Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userComparison of Grammatical Error Correction Using Back-Translation Models
مقارنة تصحيح الخطأ النحوي باستخدام نماذج الترجمة الخلفي
634
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعاني تصحيح الخطأ النحوي (GEC) من عدم وجود بيانات متوازية كافية. اقترحت دراسات حول GEC عدة طرق لتوليد بيانات زائفة، والتي تشمل أزواج من الجمل النحوية والنصيع بشكل مصطنع. حاليا، فإن النهج السائد لتوليد بيانات الزائفة هو الترجمة مرة أخرى (BT). وقد استخدمت معظم الدراسات السابقة باستخدام BT نفس الهندسة المعمارية لكل من نماذج GEC و BT. ومع ذلك، فإن نماذج GEC لها اتجاهات تصحيح مختلفة اعتمادا على بنية نماذجها. وبالتالي، في هذه الدراسة، نقارن اتجاهات تصحيح نماذج GEC المدربة على البيانات الزائفة التي تم إنشاؤها بواسطة ثلاث نماذج BT مع بنية مختلفة، وهي المحول، CNN، و LSTM. تؤكد النتائج أن ميول التصحيح لكل نوع خطأ مختلفة لكل طراز BT. بالإضافة إلى ذلك، يمكننا التحقيق في ميول التصحيح عند استخدام مجموعة من البيانات الزائفة الناتجة عن نماذج BT مختلفة. نتيجة لذلك، نجد أن مجموعة من نماذج BT المختلفة تتحسن أو تحسن أداء كل نوع من نوع الخطأ مقارنة باستخدام نموذج BT واحد مع بذور مختلفة.
Grammatical error correction (GEC) suffers from a lack of sufficient parallel data. Studies on GEC have proposed several methods to generate pseudo data, which comprise pairs of grammatical and artificially produced ungrammatical sentences. Currently, a mainstream approach to generate pseudo data is back-translation (BT). Most previous studies using BT have employed the same architecture for both the GEC and BT models. However, GEC models have different correction tendencies depending on the architecture of their models. Thus, in this study, we compare the correction tendencies of GEC models trained on pseudo data generated by three BT models with different architectures, namely, Transformer, CNN, and LSTM. The results confirm that the correction tendencies for each error type are different for every BT model. In addition, we investigate the correction tendencies when using a combination of pseudo data generated by different BT models. As a result, we find that the combination of different BT models improves or interpolates the performance of each error type compared with using a single BT model with different seeds.
References used
https://aclanthology.org/
rate research
Read More
Grammatical error correction (GEC) requires a set of labeled ungrammatical / grammatical sentence pairs for training, but obtaining such annotation can be prohibitively expensive. Recently, the Break-It-Fix-It (BIFI) framework has demonstrated strong
results on learning to repair a broken program without any labeled examples, but this relies on a perfect critic (e.g., a compiler) that returns whether an example is valid or not, which does not exist for the GEC task. In this work, we show how to leverage a pretrained language model (LM) in defining an LM-Critic, which judges a sentence to be grammatical if the LM assigns it a higher probability than its local perturbations. We apply this LM-Critic and BIFI along with a large set of unlabeled sentences to bootstrap realistic ungrammatical / grammatical pairs for training a corrector. We evaluate our approach on GEC datasets on multiple domains (CoNLL-2014, BEA-2019, GMEG-wiki and GMEG-yahoo) and show that it outperforms existing methods in both the unsupervised setting (+7.7 F0.5) and the supervised setting (+0.5 F0.5).
Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation mode
l is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://github.com/thunlp/VERNet.
In this paper, we present a new method for training a writing improvement model adapted to the writer's first language (L1) that goes beyond grammatical error correction (GEC). Without using annotated training data, we rely solely on pre-trained lang
uage models fine-tuned with parallel corpora of reference translation aligned with machine translation. We evaluate our model with corpora of academic papers written in English by L1 Portuguese and L1 Spanish scholars and a reference corpus of expert academic English. We show that our model is able to address specific L1-influenced writing and more complex linguistic phenomena than existing methods, outperforming what a state-of-the-art GEC system can achieve in this regard. Our code and data are open to other researchers.
GECko+ : a Grammatical and Discourse Error Correction Tool We introduce GECko+, a web-based writing assistance tool for English that corrects errors both at the sentence and at the discourse level. It is based on two state-of-the-art models for gramm
ar error correction and sentence ordering. GECko+ is available online as a web application that implements a pipeline combining the two models.
Although grammatical error correction (GEC) has achieved good performance on texts written by learners of English as a second language, performance on low error density domains where texts are written by English speakers of varying levels of proficie
ncy can still be improved. In this paper, we propose a contrastive learning approach to encourage the GEC model to assign a higher probability to a correct sentence while reducing the probability of incorrect sentences that the model tends to generate, so as to improve the accuracy of the model. Experimental results show that our approach significantly improves the performance of GEC models in low error density domains, when evaluated on the benchmark CWEB dataset.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
