arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.12640cs.CLcs.LG
收藏

基于转换的译码器对Transformer译码器的改进

Enhancing the Transformer Decoder with Transition-based Syntax

Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Leshem Choshen, Omri Abend

摘要:

尽管最近的进展,句法泛化仍然是文本解码器的一个挑战。虽然一些研究表明,将源端的符号句法和语义结构的文本生成Transformers的收益,很少有工作解决这种结构的解码。我们提出了一个通用的方法,树解码使用一个过渡为基础的方法。检查具有挑战性的测试情况下,将通用的重复性语法到机器翻译,我们提出了大量的改进测试集,侧重于语法泛化,同时提出改进或可比的性能标准MT基准。进一步的定性分析解决的情况下,语法概括香草Transformer解码器是不够的,并展示了整合语法信息所提供的优势。

英文摘要:

Notwithstanding recent advances, syntactic generalization remains a challenge for text decoders. While some studies showed gains from incorporating source-side symbolic syntactic and semantic structure into text generation Transformers, very little work addressed the decoding of such structure. We propose a general approach for tree decoding using a transition-based approach. Examining the challenging test case of incorporating Universal Dependencies syntax into machine translation, we present substantial improvements on test sets that focus on syntactic generalization, while presenting improved or comparable performance on standard MT benchmarks. Further qualitative analysis addresses cases where syntactic generalization in the vanilla Transformer decoder is inadequate and demonstrates the advantages afforded by integrating syntactic information.

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。

↑