Comparison of Grammatical Error Correction Using Back-Translation Models
Comparison of Grammatical Error Correction Using Back-Translation Models
复制标题
DOI：
10.18653/v1/2021.naacl-srw.16
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Aomi Koyama;Kengo Hotate;Masahiro Kaneko;Mamoru Komachi
中科院分区：
文献类型：
--
作者：
Aomi Koyama;Kengo Hotate;Masahiro Kaneko;Mamoru Komachi
语法错误纠正（GEC）缺乏足够的并行数据。GEC的研究已经提出了几种方法来生成伪数据，其中包括成对的语法和人工产生的不语法的句子。目前，生成伪数据的主流方法是回译（BT）。大多数先前使用BT的研究对GEC和BT模型都采用了相同的架构。然而，GEC模型有不同的校正倾向，这取决于其模型的架构。因此，在这项研究中，我们比较了在三种不同架构的BT模型（即Transformer，CNN和LSTM）生成的伪数据上训练的GEC模型的校正趋势。结果证实，每种错误类型的校正趋势是不同的每一个BT模型。此外，我们调查的校正趋势时，使用不同的BT模型产生的伪数据的组合。因此，我们发现，与使用具有不同种子的单个BT模型相比，不同BT模型的组合改善或内插每种错误类型的性能。
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.