eXplainable AI (XAI) does not only lie in the interpretation of the rules generated by AI systems, but also in the evaluation and selection, among many rules automatically generated by large datasets, of those that are more relevant and meaningful for domain experts. With this work, we propose a method for evaluation of similarity between rules, which identifies similar rules, or very different ones, by exploiting techniques developed for Natural Language Processing (NLP). We evaluate the similarity of if-then rules by interpreting them as sentences and generating a similarity matrix acting as an enabler for domain experts to analyse the generated rules and thus discover new knowledge. Rule similarity may be applied to rule analysis and manipulation in different scenarios: the first one deals with rule analysis and interpretation, while the second scenario refers to pruning unnecessary rules within a single ruleset. Rule similarity allows also the automatic comparison and evaluation of rulesets. Two different examples are provided to evaluate the effectiveness of the proposed method for rules analysis for knowledge extraction and rule pruning.
Bag-of-Words Similarity in eXplainable AI
Narteni S;Ferretti M;Rampa V;Mongelli M
2022
Abstract
eXplainable AI (XAI) does not only lie in the interpretation of the rules generated by AI systems, but also in the evaluation and selection, among many rules automatically generated by large datasets, of those that are more relevant and meaningful for domain experts. With this work, we propose a method for evaluation of similarity between rules, which identifies similar rules, or very different ones, by exploiting techniques developed for Natural Language Processing (NLP). We evaluate the similarity of if-then rules by interpreting them as sentences and generating a similarity matrix acting as an enabler for domain experts to analyse the generated rules and thus discover new knowledge. Rule similarity may be applied to rule analysis and manipulation in different scenarios: the first one deals with rule analysis and interpretation, while the second scenario refers to pruning unnecessary rules within a single ruleset. Rule similarity allows also the automatic comparison and evaluation of rulesets. Two different examples are provided to evaluate the effectiveness of the proposed method for rules analysis for knowledge extraction and rule pruning.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.anceserie | LECTURE NOTES IN NETWORKS AND SYSTEMS | en |
| dc.authority.orgunit | Istituto di Elettronica e di Ingegneria dell'Informazione e delle Telecomunicazioni - IEIIT | en |
| dc.authority.people | Narteni S | en |
| dc.authority.people | Ferretti M | en |
| dc.authority.people | Rampa V | en |
| dc.authority.people | Mongelli M | en |
| dc.collection.id.s | 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d | * |
| dc.collection.name | 04.01 Contributo in Atti di convegno | * |
| dc.contributor.appartenenza | Istituto di Elettronica e di Ingegneria dell'Informazione e delle Telecomunicazioni - IEIIT | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 877 | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.contributor.area | Non assegn | * |
| dc.date.accessioned | 2024/02/21 03:17:48 | - |
| dc.date.available | 2024/02/21 03:17:48 | - |
| dc.date.firstsubmission | 2025/01/23 16:15:00 | * |
| dc.date.issued | 2022 | - |
| dc.date.submission | 2025/02/21 09:14:42 | * |
| dc.description.abstracteng | eXplainable AI (XAI) does not only lie in the interpretation of the rules generated by AI systems, but also in the evaluation and selection, among many rules automatically generated by large datasets, of those that are more relevant and meaningful for domain experts. With this work, we propose a method for evaluation of similarity between rules, which identifies similar rules, or very different ones, by exploiting techniques developed for Natural Language Processing (NLP). We evaluate the similarity of if-then rules by interpreting them as sentences and generating a similarity matrix acting as an enabler for domain experts to analyse the generated rules and thus discover new knowledge. Rule similarity may be applied to rule analysis and manipulation in different scenarios: the first one deals with rule analysis and interpretation, while the second scenario refers to pruning unnecessary rules within a single ruleset. Rule similarity allows also the automatic comparison and evaluation of rulesets. Two different examples are provided to evaluate the effectiveness of the proposed method for rules analysis for knowledge extraction and rule pruning. | - |
