Details
| Original language | English |
|---|---|
| Title of host publication | 2022 Proceedings - International Conference on Computational Linguistics, COLING |
| Pages | 344-354 |
| Number of pages | 11 |
| Volume | 29 |
| Edition | 1 |
| Publication status | Published - 2022 |
| Externally published | Yes |
| Event | 29th International Conference on Computational Linguistics, COLING 2022 - Gyeongju, Korea, Republic of Duration: 12 Oct 2022 → 17 Oct 2022 |
Publication series
| Name | Proceedings - International Conference on Computational Linguistics, COLING (Online) |
|---|---|
| Publisher | Association for Computational Linguistics (ACL) |
| ISSN (Print) | 2951-2093 |
Abstract
As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions. Most research on explainable AI builds on the premise that there is one ideal explanation to be found. In fact, however, everyday explanations are co-constructed in a dialogue between the person explaining (the explainer) and the specific person being explained to (the explainee). In this paper, we introduce a first corpus of dialogical explanations to enable NLP research on how humans explain as well as on how AI can learn to imitate this process. The corpus consists of 65 transcribed English dialogues from the Wired video series 5 Levels, explaining 13 topics to five explainees of different proficiency. All 1550 dialogue turns have been manually labeled by five independent professionals for the topic discussed as well as for the dialogue act and the explanation move performed. We analyze linguistic patterns of explainers and explainees, and we explore differences across proficiency levels. BERT-based baseline results indicate that sequence information helps predicting topics, acts, and moves effectively.
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
- Mathematics(all)
- Theoretical Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2022 Proceedings - International Conference on Computational Linguistics, COLING. Vol. 29 1. ed. 2022. p. 344-354 (Proceedings - International Conference on Computational Linguistics, COLING (Online)).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - “Mama Always Had a Way of Explaining Things So I Could Understand”
T2 - 29th International Conference on Computational Linguistics, COLING 2022
AU - Wachsmuth, Henning
AU - Alshomary, Milad
N1 - Funding information: This work has been supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), partially under project number TRR 318/1 2021 – 438445824 and partially under SFB 901/3 – 160364472. We thank Meisam Booshehri, Hendrik Buschmeier, Philipp Cimiano, Josephine Fisher, Angela Grimminger, and Erick Ronoh for their input and feedback to the annotation scheme. We also thank Akshit Bhatia for his help with the corpus preparation as well as the anonymous freelancers on Upwork for their annotations.
PY - 2022
Y1 - 2022
N2 - As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions. Most research on explainable AI builds on the premise that there is one ideal explanation to be found. In fact, however, everyday explanations are co-constructed in a dialogue between the person explaining (the explainer) and the specific person being explained to (the explainee). In this paper, we introduce a first corpus of dialogical explanations to enable NLP research on how humans explain as well as on how AI can learn to imitate this process. The corpus consists of 65 transcribed English dialogues from the Wired video series 5 Levels, explaining 13 topics to five explainees of different proficiency. All 1550 dialogue turns have been manually labeled by five independent professionals for the topic discussed as well as for the dialogue act and the explanation move performed. We analyze linguistic patterns of explainers and explainees, and we explore differences across proficiency levels. BERT-based baseline results indicate that sequence information helps predicting topics, acts, and moves effectively.
AB - As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions. Most research on explainable AI builds on the premise that there is one ideal explanation to be found. In fact, however, everyday explanations are co-constructed in a dialogue between the person explaining (the explainer) and the specific person being explained to (the explainee). In this paper, we introduce a first corpus of dialogical explanations to enable NLP research on how humans explain as well as on how AI can learn to imitate this process. The corpus consists of 65 transcribed English dialogues from the Wired video series 5 Levels, explaining 13 topics to five explainees of different proficiency. All 1550 dialogue turns have been manually labeled by five independent professionals for the topic discussed as well as for the dialogue act and the explanation move performed. We analyze linguistic patterns of explainers and explainees, and we explore differences across proficiency levels. BERT-based baseline results indicate that sequence information helps predicting topics, acts, and moves effectively.
UR - http://www.scopus.com/inward/record.url?scp=85165788714&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85165788714
VL - 29
T3 - Proceedings - International Conference on Computational Linguistics, COLING (Online)
SP - 344
EP - 354
BT - 2022 Proceedings - International Conference on Computational Linguistics, COLING
Y2 - 12 October 2022 through 17 October 2022
ER -