While recent approaches to Natural Language Processing (NLP) based on machine learning from large quantities of data have delivered valuable technology, this success has obscured earlier, more visionary goals of getting computers to understand stories, to engage in natural, cooperative dialogues with people, and to translate text and speech fluently and accurately from one human language to another. As such, this workshop highlights the value of bringing these early visionary goals back into view.
The workshop features established researchers who carried out early work in a major sub-field of speech and language processing engaging in a moderated public dialogue with younger researchers involved with significant new ideas and/or methods. The workshop is organized into four sessions, each with a moderator and invited speakers, on the topics of Dialogue and Speech, Natural Language Generation, Text Understanding, and Grounded Language. Dialogue in each session is enriched through questions solicited beforehand from prospective attendees, as well as impromptu questions from the audience. The workshop includes graduate student scribes who collaborate to deliver a summary of each session, and a poster session highlights the students' research. In addition to the workshop proceedings, the workshop's outcome is a public report based on notes contributed by the speakers and the session summaries produced by the team of student scribes.