Tutorial (09:00 EST) Session Chair: Joshua Maynez
Morning Coffee (10:45 EST)
Lunch (13:00 EST)
Workshop (14:00 EST) Session Chair: Ehud Reiter
Afternoon Coffee (15:45 EST)
Opening Reception (18:00 EST)
Zoom Walk along the Kennebec (07:00 EST)
Keynote 1 (09:00 EST) Session Chair: Ehud Reiter
  • Advancing Natural Language Generation (for better or worse)
    Margaret Mitchell
Morning Coffee (10:00 EST)
Panel on Ethics in NLG (10:30 EST)
SIGGEN Session (12:00 EST)
Lunch (13:00 EST)
Oral Session 1 (14:00 EST) Session Chair: Amanda Stent
Afternoon Coffee (15:30 EST)
Demo/Poster Session 1 Survey (16:00 EST)
Demo/Poster Session 1 (16:30 EST)
Zoom Chat and BYO Coffee/Tea (07:00 EST)
Keynote 2 (09:00 EST) Session Chair: Amanda Stent
  • NLG for Human-Robot Interaction: Challenges and Opportunities
    Dimitra Gkatzia
    Human-robot interaction (HRI) focuses on researching the interaction between humans and (mostly) physical robots. Despite the media coverage of robots displaying human-level capabilities in conversational dialogue and NLG, in reality, such robots use simple template-based approaches and follow pre-scripted interactions. In this talk, I will initially provide an overview of current approaches to NLG for HRI focusing on the limitations of current approaches and emphasising the challenges of developing flexible NLG approaches for HRI. Finally, I will provide an overview of our project [CiViL: Commonsense and Visually-enhanced natural Language generation](https://gow.epsrc.ukri.org/NGBOViewGrant.aspx?GrantRef=EP/T014598/1) and discuss future directions.
Morning Coffee (10:00 EST)
Oral Session 2 (10:30 EST) Session Chair: Ondrej Dusek
Lunch (12:00 EST)
Keynote 3 (13:00 EST) Session Chair: Samira Shaikh
  • Modeling and Evaluating Faithful Generation in Language and Vision
    Mohit Bansal
    Faithfulness is a key aspect of accurate and trustworthy generation in diverse modalities such as language and vision. In this talk, I will present work towards modeling and evaluating faithfulness in summarization and multimodal tasks. First, we will discuss our earlier work on multi-task and reinforcement learning methods to incorporate auxiliary faithfulness-promoting skills such as entailment and back-translation validity. We will then describe abstractive summarization models that holistically address the problem of faithfulness during pre-training and fine-tuning. Next, we will explore improved summary faithfulness evaluation methods based on human-automation balance and semantic graph representations. Lastly, we will briefly discuss faithful, fine-grained skill evaluation of text-to-image generation models.
Afternoon Coffee (14:00 EST)
Demo/Poster Session 2 Survey (14:30 EST)
Demo/Poster Session 2 (15:00 EST)
Test of Time Award (17:00 EST)
Conference Dinner (18:00 EST)
Trip to Allen Island (06:00 EST)
Hackathon (09:00 EST)
Virtual Museum Tour (09:30 EST)
Morning Coffee (10:00 EST)
Lunch (12:00 EST)
Closing Drinks (15:00 EST)
Keynote 4 (09:00 EST) Session Chair: Thiago Castro Ferreira
  • From Generating Personalised Risk Descriptions to Data-driven Health Narratives: Applying NLG to Healthcare Data
    Emiel Krahmer
    Even though the health domain has been mentioned as a potential application domain for NLG since the early days of the field, one thing that has changed recently is the emergence of large and growing amounts of patient-generated health data in hospitals and other care facilities (think of self-reported outcome measures, electronic health records, registry data). Hospitals are urgently looking for ways to make this data accessible in a personalised manner for both patients and clinicians. Naturally, this is a task for which NLG lends itself very well. In this talk, I describe how traditional NLG tasks, such as the generation of referring expressions and of narratives, re-emerge in this health domain. I also highlight which particular evaluation questions this raises, such as, for example, what kind of information do patients actually want? In which format do they prefer this information? What cognitive implications does access to this information have? In the final part of the talk I touch upon a number of broader questions, such as is there room for transformers in this application domain, and what are ethical and privacy issues for this kind of application.
Morning Coffee (10:00 EST)
GenChal (10:30 EST) Session Chair: Sebastian Gehrmann
More Info
Lunch (13:00 EST)
Oral Session 3 (14:00 EST) Session Chair: Michael White
Afternoon Coffee (15:30 EST)
Oral Session 4 (16:00 EST) Session Chair: Ehud Reiter