Simon Flachs
YOU?
Author Swipe
View article: Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses
Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses Open
Evaluation of grammatical error correction (GEC) systems has primarily focused on essays written by non-native learners of English, which however is only part of the full spectrum of GEC applications. We aim to broaden the target domain of…
View article: A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors
A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors Open
While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data. We o…
View article: Historical Text Normalization with Delayed Rewards
Historical Text Normalization with Delayed Rewards Open
Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models. Policy gradient training enables direct optim…
View article: Noisy Channel for Low Resource Grammatical Error Correction
Noisy Channel for Low Resource Grammatical Error Correction Open
This paper describes our contribution to the low-resource track of the BEA 2019 shared task on Grammatical Error Correction (GEC). Our approach to GEC builds on the theory of the noisy channel by combining a channel model and language mode…