Neuroscience and neural networks, being a linguist in the world of NLP, evaluation methods, fine-grained NLI questions, the pace of research, and the vexing fact that, on the internet, people = men.
Transcript: https://web.stanford.edu/class/cs224u/podcast/williams/
Adina's websiteAdina on TwitterBased on billions of words on the internet, people = menApril BaileyAndrei CimpianAndrocentrismGloVefastTextPreregistrationP-hackingRishi BommasaniInterpreting pretrained contextualized representations via reductions to static embeddingsCommon CrawlBattlestar GalacticaMultiNLIANLIDynaBenchBreaching experimentLiina PylkkänenSam BowmanNikita NangiaLudwig WittgensteinIdo DaganSebastian RiedelSNLIYixin NieDouwe KielaJason WestonEmily DinanBuild it break it fix it for dialogue safety: Robustness from adversarial human attackAllyson EttingerGLUEDynaSentDeBERTaRoBERTaBreaking NLI systems with sentences that require simple lexical inferencesHANS: Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inferenceTargeted syntactic evaluation of language modelsMax BartoloMagnetoencephalographyMarr's LevelsMarco BaroniRichard FutrellRyan CotterellSIGMORPHON 2022Alexis ConneauFLORESXNLIOCNLI: Original Chinese natural language inferenceYann LeCunNovel Ideas in Learning-to-Learn through InteractionGrounding semantics in olfactory perceptionBrain in a vatEllie PavlickTom KwiatkowskiMohit BansalIdentifying inherent disagreement in natural language inferenceDALL-E 2WinogroundGary Marcus on Winoground