用于语音识别中声学建模的深度神经网络近年来,深度学习技术已经在各种分类和识别问题中获得了许多现成的结果(Krizhevsky et al。,2012; Hinton et al。,2012; Kim,2014)。然而,复杂的自然语言处理问题通常需要多个相互关联的决策,并且赋予深度学习模型以学习理性的能力仍然是一个具有挑战性的问题。为了处理没有明显答案的复杂查询,智能机器必须能够推理现有资源,并学会推断未知答案。

更具体地说,我们把我们的研究放在多跳推理的环境中,给出一个大的KG,这是学习显式推理公式的任务。例如,如果KG包含诸如Neymar为巴塞罗那出战的信念,而巴塞罗那在西甲联赛中,那么机器应该能够学习以下公式:playerPlaysForTeam(P,T)∧teamPlaysInLeague(T,L)⇒ playerPlaysInLeague(P,L)。在测试时间内,通过插入学习公式,系统应该能够自动推断一对实体之间的缺失链接。这种推理机可能会成为复杂QA系统的重要组成部分

近年来,路径排序算法(PRA)(Lao et al。,2010,2011a)成为大型幼儿园学习推理路径的一种有前途的方法。PRA使用基于重启的基于推理机制的随机游走来执行多个有界深度优先搜索过程来查找关系路径。加上基于弹性网络的学习,PRA然后使用监督式学习选择更合理的路径。然而,PRA在完全独立的空间中运作,这使得评估和比较KG中类似的实体和关系变得困难。
Continue reading

We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based algorithm and knowledge graph embedding methods on Freebase and Never-Ending Language Learning datasets.1

1 Introduction

Deep neural networks for acoustic modeling in speech recognitionIn recent years, deep learning techniques have obtained many state-of-theart results in various classification and recognition problems (Krizhevsky et al., 2012; Hinton et al., 2012; Kim, 2014). However, complex natural language processing problems often require multiple inter-related decisions, and empowering deep learning models with the ability of learning to reason is still a challenging issue. To handle complex queries where there are no obvious answers, intelligent machines must be able to reason with existing resources, and learn to infer an unknown answer.

More specifically, we situate our study in the context of multi-hop reasoning, which is the task of learning explicit inference formulas, given a large KG. For example, if the KG includes the beliefs such as Neymar plays for Barcelona, and Barcelona are in the La Liga league, then machines should be able to learn the following formula: playerPlaysForTeam(P,T) ∧ teamPlaysInLeague(T,L) ⇒ playerPlaysInLeague(P,L). In the testing time, by plugging in the learned formulas, the system should be able to automatically infer the missing link between a pair of entities. This kind of reasoning machine will potentially serve as an essential components of complex QA systems

Continue reading





• 机器的语言理解

Continue reading

Can machine think like

Language is the tool of thinking

It is the ability of language speaking and understanding that distinguish us from animals
Enabling machine to understand human language is the essential path to realize intelligent information processing and smart robot brain.

Obstacles of machine language
• Language understanding of machines
needs knowledge bases
• Large scale
• Semantically rich
• Friendly structure
• Traditional knowledge representations
can not satisfy these requirements
• Ontology
• Semantic network
• Texts

Continue reading