Published on Sun Mar 31 2013

A cookbook of translating English to Xapi

Ladislau Bölöni

Xapagy cognitive architecture was designed to model and mimic the activities performed by humans. Xapi is a simplified, "pidgin" language tied to the internal representation model. A trained knowledge engineer can translate between English and Xapi at near-native speed.

0
0
0
Abstract

The Xapagy cognitive architecture had been designed to perform narrative reasoning: to model and mimic the activities performed by humans when witnessing, reading, recalling, narrating and talking about stories. Xapagy communicates with the outside world using Xapi, a simplified, "pidgin" language which is strongly tied to the internal representation model (instances, scenes and verb instances) and reasoning techniques (shadows and headless shadows). While not fully a semantic equivalent of natural language, Xapi can represent a wide range of complex stories. We illustrate the representation technique used in Xapi through examples taken from folk physics, folk psychology as well as some more unusual literary examples. We argue that while the Xapi model represents a conceptual shift from the English representation, the mapping is logical and consistent, and a trained knowledge engineer can translate between English and Xapi at near-native speed.

Tue May 17 2011
Artificial Intelligence
Xapagy: a cognitive architecture for narrative reasoning
The Xapagy cognitive architecture is a software system designed to perform narrative reasoning. The architecture has been designed from scratch to mimic the activities performed by humans when witnessing, reading, recalling, narrating and talking about stories.
0
0
0
Tue Aug 29 2017
NLP
Narrative Variations in a Virtual Storyteller
Fabula Tales is a computational framework for a virtual storyteller that can tell the same story in different ways. The framework is based on very general methods for re-using existing story content, either from fables or personal narratives.
0
0
0
Wed Oct 31 2018
NLP
ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
ATOMIC is an atlas of everyday commonsense reasoning. It focuses on inferential knowledge organized as typed if-then relations with variables. We show that neural models can acquire simple commonsense capabilities.
0
0
0
Thu Jul 08 2021
NLP
A Systematic Survey of Text Worlds as Embodied Natural Language Environments
Text Worlds are virtual environments for embodied agents that are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments due to their low barrier to entry. They provide the ability to study semantics,compositional inference, and other high-level tasks.
3
32
85
Thu Oct 18 2018
Machine Learning
Discourse Embellishment Using a Deep Encoder-Decoder Network
We suggest a new NLG task in the context of the discourse generation pipeline. This task, textual embellishment, is defined by taking a text as input and generating a semantically equivalent output. We present promising first results on this task using LSTM Encoder-Decoder networks.
0
0
0
Tue May 19 2020
Artificial Intelligence
Human-like general language processing
Using language makes human beings surpass animals in wisdom. To let machines understand, learn, and use language flexibly, we propose a human-like general language processing architecture. The HGLP network learns from easy to hard like a child.
0
0
0