Jinlan Fu

@JinlanFu

Postdoc at @NUSComputing, previously FudanNLP. | Interests: Large Language Model, Text Evaluation, Generation, Dialog System

Singapore

jinlanfu.github.io

Joined May 2017

189 Following

208 Followers

Replies Reposts Media

Jinlan Fu
@JinlanFu
Feb 21, 2023
Can the text evaluator be customized for different/new evaluation aspects without training? Our GPTScore achieves customized, multifaceted, and training-free using emergent abilities of PLM, i.g., instruction and in-context learning. Paper: arxiv.org/pdf/2302.04166…
GIF
2
Jinlan Fu
@JinlanFu
Dec 8, 2022
Can more conceptually-diverse tasks from different languages communicate together? Our work exploits multilingual prompting methods for learning a unified semantic space for different languages and tasks. #EMNLP2022 Paper: arxiv.org/pdf/2204.14264… Code: github.com/jinlanfu/Polyg…
2
Jinlan Fu
@JinlanFu
Apr 29, 2021
So excited to share our recent work at #NAACL2021. We empirically study four tagging tasks and thirteen datasets, interpreting the improvement brought by larger-context training using the ExplainaBoard toolkit. explainaboard.nlpedia.ai
Pengfei Liu
@stefan_fee
Apr 29, 2021
The success of many NLP techniques (BERT, Retrieval ...) is essentially due to the use of the larger context, but the MORE, the BETTER? We (@JinlanFu ) try to answer this question in #NAACL2021: Larger-Context Tagging: When and Why Does It Work? arxiv.org/pdf/2104.04434…
Jinlan Fu
@JinlanFu
Apr 15, 2021
Happy to be one of the contributors of ExplainaBoard, which covers more than 40 datasets, 9 tasks, and 7 analysis functionalities to interpret the characteristics of systems, datasets, and their interplay. Thanks, @stefan_fee, @gneubig, and et al.. Tool: explainaboard.nlpedia.ai
Pengfei Liu
@stefan_fee
Apr 14, 2021
What's your system good/bad at? Where can your model outperform others? What are the mistakes that the top-10 systems make？ We are always struggling with these questions. A new academic tool can help us answer them in a one-click fashion and many more:explainaboard.nlpedia.ai
GIF
1
Jinlan Fu
@JinlanFu
Nov 17, 2020
It’s my honor to work with @stefan_fee and @gneubig. Current evaluation metrics are opaque to the strengths and weaknesses of systems. Our works proposed an interpretable evaluation to interpret the differences in models and datasets, as well as the interplay between them.
Pengfei Liu
@stefan_fee
Nov 17, 2020
Interpretable Evaluation for NLP + ExplainBoard !! @JinlanFu @gneubig 1. Performance reached a plateau? What's left & next? 2. Can metrics tell the pros & cons of systems? 3. ExplainBoard: Next Generation Leaderboard? @emnlp2020 arxiv.org/pdf/2011.06854… arxiv.org/pdf/2011.06858…
GIF

Jinlan Fu

Jinlan Fu’s posts