论文标题
开放域表的逻辑自然语言生成
Logical Natural Language Generation from Open-Domain Tables
论文作者
论文摘要
神经自然语言产生（NLG）模型最近显示出流利度和连贯性的显着进步。但是，现有的关于神经NLG的研究主要集中在表面级别的实现上，重点是逻辑推断，这是人类思维和语言的重要方面。在本文中，我们建议一项新的NLG任务，其中模型的任务是生成可以通过开放域半结构化表中的事实来生成可以\ emph {逻辑上的}的自然语言语句。为了促进对拟议的逻辑NLG问题的研究，我们将现有的TABFACT数据集\ cite \ cite {Chen2019TabFact}作为测试台，并提出了广泛的逻辑/符号推理，并提出了新的自动指标来评估生成型号W.R.R.T. w.r.t. \ logical logical forical flogical flogical flogical flogical flogical \ forigical flogical的限制。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构成了挑战。 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)粗到最新的生成可以帮助部分缓解忠诚的问题，同时保持高语言流利性。代码和数据可在\ url {https://github.com/wenhuchen/logicnlg}上获得。
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}.
