no code implementations • NAACL (TeachingNLP) 2021 • Greg Durrett, Jifan Chen, Shrey Desai, Tanya Goyal, Lucas Kabela, Yasumasa Onoe, Jiacheng Xu
We present a series of programming assignments, adaptable to a range of experience levels from advanced undergraduate to PhD, to teach students design and implementation of modern NLP systems.
1 code implementation • 19 Jun 2023 • Tomoki Sugimoto, Yasumasa Onoe, Hitomi Yanaka
Natural Language Inference (NLI) tasks involving temporal inference remain challenging for pre-trained language models (LMs).
1 code implementation • NeurIPS 2023 • Shankar Padmanabhan, Yasumasa Onoe, Michael J. Q. Zhang, Greg Durrett, Eunsol Choi
Then, we update the model parameters so that the distribution of the LM (the student) matches the distribution of the LM conditioned on the definition (the teacher) on the transfer set.
1 code implementation • 2 May 2023 • Yasumasa Onoe, Michael J. Q. Zhang, Shankar Padmanabhan, Greg Durrett, Eunsol Choi
Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes.
no code implementations • CVPR 2023 • Su Wang, Chitwan Saharia, Ceslee Montgomery, Jordi Pont-Tuset, Shai Noy, Stefano Pellegrini, Yasumasa Onoe, Sarah Laszlo, David J. Fleet, Radu Soricut, Jason Baldridge, Mohammad Norouzi, Peter Anderson, William Chan
Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.
1 code implementation • 3 Dec 2022 • Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh, Byron C. Wallace
However, while fine-tuning sparse, interpretable representations improves accuracy on downstream tasks, it destroys the semantics of the dimensions which were enforced in pre-training.
no code implementations • Findings (NAACL) 2022 • Yasumasa Onoe, Michael J. Q. Zhang, Eunsol Choi, Greg Durrett
Given its wide coverage on entity knowledge and temporal indexing, our dataset can be used to evaluate LMs and techniques designed to modify or extend their knowledge.
no code implementations • 13 Dec 2021 • Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh
In this work, we empirically study how and whether such methods, applied in a bi-modal setting, can improve an existing VQA system's performance on the KBVQA task.
no code implementations • 15 Oct 2021 • Nila Selvaraj, Yasumasa Onoe, Greg Durrett
In this paper, we present a unified cross-lingual fine-grained entity typing model capable of handling over 100 languages and analyze this model's ability to generalize to languages and entities unseen during training.
2 code implementations • 3 Sep 2021 • Yasumasa Onoe, Michael J. Q. Zhang, Eunsol Choi, Greg Durrett
We introduce CREAK, a testbed for commonsense reasoning about entity knowledge, bridging fact-checking about entities (Harry Potter is a wizard and is skilled at riding a broomstick) with commonsense inferences (if you're good at a skill you can teach others how to do it).
2 code implementations • Findings (ACL) 2021 • Diego Garcia-Olano, Yasumasa Onoe, Ioana Baldini, Joydeep Ghosh, Byron C. Wallace, Kush R. Varshney
Pre-trained language models induce dense entity representations that offer strong performance on entity-centric NLP tasks, but such representations are not immediately interpretable.
1 code implementation • ACL 2021 • Yasumasa Onoe, Michael Boratko, Andrew McCallum, Greg Durrett
Neural entity typing models typically represent fine-grained entity types as vectors in a high-dimensional space, but such spaces are not well-suited to modeling these types' complex interdependencies.
Ranked #9 on Entity Typing on Open Entity
no code implementations • Findings of the Association for Computational Linguistics 2020 • Yasumasa Onoe, Greg Durrett
On entity probing tasks involving recognizing entity identity, our embeddings used in parameter-free downstream models achieve competitive performance with ELMo- and BERT-based embeddings in trained models.
1 code implementation • 12 Sep 2019 • Yasumasa Onoe, Greg Durrett
For this problem, a domain is characterized not just by genre of text but even by factors as specific as the particular distribution of entities, as neural models tend to overfit by memorizing properties of frequent entities in a dataset.
1 code implementation • NAACL 2019 • Yasumasa Onoe, Greg Durrett
In this work, we propose a two-stage procedure for handling this type of data: denoise it with a learned model, then train our final model on clean and denoised distant data with standard supervised training.
Ranked #2 on Entity Typing on Ontonotes v5 (English)