XRDS

Crossroads The ACM Magazine for Students

Sign In

Association for Computing Machinery

Articles Tagged: Natural language generation

Articles & Features

SECTION: Features

The Importance of Memory for Language-Capable Robots

Robots need to be able to communicate with people through natural language. But how should their memory systems be designed to facilitate this communication?

By Rafael Sousa Silva, Zhao Han, Tom Williams, October 2023

PDF | HTML | In the Digital Library

Designing AI-Powered Art-Making Tools

We are living in the era of art-making being transformed by rapidly advancing generative AI technologies. With these technologies, what are some approaches to design and build AI-powered art-making tools?

By John Joon Young Chung, June 2023

PDF | HTML | In the Digital Library

COLUMN: INIT

In search of a strategy against misinformation

By Numair Khan, September 2020

PDF | HTML | In the Digital Library

SECTION: Features

OpenGPT-2

When OpenAI released its billion-parameter language model GPT-2, their attempts to withhold the model inspired two researchers to use open research practices to combat the misuse of machine learning.

By Vanya Cohen, Aaron Gokaslan, September 2020

PDF | HTML | In the Digital Library

Towards a user-friendly semantic formalism for natural language generation

Computational semantics has become an interesting and important branch of computational linguistics. Born from the fusion of formal semantics and computer science, it is concerned with the automated processing of meaning associated with natural language expressions [2]. Systems of semantic representation, hereafter referred to as semantic formalisms, exist to describe meaning underlying natural language expressions. To date, several formalisms have been defined by researchers from a number of diverse disciplines including philosophy, logic, psychology and linguistics. These formalisms have a number of different applications in the realm of computer science. For example, in machine translation a sentence could be parsed and translated into a series of semantic expressions, which could then be used to generate an utterance with the same meaning in a different language [14]. This paper presents two existing formalisms and examines their user-friendliness. Additionally, a new form of semantic representation is proposed with wide coverage and user-friendliness suitable for a computational linguist.

By Craig Thomas, December 2008

PDF | HTML | In the Digital Library