Predicting the Performance of Parsing with Referential Translation Machines

Referential translation machine (RTM) is a prediction engine used for predicting the performance of natural language processing tasks including parsing, machine translation, and semantic similarity pioneering language, task, and domain independence. RTM results for predicting the performance of pars...

Full description

Saved in:
Bibliographic Details
Published in:Prague bulletin of mathematical linguistics 2016-10, Vol.106 (1), p.31-44
Main Author: Biçici, Ergun
Format: Article
Language:English
Subjects:
Artificial intelligence
Bilingualism
Consortia
Language
Linguistics
Lower bounds
Machine learning
Machine translation
Natural language processing
Parsing
Performance prediction
Quality
Semantics
Training sets
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Referential translation machine (RTM) is a prediction engine used for predicting the performance of natural language processing tasks including parsing, machine translation, and semantic similarity pioneering language, task, and domain independence. RTM results for predicting the performance of parsing (PPP) in out-of-domain or in-domain settings with different training sets and types of features present results independent of language or parser. RTM PPP models can be used without parsing using only text input and without any parser or language dependent information. Our results detail prediction performance, top selected features, and lower bound on the prediction error of PPP.
ISSN:1804-0462
0032-6585
1804-0462
DOI:10.1515/pralin-2016-0010