Do we always need sentence vectors for sentence retrieval and passage vectors for passage retrieval?🤔 Our #EMNLP2021 paper suggests that phrase vectors can serve as a basic building block🧱 for "multi-granularity" retrieval! 📜 arxiv.org/abs/2109.08133 💾 github.com/princeton-nlp/…

Excited to share BERN2! We use state-of-the-art biomedical NER and normalization models to annotate 9 biomedical entity types in real-time (0.3 sec/abstract). Web Service: bern2.korea.ac.kr Github: github.com/dmis-lab/BERN2 Paper: arxiv.org/abs/2201.02080

Pleased to announce that our paper 'Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models' is accepted at #ACL2022! Joint work with CambridgeLTL forks Fangyu Liu Ehsan Shareghi Yixuan Su Charlotte Collins and Nigel Collier.

How to intern? Research internships are great opportunities to do cool research in industrial labs! But it's definitely not easy to complete a solid work in 3 months. Some tips for having a successful internship ... 🧵

When the machine asks a question, is it better to know its answer in advance? 🙄🤖 Our #EMNLP2022 paper simulates two scenarios and reveals the difference. With our synthetic datasets, our CQA models achieve SOTA on QuAC. Check our camera-ready 🙌 arxiv: arxiv.org/abs/2205.12609

Are factually verified articles always safe? Even the news articles present different points of view on the same event. We propose ✨ClaimDiff✨, a dataset for "comparing" the news to detect the difference in nuances. [1/6] 📚 Paper (Latest): drive.google.com/file/d/1a5dsdf…

I will be at #ACL2023NLP next week! I am recruiting Ph.D. students in the next academic cycle, so if you are interested in working with me and would like to connect at the conference, please reach out! Looking forward to meeting everyone🎉

I will be presenting our paper "CausalDialogue" at Toronto #acl2023! Welcome to have a chat! Virtual Poster: July10 11-12:30 on GatherTown (Lobby ➡️Poster Session 1 ➡️Group 1 ➡️ ID2466) Spotlight: July10 7-9pm Workshop Poster: July14 10:50-12pm Video: shorturl.at/fqAQX

I’m attending #ACL2023NLP, and thrilled to present our papers! Checkout the details 👇 NAVER AI LAB

I'm finally in Toronto & presenting my 2 Continual-Learning #ACL2023nlp papers: 1) Our ExSSNeT paper was accepted as findings and will be presented as spotlight Mon 7pm and poster at Tue 11am. 2) Our Code-CL paper in main conf. on Wed 11am. Mohit Bansal Amazon Science @uncnlp 🧵

Come hear my #ACL2023NLP Poster Session of BioNLP-ST Workshop (14:00 - 17:30)! I will discuss my Microsoft Research Asia internship work on our new vision-language model, CheXOFA. We ranked 1st🥇on RadSum23 shared task for multi-modal radiology report summarization🩻!

Excited to share our #EMNLP2023 paper on answering ambiguous questions in open-domain QA. 🌲Tree of Clarifications🌲, LLM-based framework, recursively constructs a tree of disambiguations in a retrieval-augmented manner. 📑 arXiv: arxiv.org/abs/2310.14696

XTR has been accepted to NeurIPS 2023! I'll be attending NeurIPS in person to present XTR. Please check out our updated paper in OpenReview. openreview.net/forum?id=ZQzm0… Code release is also coming soon!