Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

14

ANLP
2000

favoriteEmaildiscussreport

118views more ANLP 2000»

An Unsupervised Method for Detecting Grammatical Errors

13 years 5 months ago

An Unsupervised Method for Detecting Grammatical Errors

Download acl.ldc.upenn.edu

We present an unsupervised method for detecting grammatical errors by inferring negative evidence from edited textual corpora. The system was developed and tested using essay-length responses to prompts on the Test of English as a Foreign Language (TOEFL). The errorrecognition system, ALEK, performs with about 80% precision and 20% recall.

Martin Chodorow, Claudia Leacock

Real-time Traffic

ANLP 2000 | Essay-length Responses | Grammatical Errors | Unsupervised Method |

claim paper

Related Content

» Automatic Error Detection in the Japanese Learners English Spoken Data

» The Grammatical Function Analysis between Adnoun Clause and Noun Phrase in Korean

» Unsupervised pronunciation validation

» Performance Prediction for Unsupervised Video Indexing

» FAST An Automatic Generation System for Grammar Tests

» PhaseAware Nonnegative Spectrogram Factorization

» Learning Semantic Scene Models by Trajectory Analysis

» Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restr...

» DictionaryFree Categorization of Very Similar Objects via Stacked Evidence Trees

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	2000
Where	ANLP
Authors	Martin Chodorow, Claudia Leacock

Comments (0)