Two special sessions will be held
SummDial: A SIGDial 2021 Special Session on Summarization of Dialogues and Multi-Party Meetings
With a sizeable working population of the world going virtual, resulting in information overload from multiple online meetings, imagine how convenient it would be to just hover over past calendar invites and get concise summaries of the meeting proceedings? How about automatically minuting a multimodal multi-party meeting? Are minutes and multi-party dialogue summaries the same? We believe Automatic Minuting is challenging. There are possibly no agreed-upon guidelines to take minutes, and people adopt different styles to record minutes of the meeting. The minutes also depend on the meeting’s category, the intended audience, and the goal or objective of the meeting.
The SummDial special session at SIGDIAL 2021 intends to instigate discussions on these challenges. Our goal for this SIGDial special session would be to stimulate intense discussions around this topic and set the tone for further interest, research, and collaboration in both Speech and Natural Language Processing communities. We are also launching a shared task on Automatic Minuting (AutoMin) at Interspeech 2021.
SummDial @ SIGDial 2021 will be an all-virtual event on July 29, 2021 at 22:30 Singapore Time.
Registration to SummDial is live now until July 29 (30 SGD).
Recent progress in end-to-end (E2E) open-domain dialogue agents has shown a dramatic improvement in the ability of these models to learn patterns and mimic conversational behaviors from the training data. Unfortunately these models still exhibit many concerning problems. First, they may learn undesirable features present in the training data such as biased, toxic, or otherwise harmful language. Second, they do not respond reliably in safety critical situations, such as the user asking for medical advice, indicating intention of self-harm, or during public health crises such as COVID-19.
These problems are difficult, as what is deemed as “offensive” or even “sensitive” is both contextually and culturally dependent, and picking up on more subtle examples of unsafe language often requires a level of language understanding that is well beyond current capabilities.
A first workshop was held to discuss these topics on October 2020. Following on from that, this special session will take place at SIGDIAL 2021.