GECToR – Grammatical Error Correction: Tag, Not Rewrite
By Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem Chernodub, Oleksandr Skurzhanskyi. 2020
393 citations recorded by the source corpus.
In this paper, we present a simple and efficient GEC sequence tagger using a Transformer encoder. Our system is pre-trained on synthetic data and then fine-tuned in two stages: first on errorful corpora, and second on a combination of errorful and error-free parallel corpora. We design custom token-level transformations to map input tokens to target corrections. Our best single-model/ensemble GEC tagger achieves an F_0.5 of 65.3/66.5 on CONLL-2014 (test) and F_0.5 of 72.4/73.6 on BEA-2019 (test). Its inference speed is up to 10 times as fast as a Transformer-based seq2seq GEC system.
Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Natural Language Processing
In Information Extraction
Citations in the corpus
- STAR: A Benchmark for Situated Reasoning in Real-World Videos (2024, methodology): “To validate grammar correctness, we apply grammar checkers [3, 29] to perform grammar checking and correction for word typos, tense issues, or syntactic structures.”
- Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding (2021, methodology): “Note that for GECToR , we re-implement its inference process of GECToR (RoBERTa) using fairseq for testing its speedup in our setting.”
- Lossless Acceleration for Seq2seq Generation with Aggressive Decoding (2022, methodology): “For facilitating fair comparison in the efficiency evaluation, we follow the previous studies (Omelianchuk et al., 2020; Chen et al., 2020) which conduct GEC efficiency evaluation to use CoNLL-2014 (Ng et al.”
- A Comprehensive Survey of Grammatical Error Correction (2021, methodology): “GECToR is edited by manually defining editing operations whose edits include common grammatical errors such as spelling, number of nouns, subject-verb agreement, and verb forms [101].”
- Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation (2022, result): “…(Ge et al., 2022b; Yang et al., 2023) present extensive empirical studies of Speculative Decoding in special cases (e.g., text editing or retrieval-augmented generation) and compare it with competitive approaches (Malmi et al., 2019; Omelianchuk et al., 2020; Chen et al., 2020) in those scenarios.”
- Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction (2020, neutral): “One branch of the work is language-dependent approaches, like PIE (Awasthi et al., 2019) and GECToR (Omelianchuk et al., 2020).”
- Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation (2020, methodology): “Following Omelianchuk et al.(2020), we train the GEC model in three stages.”
- Learning to Model Editing Processes (2022, background): “…has been a reasonable amount of work that can generate edits to existing sequences for the purposes of post-editing, grammatical error correction (Omelianchuk et al., 2020), text style transfer (Mallinson et al., 2020; Malmi et al., 2020; Reid and Zhong, 2021), sentence fusion (Malmi et al.,…”
- SQA3D: Situated Question Answering in 3D Scenes (2022, methodology): “We adopt both rule-based cleaning and an MLbased tool called GECToR (Omelianchuk et al., 2020) in our grammatical correction pipeline.”