Character Transformations for Non-Autoregressive GEC Tagging
We propose a character-based nonautoregressive GEC approach, with automatically generated character transformations. Recently, per-word classification of correction edits has proven an efficient, parallelizable alternative to current encoder-decoder GEC systems. We show that word replacement edits may be suboptimal and lead to explosion of rules for spelling, diacritization and errors in morphologically rich languages, and propose a method for generating character transformations from GEC corpus. Finally, we train character transformation models for Czech, German and Russian, reaching solid results and dramatic speedup compared to autoregressive systems. The source code is released at https://github.com/ufal/wnut2021_character_transformations_gec.
Code (1)
Tasks
DecoderSimilar Papers 제목 키워드 기반
EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start
We present EdiT5 - a novel semi-autoregressive text-editing model designed to combine the strengths of non-autoregressive text-editing and autoregressive decoding. EdiT5 is faster during inference than conventional seque…
DecoderGrammatical Error CorrectionSentenceSentence FusionFelix: Flexible Text Editing Through Tagging and Insertion
We present Felix --- a flexible text-editing approach for generation, designed to derive the maximum benefit from the ideas of decoding with bi-directional contexts and self-supervised pre-training. In contrast to conven…
Automatic Post-EditingLanguage ModelingLanguage ModellingMachine Translation+4Transformation Autoregressive Networks
The fundamental task of general density estimation $p(x)$ has been of keen interest to machine learning. In this work, we attempt to systematically characterize methods for density estimation. Broadly speaking, most of t…
Density EstimationOutlier DetectionText Simplification by Tagging
Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratc…
Text SimplificationUnsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data
Domain adaptation is an important and widely studied problem in natural language processing. A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain. In…
Domain AdaptationPart-Of-Speech TaggingPOSPOS Tagging+1