Inducing latent tree structures from sequential data is an emerging trend in the NLP research landscape today, largely popularized by recent methods such as Gumbel LSTM and Ordered Neurons (ON-LSTM). This paper proposes FASTTREES, a new general purpose neural module for fast sequence encoding. Unlike most previous works that consider recurrence to be necessary for tree induction, our work explores the notion of parallel tree induction, i.e., imbuing our model with hierarchical inductive biases in a parallelizable, non-autoregressive fashion. To this end, our proposed FASTTREES achieves competitive or superior performance to ON-LSTM on four well-established sequence modeling tasks, i.e., language modeling, logical inference, sentiment analysis and natural language inference. Moreover, we show that the FASTTREES module can be applied to enhance Transformer models, achieving performance gains on three sequence transduction tasks (machine translation, subject-verb agreement and mathematical language understanding), paving the way for modular tree induction modules. Overall, we outperform existing state-of-the-art models on logical inference tasks by +4% and mathematical language understanding by +8%.
翻译:从相继数据中引领潜在的树结构,是今天全国木材计划研究景观中出现的一种新趋势,主要为诸如Gumbel LSTM和定序神经(ON-LSTM)等最新方法所推广。本文提出FASTTREES,这是一个用于快速序列编码的新的通用神经神经模块。与以往认为树诱导需要重现的大多数工作不同,我们的工作探索了平行树诱导的概念,即以平行、非自动的方式将我们的模型与等级感应偏差植入一个平行的、非自动的方式。为此,我们提议的FASTTREES在四种既定序列模型任务上,即语言建模、逻辑推断、情绪分析和自然语言推断,取得了竞争或优异性业绩。此外,我们表明,FASTTREES模块可以用来加强变换模型,在三种序列移植任务(机器翻译、主题-verb协议和数学语言理解)上取得绩效收益,为模版树引模模块铺平道路。总体而言,我们用逻辑模型超越了现有状态-%的数学理解,通过逻辑模型,通过数学+4 理解现有状态-理解。