| dc.description.affiliations | Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), National Research Council of Italy (CNR), and Department of Control and Computer Engineering (DAUIN), Politecnico di Torino; Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), National Research Council of Italy (CNR) ; Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), National Research Council of Italy (CNR); Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), National Research Council of Italy (CNR) | - |
| dc.description.allpeople | Narteni, S; Ferretti, M; Rampa, V; Mongelli, M | - |
| dc.description.allpeopleoriginal | Narteni, S; Ferretti, M.; Rampa, V.; Mongelli, M. | en |
| dc.description.fulltext | restricted | en |
| dc.description.note | Proceedings of SAI Intelligent Systems Conference (IntelliSys'22), Sept. 1-2, Amsterdam, The Netherlands, 2022. Link: https://saiconference.com/Conferences/IntelliSys2022. Print ISBN: 978-3-031-16077-6. Online ISBN: 978-3-031-16078-3. | en |
| dc.description.numberofauthors | 4 | - |
| dc.identifier.doi | 10.1007/978-3-031-16078-3_58 | en |
| dc.identifier.isbn | 978-3-031-16078-3 | en |
| dc.identifier.isi | WOS:000890320100058 | en |
| dc.identifier.scopus | 2-s2.0-85138318393 | en |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/415728 | - |
| dc.identifier.url | https://link.springer.com/chapter/10.1007/978-3-031-16078-3_58 | en |
| dc.language.iso | eng | en |
| dc.publisher.country | CHE | en |
| dc.publisher.name | Springer Nature Switzerland | en |
| dc.publisher.place | Basel | en |
| dc.relation.allauthors | Janusz Kacprzyk | en |
| dc.relation.alleditors | Arai, K. | en |
| dc.relation.conferencename | SAI Intelligent Systems Conference 2022 | en |
| dc.relation.firstpage | 835 | en |
| dc.relation.ispartofbook | Intelligent Systems and Applications Proceedings of the 2022 Intelligent Systems Conference (IntelliSys) Volume 2 | en |
| dc.relation.lastpage | 851 | en |
| dc.relation.numberofpages | 17 | en |
| dc.relation.volume | 2 | en |
| dc.subject.keywordseng | eXplainable AI | - |
| dc.subject.keywordseng | Rule similarity | - |
| dc.subject.keywordseng | Cosine similarity | - |
| dc.subject.keywordseng | Bag-of-words | - |
| dc.subject.keywordseng | Physical fatigue detection | - |
| dc.subject.keywordseng | Vehicle platooning | - |
| dc.subject.singlekeyword | eXplainable AI | * |
| dc.subject.singlekeyword | Rule similarity | * |
| dc.subject.singlekeyword | Cosine similarity | * |
| dc.subject.singlekeyword | Bag-of-words | * |
| dc.subject.singlekeyword | Physical fatigue detection | * |
| dc.subject.singlekeyword | Vehicle platooning | * |
| dc.title | Bag-of-Words Similarity in eXplainable AI | en |
| dc.type.driver | info:eu-repo/semantics/conferenceObject | - |
| dc.type.full | 04 Contributo in convegno::04.01 Contributo in Atti di convegno | it |
| dc.type.miur | 273 | - |
| dc.type.referee | Esperti anonimi | en |
| dc.ugov.descaux1 | 470419 | - |
| iris.isi.extIssued | 2023 | - |
| iris.isi.extTitle | Bag-of-Words Similarity in eXplainable AI | - |
| iris.isi.ideLinkStatusDate | 2025/02/19 13:42:28 | * |
| iris.isi.ideLinkStatusMillisecond | 1739968948260 | * |
| iris.mediafilter.data | 2025/12/10 03:53:54 | * |
| iris.orcid.lastModifiedDate | 2025/12/09 15:59:27 | * |
| iris.orcid.lastModifiedMillisecond | 1765292367351 | * |
| iris.scopus.extIssued | 2023 | - |
| iris.scopus.extTitle | Bag-of-Words Similarity in eXplainable AI | - |
| iris.sitodocente.maxattempts | 8 | - |
| iris.unpaywall.doi | 10.1007/978-3-031-16078-3_58 | * |
| iris.unpaywall.isoa | false | * |
| iris.unpaywall.journalisindoaj | false | * |
| iris.unpaywall.metadataCallLastModified | 10/12/2025 03:57:58 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1765335478973 | - |
| iris.unpaywall.oastatus | closed | * |
| isi.authority.anceserie | LECTURE NOTES IN NETWORKS AND SYSTEMS###2367-3370 | * |
