| 1 |
The Best Lexical Metric for Phrase-Based Statistical MT System Optimization
|
|
|
|
In: http://www.mt-archive.info/NAACL-HLT-2010-Cer-1.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Learning continuous phrase representations and syntactic parsing with recursive neural networks
|
|
|
|
In: http://www.socher.org/uploads/Main/2010SocherManningNg.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Learning continuous phrase representations and syntactic parsing with recursive neural networks
|
|
|
|
In: http://wuawua.googlecode.com/files/Learning Continuous Phrase Representations and Syntactic Parsing with Recursive Neural Networks.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Better Arabic parsing: Baselines, evaluations, and analysis
|
|
|
|
In: http://aclweb.org/anthology-new/C/C10/C10-1045.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Better Arabic Parsing: Baselines, Evaluations, and Analysis
|
|
|
|
In: http://www.spencegreen.com/pubs/green+manning.coling10.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Better Arabic parsing: Baselines, evaluations, and analysis
|
|
|
|
In: http://nlp.stanford.edu/pubs/coling2010-arabic.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Subword variation in text message classification. Paper presented at the Human Language Technologies: The Annual Conference of the North American Chapter of the ACL
|
|
|
|
In: http://mickey.ifp.illinois.edu/speechWiki/images/7/73/Munro-Manning_NAACL10.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Subword variation in text message classification
|
|
|
|
In: http://nlp.stanford.edu/pubs/munro2010chichewa.pdf (2010)
|
|
Abstract:
For millions of people in less resourced regions of the world, text messages (SMS) provide the only regular contact with their doctor. Classifying messages by medical labels supports rapid responses to emergencies, the early identification of epidemics and everyday administration, but challenges include textbrevity, rich morphology, phonological variation, and limited training data. We present a novel system that addresses these, working with a clinic in rural Malawi and texts in the Chichewa language. We show that modeling morphological and phonological variation leads to a substantial average gain of F=0.206 and an error reduction of up to 63.8 % for specific labels, relative to a baseline system optimized over word-sequences. By comparison, there is no significant gain when applying the same system to the English translations of the same texts/labels, emphasizing the need for subword modeling in many languages. Language independent morphological models perform as accurately as language specific models, indicating a broad deployment potential. 1
|
|
URL: http://nlp.stanford.edu/pubs/munro2010chichewa.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.7411
|
|
BASE
|
|
Hide details
|
|
|
| 9 |
Phrasal: a toolkit for statistical machine translation with facilities for extraction and incorporation of arbitrary model features.
|
|
|
|
In: https://www.microsoft.com/en-us/research/wp-content/uploads/2010/06/Phrasal-A-Statistical-Machine-Translation-Toolkit-for-Exploring-New-Model-Features.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Subword variation in text message classification
|
|
|
|
In: http://www.aclweb.org/anthology-new/N/N10/N10-1075.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Probabilistic treeedit models with structured latent variables for textual entailment and question answering
|
|
|
|
In: http://nlp.stanford.edu/pubs/wang-manning-coling10.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
|
|
