computational linguisticscorpus-based methodsmachine translationstatistical methodssymbolic parsing
Figures from the paper
Abstract (AI)
Abstract Computational linguistics grew out of early projects in machine translation. Initially it was conceived of as a branch of artificial intelligence with the goal of complete human-like language understanding, and was concerned with symbolic methods of parsing and semantic analysis. In recent years, because of more powerful computers, the development of machine-learning algorithms, and the rise of the World Wide Web, computational linguistics has taken an empiricist view of language processing that is based on corpora and statistical methods. It emphasizes practical applications with a tolerance for some degree of error.
Key Findings
1
Computational linguistics originated from machine translation projects and was initially framed as AI aiming for complete human-like language understanding.
2
Early approaches emphasized symbolic methods of parsing and semantic analysis.
3
Recent developments shifted the field toward empiricist, corpus-based and statistical methods due to more powerful computers, machine-learning algorithms, and the World Wide Web.
4
The modern field prioritizes practical applications and accepts some degree of error compared to earlier idealized goals.
Research Object
Computational linguistics as a scientific field and practice
Research Subject
The paradigms, methods, and aims of computational linguistics—transition from symbolic AI-based parsing and semantic analysis toward corpus-based, statistical, and machine-learning approaches and their practical application trade-offs
Publication Details
Publication Date
2013-07-01
Journal
Publisher
ISSN
Access Type
Author Information
Download PDF
Subscribe to digest