论文标题
稍后翻译首先重新排序：在语义解析中利用单调性
Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing
论文作者
论文摘要
语义解析的先前工作表明，常规的SEQ2SEQ模型在组成概括任务中失败。这种限制导致了方法的复兴，该方法的复兴是模拟句子及其相应含义表示形式之间的对齐方式，即通过潜在变量隐式或通过利用对齐方式注释明确。我们采取第二个方向并提出了TPOL，这是一种两步方法，首先单调地翻译输入句子，然后再换取它们以获得正确的输出。这是通过一个模块化框架来实现的，该框架包括翻译器和一个重新排序组件。我们在两个流行的语义解析数据集上测试了我们的方法。我们的实验表明，通过单调翻译，TPOL可以从对齐数据中学习可靠的词典逻辑模式，从而显着改善了比常规SEQ2SEQ模型的组成概括，以及利用黄金对齐的其他方法。
Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alignments between sentences and their corresponding meaning representations, either implicitly through latent variables or explicitly by taking advantage of alignment annotations. We take the second direction and propose TPOL, a two-step approach that first translates input sentences monotonically and then reorders them to obtain the correct output. This is achieved with a modular framework comprising a Translator and a Reorderer component. We test our approach on two popular semantic parsing datasets. Our experiments show that by means of the monotonic translations, TPOL can learn reliable lexico-logical patterns from aligned data, significantly improving compositional generalization both over conventional seq2seq models, as well as over other approaches that exploit gold alignments.
