An Extended Sequence Tagging Vocabulary for Grammatical Error Correction

02/12/2023
by   Stuart Mesham, et al.
0

We extend a current sequence-tagging approach to Grammatical Error Correction (GEC) by introducing specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms. Our approach improves generalisation: the proposed new tagset allows a smaller number of tags to correct a larger range of errors. Our results show a performance improvement both overall and in the targeted error categories. We further show that ensembles trained with our new tagset outperform those trained with the baseline tagset on the public BEA benchmark.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2020

Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction

We propose a novel language-independent approach to improve the efficien...
research
02/14/2017

JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction

We present a new parallel corpus, JHU FLuency-Extended GUG corpus (JFLEG...
research
09/18/2023

HTEC: Human Transcription Error Correction

High-quality human transcription is essential for training and improving...
research
03/24/2022

Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction

In this paper, we investigate improvements to the GEC sequence tagging a...
research
05/29/2021

Grammatical Error Correction as GAN-like Sequence Labeling

In Grammatical Error Correction (GEC), sequence labeling models enjoy fa...
research
05/22/2022

Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation

The task of Grammatical Error Correction (GEC) has received remarkable a...
research
06/04/2020

Personalizing Grammatical Error Correction: Adaptation to Proficiency Level and L1

Grammar error correction (GEC) systems have become ubiquitous in a varie...

Please sign up or login with your details

Forgot password? Click here to reset