LACATODA 2021, August 21


UTC 1:25-1:30AM (opening)

(Sweden: 3:25-3:30AM, Cyprus: 4:25-4:30AM, India: 6:55-7:00AM, Japan: 10:25-10:30AM)

UTC 1:30-2:30AM (invited lecture)

(Sweden: 3:30-4:30AM, Cyprus: 4:30-5:30AM, India: 7:00-8:00AM, Japan: 10:30-11:30AM)

Takamasa Iio
"Know-how on scenario creation for interactive robot systems"

UTC 2:30-2:45AM (break)

(Sweden: 4:30-4:45AM, Cyprus: 5:30-5:45AM, India: 8:00-8:15AM, Japan: 11:30-11:45AM)

UTC 2:45-3:00AM (short talk)

(Sweden: 4:45-5:00AM, Cyprus: 5:45-6:00AM, India: 8:45-9:00AM Japan: 11:45-12:00AM)

Akihiko Obayashi and Rafal Rzepka

"Annotated Question and Answer Dataset for Security Export Control" [SLIDES]

UTC 3:00-3:30AM (long talk)

(Sweden: 5:00-5:30AM, Cyprus: 6:00-6:30AM, India: 8:30-9:00AM, Japan:12:00-12:30PM)

Juuso Eronen, Michal Ptaszynski, Fumito Masui, Gniewosz Leliwa and Michal Wroczynski

"Exploring the Potential of Feature Density in Estimating Machine Learning Classifier Performance with Application to Cyberbullying Detection"

UTC 3:30-4:00AM (long talk)

(Sweden: 5:30-6:30AM, Cyprus: 6:30-7:00AM, India: 9:00-9:30AM, Japan:12:30-13:00PM)

Midhush Manohar Thevendria Karthic, Ninaad Rao, Nishant Ravi Shankar and Dr. Ramamoorthy Srinath

"HumourSpace: A Novel Framework for Quantification and Characterisation of Humour" [SLIDES]

UTC 4:00-4:30AM (break)

(Sweden: 6:00-6:30AM, Cyprus:7:00-7:30AM, India: 9:30-10:00AM, Japan: 1:00-1:30PM)

UTC 4:30AM-5:30 (invited talk)

(Sweden: 6:30-7:30AM, Cyprus: 7:30-8:30AM, India: 10:00-11:00AM, Japan: 1:30-2:30PM)

Ryuichiro Higashinaka

"Challenges for chat-oriented dialogue systems ---Experience from the dialogue breakdown detection challenge and the dialogue system live competition---" [VIDEO] [SLIDES]

UTC 5:30-6:00AM (long talk)

(Sweden: 7:30-8:00AM, Cyprus: 8:30-9:00AM, India:11:00-11:30AM, Japan: 2:30-3:00PM)

Christodoulos Ioannou and Loizos Michael

"Knowledge-Based Translation of Natural Language into Symbolic Form" [SLIDES]

UTC 6:00-6:30AM (long talk)

(Sweden:8:00-8:30AM, Cyprus: 9:00-9:30AM, India: 11:30-12:00AM, Japan: 3:00-3:30PM)

Vladislav Maraev, Jean-Philippe Bernardy and Christine Howes

"Non-humorous use of laughter in spoken dialogue systems"

Invited Talk Abstract

Although many chat-oriented dialogue systems are emerging and showing promising results, their performance is still limited and the dialogue with a system often breaks down. To counter dialogue breakdowns, I have been leading dialogue breakdown detection challenges, the aim of which is to develop algorithms to detect inappropriate utterances by the system so that dialogue breakdowns can be avoided. In this talk, I will go over the past challenges and mention the current performance of dialogue breakdown detection and the types of errors that still need to be tackled. In addition, I will describe the dialogue system live competitions that I have also been involved with, in which the audience, consisting mainly of researchers in the dialogue community, watch and evaluate a live dialogue conducted between users and dialogue systems. The motivation behind the event is to cultivate state-of-the-art techniques in chat-oriented dialogue systems and enable the dialogue community to share the problems with current dialogue systems. I will talk about the lessons learnt from organizing the event and mention possible directions for the dialogue systems community.

Invited Speaker’s Bio

Ryuichiro Higashinaka received his B.A. degree in Environmental Information, Masters in Media and Governance, and Ph.D. from Keio University, Kanagawa, in 1999, 2001, and 2008, respectively. He joined NTT corporation in 2001. He is currently a professor at Nagoya University. He is a visiting senior distinguished researcher at NTT Media Intelligence Laboratories. His research interests include building question-answering systems and spoken-dialogue systems. From November 2004 to March 2006, he was a visiting researcher at the University of Sheffield, UK. He received the “Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology” in 2016. He was a program co-chair for SIGDIAL2016. Since 2017, he has been serving the SIGdial board. He has worked as area chair (dialogue and interactive systems track) for ACL2019/2020/2021, EMNLP2019, and NAACL2021.

Invited Lecture Abstract

There has been much research on social robots that provide information while conversing with people in public facilities and homes. I have developed and demonstrated various robot systems, including a guide robot that explains exhibits at a science museum, a care robot that chats with older adults at a nursing home, and entertainment robots that discuss human nature with people at an event. In terms of time and cost, such demonstrations in real-world environments prefer old-fashioned but robust methods (e.g., dialogue management based on manual scenarios) rather than sophisticated methods (e.g., state-of-the-art machine learning technology). As a result of my involvement in those projects, I have acquired the know-how to create scenarios for human-robot interaction. That know-how may be insignificant in this AI era, but it can be helpful to implement interactive robots working in the real world quickly. In this talk, I will talk about this know-how.

Invited Lecturer's Bio

Takamasa Iio received a Ph.D. degree from Doshisha University, Kyoto, Japan, in 2012. Then, he has worked at Intelligent Robotics and Communication Laboratories, ATR, Osaka University, and the University of Tsukuba. Currently, he is an associate professor at Doshisha University, Kyoto, Japan. His field of expertise is social robotics. He is interested in how people's cognition and behavior change through interaction with social robots and how human society changes.

CEUR Proceedings: