| Author Name | Affiliation | | Hengsheng Wan | College of Mechanical & Electrical Engineering, Central South University, Changsha 410083, China
State Key Laboratory for High Performance Complex Manufacturing, Changsha 410083, China | | Zhengang Zhang | College of Mechanical & Electrical Engineering, Central South University, Changsha 410083, China | | Jin Ren | College of Mechanical & Electrical Engineering, Central South University, Changsha 410083, China | | Tong Liu | College of Mechanical & Electrical Engineering, Central South University, Changsha 410083, China |
|
| Abstract: |
| Natural language processing has got great progress recently. Controlling robots with spoken natural language has become expectable. With the reliability problem of this kind of control in mind, a confirmation process of natural language instruction should be included before carried out by the robot autonomously; and the prototype dialog system was designed, thus the standardization problem was raised for the natural and understandable language interaction. In the application background of remotely navigating a mobile robot inside a building with Chinese natural spoken language, considering that as an important navigation element in instructions a place name can be expressed with different lexical terms in spoken language, this paper proposes a model for substituting different alternatives of a place name with a standard one (called standardization). First a CRF (Conditional Random Fields) model is trained to label the term required be standardized, then a trained word embedding model is to represent lexical terms as digital vectors. In the vector space similarity of lexical terms is defined and used to find out the most similar one to the term picked out to be standardized. Experiments show that the method proposed works well and the dialog system responses to confirm the instructions are natural and understandable. |
| Key words: word embedding Conditional Random Fields (CRFs) standardization human-robot interaction Chinese Natural Spoken Language (CNSL) Natural Language Processing (NLP) |
| DOI：10.11916/j.issn.1005-9113.17151 |
| Clc Number:TP391.1 |
| Fund: |
|
| Descriptions in Chinese: |
| 基于条件随机场和词向量的机器人指令要素标准化 王恒升1,2，张震钢1，任晋1，刘通1 (1.中南大学 机电工程学院，长沙 410083； 2. 高性能复杂制造国家重点实验室，长沙 410083) 创新点说明：本文针对机器人自然语言人机交互，提出一种对交互指令要素的标准化方法。通过条件随机场从交互指令中提取出指令要素并标注出待标准化要素中的中心词；使用词向量可以表现不同词语之间语义相关程度的特点，完成指令中心词的标准化，实现机器人人机交互过程的自然性；进一步将强化学习应用于标准化过程中阈值的自动设定，有效提高了标准化结果的准确性。 研究目的： 自然语言具有丰富的表现形式，同一意图的机器人自然语言人机交互指令也有多种不同的表达形式，这对机器人正确的指令意图理解提出了挑战。本文为解决这一问题，提出了一种指令要素的标准化方法。 研究方法： 1)训练条件随机场模型，实现自然语言指令的要素提取和待标准化中心词的提取。 2)训练词向量模型，根据其具有分辨语义相关性的特点，完成标准化过程。 3)引入增强学习算法，实现了标准化过程中的阈值自动选取，提高了标准化结果的准确性。 研究结果： 训练的条件随机场模型可有效提取出指令要素中的待标准化词语；在与字符串近似匹配的对比实验中，词向量模型的标准化准确率达到了76.3%；通过增强学习，可以在不牺牲匹配率的情况下将意图识别准确率提高到75.2%。 结论： 实验结果表明，本文方法在机器人自然语言人机交互指令处理中，能有效提高机器人对人的意图理解的准确性，有效提高了人机交互的流畅性和自然性。 关键词：词向量； 条件随机场(CRFs)；标准化；人机交互；中文自然语言口语(CNSL)；自然语言处理(NLP) |
