Abstract
A long-term goal of Artificial Intelligence (AI) is to provide machines with the capability of understanding natural language. Understanding natural language may be referred as the system must produce a correct response to the received input order. This response can be a robot move, an answer to a question, etc. One way to achieve this goal is semantic parsing. It parses utterances into semantic representations called logical form, a representation of many important linguistic phenomena that can be understood by machines. Semantic parsing is a fundamental problem in natural language understanding area. In recent years, researchers have made tremendous progress in this field. In this paper, we review recent algorithms for semantic parsing including both conventional machine learning approaches and deep learning approaches. We first give an overview of a semantic parsing system, then we summary a general way to do semantic parsing in statistical learning. With the rise of deep learning, we will pay more attention on the deep learning based semantic parsing, especially for the application of Knowledge Base Question Answering (KBQA). At last, we survey several benchmarks for KBQA.
Highlights
Enabling machines to understand natural language with big challenge and huge promising future, has attracted so many attention in the last few decades
Before we introduce the formal language for semantic parsing, let us give some examples of some pairs of utterance-action pairs (Table 1)[2]
We investigate a unified learning algorithm[28] to induce semantic parsing which is related to loss-sensitive structured perceptron[44]
Summary
Enabling machines to understand natural language with big challenge and huge promising future, has attracted so many attention in the last few decades. Semantic parsing has been widely adopted for language reasoning and question answering with knowledge base[1]. Big Data Mining and Analytics, December 2019, 2(4): 217–239 interface to a database about moon rocks, and SHRDLU, a toy blocks world environment, could both answer questions and perform actions[4] These systems achieved significant achievements in the early time. This paper is structured as follows: we will present a general framework for statistical semantic parsing in Section 2[2] This framework is gratifying modular and can be easy to be extended for conventional statistical learning algorithms with hand-crafted features (Section 3).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
