arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.05940cs.CL
收藏

将神经语法纠错作为低资源机器翻译任务

Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task

Microsoft(微软);University of Edinburgh(爱丁堡大学)

Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, Kenneth Heafield

摘要:

以前,与基于短语的统计机器翻译(SMT)基线相比,语法错误纠正(GEC)中的神经方法没有达到最先进的结果。我们证明了神经GEC和低资源神经MT之间的相似之处,并成功地适应了几种方法,从低资源MT神经GEC。我们进一步建立了神经GEC的可信结果的指导方针,并提出了一套模型无关的神经GEC的方法,可以很容易地应用于大多数GEC设置。所提出的方法包括添加源端噪声、领域自适应技术、特定于GEC的训练目标、使用单语数据的迁移学习以及独立训练的GEC模型和语言模型的集成。这些方法的综合效果导致比最先进的神经GEC模型更好,在CoNLL-2014基准测试中比以前最好的神经GEC系统表现出超过10%的M $^2$和5.9%的JFLEG测试集。在CoNLL-2014基准测试中,非神经系统的表现优于2%以上,在JFLEG测试中优于4%。

英文摘要:

Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific training-objective, transfer learning with monolingual data, and ensembling of independently trained GEC models and language models. The combined effects of these methods result in better than state-of-the-art neural GEC models that outperform previously best neural GEC systems by more than 10% M$^2$ on the CoNLL-2014 benchmark and 5.9% on the JFLEG test set. Non-neural state-of-the-art systems are outperformed by more than 2% on the CoNLL-2014 benchmark and by 4% on JFLEG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