Mitigating bias in deep nets with knowledge bases: The case of natural language understanding for robots

Martino Mensio, Emanuele Bastianelli, Ilaria Tiddi, Giuseppe Rizzo

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

In this paper, we tackle the problem of lack of understandability of deep learning systems by integrating heterogeneous knowledge sources, and in the specific we present how we used FrameNet to guarantee the correct learning for an LSTM-based semantic parser in the task of Spoken Language Understanding for robots. The problem of the explainability of Artificial Intelligence (AI) systems, i.e. their ability to explain decisions to both experts and end users, has attracted growing attention in the latest years, affecting their credibility and trustworthiness. Trusting these systems is fundamental in the context of AI-based robotic companions interacting in natural language, as the users’ acceptance of the robot also relies on the ability to explain the reasons behind its actions. Following similar approaches, we first use the values of the neural attention layers employed in the semantic parser as a clue to analyze and interpret the model’s behavior and reveal the intrinsic bias induced by the training data. We then show how the integration of knowledge from external resources such as FrameNet can help minimizing, or mitigating, such bias, and consequently guarantee the model to provide the correct interpretations. Our preliminary, but promising results suggest that (i) attention layers can improve the model understandability; (ii) the integration of different knowledge bases can help overcoming the limitations of machine learning models; and (iii) an approach combining the strengths of both knowledge engineering and machine learning can foster the development of more transparent, understandable intelligent systems.

Original languageEnglish
Title of host publicationAAAI-MAKE 2020 Combining Machine Learning and Knowledge Engineering in Practice - Volume I: Spring Symposium
Subtitle of host publicationProceedings of the AAAI 2020 Spring Symposium on Combining Machine Learning and Knowledge Engineering in Practice (AAAI-MAKE 2020) - Volume I Stanford University, Palo Alto, California, USA, March 23-25, 2020
EditorsAndreas Martin, Knut Hinkelmann, Hans-Georg Fill, Aurona Gerber, Doug Lenat, Reinhard Stolle, Frank van Harmelen
PublisherCEUR-WS.org
Chapter20
Pages1-9
Number of pages9
Volume1
Publication statusPublished - 5 May 2020
Event2020 AAAI Spring Symposium on Combining Machine Learning and Knowledge Engineering in Practice, AAAI-MAKE 2020 - Palo Alto, United States
Duration: 23 Mar 202025 Mar 2020

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR Workshop Proceedings
Volume2600
ISSN (Print)1613-0073

Conference

Conference2020 AAAI Spring Symposium on Combining Machine Learning and Knowledge Engineering in Practice, AAAI-MAKE 2020
CountryUnited States
CityPalo Alto
Period23/03/2025/03/20

Fingerprint Dive into the research topics of 'Mitigating bias in deep nets with knowledge bases: The case of natural language understanding for robots'. Together they form a unique fingerprint.

Cite this