Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar
Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar
复制标题
DOI：
10.18653/v1/n19-1377
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Wenchao Du;A. Black
中科院分区：
文献类型：
--
作者：
Wenchao Du;A. Black
我们考虑在新问题设置下的神经语言生成：根据单词在词汇化 PCFG 解析树中首次出现的顺序，以深度优先、从左到右的方式生成句子的单词。与之前基于树的语言生成方法不同，我们的方法是（i）自上而下和（ii）同时显式生成句法结构。此外，我们的方法将神经模型与符号方法相结合：每一步的单词选择都受到其预测句法功能的约束。我们将我们的模型应用于对话响应生成的任务，发现它在多样性和相关性方面显着优于序列到序列的基线。我们还研究了词汇化对语言生成的影响，发现优先考虑实词的词汇化方案比关注依存关系的词汇化方案具有一定的优势。
We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-right manner. Unlike previous tree-based language generation methods, our approach is both (i) top-down and (ii) explicitly generating syntactic structure at the same time. In addition, our method combines neural model with symbolic approach: word choice at each step is constrained by its predicted syntactic function. We applied our model to the task of dialog response generation, and found it significantly improves over sequence-to-sequence baseline, in terms of diversity and relevance. We also investigated the effect of lexicalization on language generation, and found that lexicalization schemes that give priority to content words have certain advantages over those focusing on dependency relations.