| isi.category | EV | * |
| isi.category | EP | * |
| isi.contributor.affiliation | Consiglio Nazionale delle Ricerche (CNR) | - |
| isi.contributor.affiliation | Consiglio Nazionale delle Ricerche (CNR) | - |
| isi.contributor.affiliation | Consiglio Nazionale delle Ricerche (CNR) | - |
| isi.contributor.affiliation | Consiglio Nazionale delle Ricerche (CNR) | - |
| isi.contributor.country | Italy | - |
| isi.contributor.country | Italy | - |
| isi.contributor.country | Italy | - |
| isi.contributor.country | Italy | - |
| isi.contributor.name | Sara | - |
| isi.contributor.name | Melissa | - |
| isi.contributor.name | Vittorio | - |
| isi.contributor.name | Maurizio | - |
| isi.contributor.researcherId | ACW-2577-2022 | - |
| isi.contributor.researcherId | COJ-1891-2022 | - |
| isi.contributor.researcherId | AGR-0073-2022 | - |
| isi.contributor.researcherId | DFY-2820-2022 | - |
| isi.contributor.subaffiliation | Inst Elect Comp & Telecommunicat Engn IEIIT | - |
| isi.contributor.subaffiliation | Inst Elect Comp & Telecommunicat Engn IEIIT | - |
| isi.contributor.subaffiliation | Inst Elect Comp & Telecommunicat Engn IEIIT | - |
| isi.contributor.subaffiliation | Inst Elect Comp & Telecommunicat Engn IEIIT | - |
| isi.contributor.surname | Narteni | - |
| isi.contributor.surname | Ferretti | - |
| isi.contributor.surname | Rampa | - |
| isi.contributor.surname | Mongelli | - |
| isi.date.issued | 2023 | * |
| isi.description.abstracteng | eXplainable AI (XAI) does not only lie in the interpretation of the rules generated by AI systems, but also in the evaluation and selection, among many rules automatically generated by large datasets, of those that are more relevant and meaningful for domain experts. With this work, we propose a method for evaluation of similarity between rules, which identifies similar rules, or very different ones, by exploiting techniques developed for Natural Language Processing (NLP). We evaluate the similarity of if-then rules by interpreting them as sentences and generating a similarity matrix acting as an enabler for domain experts to analyse the generated rules and thus discover new knowledge. Rule similarity may be applied to rule analysis and manipulation in different scenarios: the first one deals with rule analysis and interpretation, while the second scenario refers to pruning unnecessary rules within a single ruleset. Rule similarity allows also the automatic comparison and evaluation of rulesets. Two different examples are provided to evaluate the effectiveness of the proposed method for rules analysis for knowledge extraction and rule pruning. | * |
| isi.description.allpeopleoriginal | Narteni, S; Ferretti, M; Rampa, V; Mongelli, M; | * |
| isi.document.sourcetype | WOS.ISTP | * |
| isi.document.type | Proceedings Paper | * |
| isi.document.types | Proceedings Paper | * |
| isi.identifier.doi | 10.1007/978-3-031-16078-3_58 | * |
| isi.identifier.eissn | 2367-3389 | * |
| isi.identifier.isi | WOS:000890320100058 | * |
| isi.journal.journaltitle | INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 2 | * |
| isi.journal.journaltitleabbrev | LECT NOTE NETW SYST | * |
| isi.language.original | English | * |
| isi.publisher.place | GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND | * |
| isi.relation.firstpage | 835 | * |
| isi.relation.lastpage | 851 | * |
| isi.relation.volume | 543 | * |
| isi.title | Bag-of-Words Similarity in eXplainable AI | * |
| scopus.authority.anceserie | LECTURE NOTES IN NETWORKS AND SYSTEMS###2367-3370 | * |
| scopus.category | 2207 | * |
| scopus.category | 1711 | * |
| scopus.category | 1705 | * |
| scopus.contributor.affiliation | Politecnico di Torino | - |
| scopus.contributor.affiliation | National Research Council of Italy (CNR) | - |
| scopus.contributor.affiliation | National Research Council of Italy (CNR) | - |
| scopus.contributor.affiliation | National Research Council of Italy (CNR) | - |
| scopus.contributor.afid | 60012162 | - |
| scopus.contributor.afid | 60021199 | - |
| scopus.contributor.afid | 60021199 | - |
| scopus.contributor.afid | 60021199 | - |
| scopus.contributor.auid | 57220574684 | - |
| scopus.contributor.auid | 57203499432 | - |
| scopus.contributor.auid | 6603275866 | - |
