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 2107.09846cs.CL
收藏

引导产生因果

Guided Generation of Cause and Effect

Zhongyang Li, Xiao Ding, Ting Liu, J. Edward Hu, Benjamin Van Durme

摘要:

我们提出了一个有条件的文本生成框架,假定可能的原因和影响的原始表达式。这个框架取决于两个新的资源,我们在这项工作的过程中开发:一个非常大规模的收集英语句子表达因果模式CauseBank;和一个完善以前的工作,构建大型词汇因果知识图谱因果图。此外,我们扩展以前的工作在词汇约束的解码,以支持析取正约束。人工评估证实,我们的方法提供了高质量和多样化的输出。最后,我们使用CauseBank对支持最近最先进的因果推理模型的编码器进行持续训练,从而在模型架构没有变化的情况下,对COPA挑战集进行了3点改进。

英文摘要:

We present a conditional text generation framework that posits sentential expressions of possible causes and effects. This framework depends on two novel resources we develop in the course of this work: a very large-scale collection of English sentences expressing causal patterns CausalBank; and a refinement over previous work on constructing large lexical causal knowledge graphs Cause Effect Graph. Further, we extend prior work in lexically-constrained decoding to support disjunctive positive constraints. Human assessment confirms that our approach gives high-quality and diverse outputs. Finally, we use CausalBank to perform continued training of an encoder supporting a recent state-of-the-art model for causal reasoning, leading to a 3-point improvement on the COPA challenge set, with no change in model architecture.

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。

↑