The Stanford AI Lab Blog

FEBRUARY 1, 2022

Using a set of automated metrics, which we validated using manual annotations, we found the following results, which provide direction for future conversational design: Using statements alone outperformed questions or combined statements and questions Giving personal opinion statements (e.g. Strategies for handling cus- tomer abuse of ECAs.

Computational Linguistics 40

Computational Linguistics Chatbots Robotics Natural Language Processing 40

ML Review

MARCH 5, 2019

Automate it for everyone, and then we can go make something else. Note : The “Charts and Additional Insights” page, one chart being “Top topics from 2014 onwards”. Note : Top 100 cited papers according to the semantic scholar API from 2014+ (specifically from our arxiv dataset). 2014, January). 2126–2136). Deerwester, S.,

AI 40

AI AI Computer Vision Computational Linguistics 40

Ehud Reiter

DECEMBER 15, 2024

AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts. I also loved their example of domain drift, where GPT gave a wrong answer because it used an old law which had been superceded in 2014 (ie GPT could not deal with a domain change that happened 10 years ago). Computational Linguistics.

NLP 120

NLP Computational Linguistics Explainability Machine Learning 120