@inbook{10818f185dda46b8bb8753032e7f1eed,
title = "The margarita dialogue corpus: A data set for time-offset interactions and unstructured dialogue systems",
abstract = "Time-Offset Interaction Applications (TOIAs) are systems that simulate face-to-face conversations between humans and digital human avatars recorded in the past. Developing a well-functioning TOIA involves several research areas: artificial intelligence, human-computer interaction, natural language processing, question answering, and dialogue systems. The first challenges are to define a sensible methodology for data collection and to create useful data sets for training the system to retrieve the best answer to a user's question. In this paper, we present three main contributions: a methodology for creating the knowledge base for a TOIA, a dialogue corpus, and baselines for single-turn answer retrieval. We develop the methodology using a two-step strategy. First, we let the avatar maker list pairs by intuition, guessing what possible questions a user may ask to the avatar. Second, we record actual dialogues between random individuals and the avatar-maker. We make the Margarita Dialogue Corpus available to the research community. This corpus comprises the knowledge base in text format, the video clips for each answer, and the annotated dialogues.",
keywords = "Annotation, Corpus Creation, Dialogue, Question Answering",
author = "Chierici, {Alberto M.} and Nizar Habash and Margarita Bicec",
note = "Funding Information: We would to thank David Traum for helpful conversations. We also would like to thank the NYUAD TOIA team (Dana Abu Ali, Muaz Ahmad, Hayat Al Hassan, Paula Dozsa, Ming Hu, and Jose Varias) for making the TOIA software they created available to us. Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC",
year = "2020",
language = "English (US)",
isbn = "9791095546344",
series = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "476--484",
booktitle = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
}