Back to the Future for Dialogue Research: A Position Paper — mentioned by Seabiscuit

Wed, 24 Jun 2020 13:22:26 GMT

These predictions often surely make most sense and are most prevalent in a particular field of NLP research, like dialogue (open-domain, non-task oriented). Believable dialogue seems to require some kind of world knowledge, certain forms of 'common sense' (e.g. arithmetic reasoning), and the ability to track belief states and be coherent over long periods. GPT-2 was critiqued for its inability to deal with simple arithmetic questions, as well as contradicting itself over long periods [1]. GPT-3 has similar deficiencies in terms of sensible real-world knowledge and displaying coherence both…

Paper and discussion history. A mention is not an endorsement.

Back to the Future for Dialogue Research: A Position Paper · HackerPapers discussions

Back to the Future for Dialogue Research: A Position Paper — mentioned by Seabiscuit