论文标题
基于跨度的语义解析组成概括
Span-based Semantic Parsing for Compositional Generalization
论文作者
论文摘要
尽管在语义解析中取得了序列到序列（SEQ2SEQ）模型的成功，但最近的工作表明，它们在构图概括中未能通过概括到训练过程中观察到的组件构建的新结构的能力。在这项工作中，我们认为基于跨度的解析器应导致更好的组成概括。我们提出了SpanBasateSP，这是一种解析器，可以通过输入话语预测跨度树，明确编码部分程序在输入中的跨度上的组成。 SpanbasateSP扩展了Pasupat等。 （2019年）可以通过（i）从程序中培训，无需获得金树，将树视为潜在变量，（ii）通过扩展到标准CKY来解析一类非项目的树。在GeoQuery，扫描和闭合数据集上，SpanBasedSP在随机分裂上的强度SEQ2SEQ基准类似，但是与需要组成概括的基线相比，相比之下，性能显着提高：从61.0美元\ rightarrow 88.9 $平均准确度。
Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of components observed during training. In this work, we posit that a span-based parser should lead to better compositional generalization. we propose SpanBasedSP, a parser that predicts a span tree over an input utterance, explicitly encoding how partial programs compose over spans in the input. SpanBasedSP extends Pasupat et al. (2019) to be comparable to seq2seq models by (i) training from programs, without access to gold trees, treating trees as latent variables, (ii) parsing a class of non-projective trees through an extension to standard CKY. On GeoQuery, SCAN and CLOSURE datasets, SpanBasedSP performs similarly to strong seq2seq baselines on random splits, but dramatically improves performance compared to baselines on splits that require compositional generalization: from $61.0 \rightarrow 88.9$ average accuracy.
