no code implementations • 1 May 2024 • Hugh Zhang, Jeff Da, Dean Lee, Vaughn Robinson, Catherine Wu, Will Song, Tiffany Zhao, Pranav Raja, Dylan Slack, Qin Lyu, Sean Hendryx, Russell Kaplan, Michele Lunati, Summer Yue
Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning.
no code implementations • 13 Sep 2022 • Jack Hessel, Ana Marasović, Jena D. Hwang, Lillian Lee, Jeff Da, Rowan Zellers, Robert Mankoff, Yejin Choi
Large neural networks can now generate jokes, but do they really "understand" humor?
no code implementations • ACL 2021 • Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin Choi
Understanding manipulated media, from automatically generated {`}deepfakes{'} to manually edited ones, raises novel research challenges.
1 code implementation • AKBC 2021 • Jeff Da, Ronan Le Bras, Ximing Lu, Yejin Choi, Antoine Bosselut
Our results show that commonsense knowledge models can rapidly adapt from limited examples, indicating that KG fine-tuning serves to learn an interface to encoded knowledge learned during pretraining.
no code implementations • 8 Dec 2020 • Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin Choi
The difference between this example, and harmful edits that spread disinformation, is one of intent.
3 code implementations • 12 Oct 2020 • Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, Yejin Choi
Next, we show that ATOMIC 2020 is better suited for training knowledge models that can generate accurate, representative knowledge for new, unseen entities and events.
no code implementations • WS 2019 • Jeff Da
Finally, we contribute a method of contextualizing BERT after combining with knowledge base embeddings.
no code implementations • 17 Oct 2019 • Jeff Da
Finally, we contribute a method of contextualizing BERT after combining with knowledge base embeddings.
no code implementations • WS 2019 • Jeff Da, Jungo Kasai
Pretrained deep contextual representations have advanced the state-of-the-art on various commonsense NLP tasks, but we lack a concrete understanding of the capability of these models.
no code implementations • EACL 2021 • Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi
We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.