the-art letterbased approach by a significant margin, but is also orders of magnitude faster.
66
•Proceedings Article
Statistical Transliteration for Cross Langauge Information Retrieval using HMM alignment and CRF
Surya Ganesh,Sree Harsha,Prasad Pingali,Vasudeva Varma +3 more
- 01 Jan 2008
TL;DR: The results show that the technique perfoms better than the existing transliteration system which uses HMM alignment and conditional probabilities derived from counting the alignments.