arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02486cs.CL
收藏

基于概率世界构建的一般自然语言理解

Towards General Natural Language Understanding with Probabilistic Worldbuilding

Carnegie Mellon University(卡内基梅隆大学)

Abulhair Saparov, Tom M. Mitchell

摘要:

我们引入概率世界构建模型(PWM),一个新的完全符号化的贝叶斯语义解析和推理模型,作为研究计划的第一步,走向更多的领域和任务一般的NLU和AI。人类创造了他们观察的内部心理模型,这大大有助于他们理解和推理各种问题的能力。在PWM中,句子的含义,关于世界的已获取事实,以及推理的中间步骤都以人类可读的形式语言表示,其设计目标是可解释性。PWM是贝叶斯的,专门设计为能够推广到新的领域和新的任务。我们推导并实现了一个推理算法,该算法通过解析和推导更新其潜在的世界模型来读取句子,该模型捕获这些句子的语义,并在两个域外问答数据集上对其进行评估:(1)ProofWriter和(2)一个新的数据集,我们称之为FictionalGeoQA,旨在更能代表真实语言,但仍然足够简单,可以专注于评估推理能力,同时还能抵抗寄生虫。我们的方法在这两个方面都优于基线,从而证明了其作为概念验证的价值。

英文摘要:

We introduce the Probabilistic Worldbuilding Model (PWM), a new fully-symbolic Bayesian model of semantic parsing and reasoning, as a first step in a research program toward more domain- and task-general NLU and AI. Humans create internal mental models of their observations which greatly aid in their ability to understand and reason about a large variety of problems. In PWM, the meanings of sentences, acquired facts about the world, and intermediate steps in reasoning are all expressed in a human-readable formal language, with the design goal of interpretability. PWM is Bayesian, designed specifically to be able to generalize to new domains and new tasks. We derive and implement an inference algorithm that reads sentences by parsing and abducing updates to its latent world model that capture the semantics of those sentences, and evaluate it on two out-of-domain question-answering datasets: (1) ProofWriter and (2) a new dataset we call FictionalGeoQA, designed to be more representative of real language but still simple enough to focus on evaluating reasoning ability, while being robust against heuristics. Our method outperforms baselines on both, thereby demonstrating its value as a proof-of-concept.

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。

↑