| scopus.contributor.auid | 7005882346 | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.country | Italy | - |
| scopus.contributor.dptid | - | |
| scopus.contributor.dptid | 104074982 | - |
| scopus.contributor.dptid | 104074982 | - |
| scopus.contributor.dptid | 104074982 | - |
| scopus.contributor.name | Sara | - |
| scopus.contributor.name | Melissa | - |
| scopus.contributor.name | Vittorio | - |
| scopus.contributor.name | Maurizio | - |
| scopus.contributor.subaffiliation | Department of Control and Computer Engineering (DAUIN); | - |
| scopus.contributor.subaffiliation | Institute of Electronics;Computer and Telecommunication Engineering (IEIIT); | - |
| scopus.contributor.subaffiliation | Institute of Electronics;Computer and Telecommunication Engineering (IEIIT); | - |
| scopus.contributor.subaffiliation | Institute of Electronics;Computer and Telecommunication Engineering (IEIIT); | - |
| scopus.contributor.surname | Narteni | - |
| scopus.contributor.surname | Ferretti | - |
| scopus.contributor.surname | Rampa | - |
| scopus.contributor.surname | Mongelli | - |
| scopus.date.issued | 2023 | * |
| scopus.description.abstracteng | eXplainable AI (XAI) does not only lie in the interpretation of the rules generated by AI systems, but also in the evaluation and selection, among many rules automatically generated by large datasets, of those that are more relevant and meaningful for domain experts. With this work, we propose a method for evaluation of similarity between rules, which identifies similar rules, or very different ones, by exploiting techniques developed for Natural Language Processing (NLP). We evaluate the similarity of if-then rules by interpreting them as sentences and generating a similarity matrix acting as an enabler for domain experts to analyse the generated rules and thus discover new knowledge. Rule similarity may be applied to rule analysis and manipulation in different scenarios: the first one deals with rule analysis and interpretation, while the second scenario refers to pruning unnecessary rules within a single ruleset. Rule similarity allows also the automatic comparison and evaluation of rulesets. Two different examples are provided to evaluate the effectiveness of the proposed method for rules analysis for knowledge extraction and rule pruning. | * |
| scopus.description.allpeopleoriginal | Narteni S.; Ferretti M.; Rampa V.; Mongelli M. | * |
| scopus.differences | scopus.publisher.name | * |
| scopus.differences | scopus.subject.keywords | * |
| scopus.differences | scopus.relation.conferencedate | * |
| scopus.differences | scopus.description.allpeopleoriginal | * |
| scopus.differences | scopus.relation.conferencename | * |
| scopus.differences | scopus.identifier.isbn | * |
| scopus.differences | scopus.date.issued | * |
| scopus.differences | scopus.title | * |
| scopus.differences | scopus.relation.volume | * |
| scopus.document.type | cp | * |
| scopus.document.types | cp | * |
| scopus.identifier.doi | 10.1007/978-3-031-16078-3_58 | * |
| scopus.identifier.eissn | 2367-3389 | * |
| scopus.identifier.isbn | 9783031160776 | * |
| scopus.identifier.pui | 639054600 | * |
| scopus.identifier.scopus | 2-s2.0-85138318393 | * |
| scopus.journal.sourceid | 21100901469 | * |
| scopus.language.iso | eng | * |
| scopus.publisher.name | Springer Science and Business Media Deutschland GmbH | * |
| scopus.relation.conferencedate | 2022 | * |
| scopus.relation.conferencename | Intelligent Systems Conference, IntelliSys 2022 | * |
| scopus.relation.firstpage | 835 | * |
| scopus.relation.lastpage | 851 | * |
| scopus.relation.volume | 543 | * |
| scopus.subject.keywords | Bag-of-words; Cosine similarity; eXplainable AI; Physical fatigue detection; Rule similarity; Vehicle platooning; | * |
| scopus.title | Bag-of-Words Similarity in eXplainable AI | * |
| scopus.titleeng | Bag-of-Words Similarity in eXplainable AI | * |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
prod_470419-doc_190831.pdf
solo utenti autorizzati
Descrizione: Bag-of-Words Similarity in eXplainable AI
Tipologia:
Versione Editoriale (PDF)
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
460.69 kB
Formato
Adobe PDF
|
460.69 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
