DeepAI AI Chat
Log In Sign Up

End-to-End Rationale Reconstruction

by   Mouna Dhaouadi, et al.

The logic behind design decisions, called design rationale, is very valuable. In the past, researchers have tried to automatically extract and exploit this information, but prior techniques are only applicable to specific contexts and there is insufficient progress on an end-to-end rationale information extraction pipeline. Here we outline a path towards such a pipeline that leverages several Machine Learning (ML) and Natural Language Processing (NLP) techniques. Our proposed context-independent approach, called Kantara, produces a knowledge graph representation of decisions and of their rationales, which considers their historical evolution and traceability. We also propose validation mechanisms to ensure the correctness of the extracted information and the coherence of the development process. We conducted a preliminary evaluation of our proposed approach on a small example sourced from the Linux Kernel, which shows promising results.


Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text

We present an end-to-end approach that takes unstructured textual input ...

An End-To-End Machine Learning Pipeline That Ensures Fairness Policies

In consequential real-world applications, machine learning (ML) based sy...

Occode: an end-to-end machine learning pipeline for transcription of historical population censuses

Machine learning approaches achieve high accuracy for text recognition a...

Multilingual Medical Question Answering and Information Retrieval for Rural Health Intelligence Access

In rural regions of several developing countries, access to quality heal...

Zap: Making Predictions Based on Online User Behavior

This paper introduces Zap, a generic machine learning pipeline for makin...