arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.10404cs.CLcs.AI
收藏

从开域表生成逻辑自然语言

Logical Natural Language Generation from Open-Domain Tables

University of California Santa Barbara(加州大学圣巴巴拉分校);Tencent AI Lab(腾讯人工智能实验室);The Ohio State University(俄亥俄州立大学)

Wenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen, William Yang Wang

摘要:

神经自然语言生成(NLG)模型最近在流畅性和连贯性方面取得了显著的进展。然而,现有的神经NLG的研究主要集中在表面水平的实现与有限的重视逻辑推理,人类思维和语言的一个重要方面。在本文中,我们提出了一个新的NLG任务,模型的任务是生成自然语言语句,可以是\emph{logically entailed}的事实在一个开放域的半结构化表。为了便于研究所提出的逻辑NLG问题,我们使用现有的TabFact数据集\cite{chen2019tabfact}具有广泛的逻辑/符号推理作为我们的测试床,并提出新的自动度量来评估生成模型的保真度w.r.t.逻辑推理由于序列顺序和逻辑顺序之间的不匹配,新任务对现有的单调生成框架提出了挑战。在我们的实验中,我们全面调查了不同的生成架构,(LSTM、Transformer、Pre-Trained LM)使用不同算法训练(RL,对抗训练,从粗到精),并进行了以下观察:1)预先训练的LM可以显著提高流畅性和逻辑保真度指标,2)RL和对抗训练是为了保真度而交易流畅性,3)从粗到精的生成可以部分缓解保真度问题,同时保持较高的语言流畅性。代码和数据可在\url{https://github.com/wenhuchen/LogicNLG}上获得。

英文摘要:

Neural natural language generation (NLG) models have recently shown remarkable progress in fluency and coherence. However, existing studies on neural NLG are primarily focused on surface-level realizations with limited emphasis on logical inference, an important aspect of human thinking and language. In this paper, we suggest a new NLG task where a model is tasked with generating natural language statements that can be \emph{logically entailed} by the facts in an open-domain semi-structured table. To facilitate the study of the proposed logical NLG problem, we use the existing TabFact dataset \cite{chen2019tabfact} featured with a wide range of logical/symbolic inferences as our testbed, and propose new automatic metrics to evaluate the fidelity of generation models w.r.t.\ logical inference. The new task poses challenges to the existing monotonic generation frameworks due to the mismatch between sequence order and logical order. In our experiments, we comprehensively survey different generation architectures (LSTM, Transformer, Pre-Trained LM) trained with different algorithms (RL, Adversarial Training, Coarse-to-Fine) on the dataset and made following observations: 1) Pre-Trained LM can significantly boost both the fluency and logical fidelity metrics, 2) RL and Adversarial Training are trading fluency for fidelity, 3) Coarse-to-Fine generation can help partially alleviate the fidelity issue while maintaining high language fluency. The code and data are available at \url{https://github.com/wenhuchen/LogicNLG}.

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。

↑