Yi-Ling Chung

132 posts

Yi-Ling Chung banner
Yi-Ling Chung

Yi-Ling Chung

@yilingchung27

Senior Research Scientist at Genaios. Prev: @turinginst, PhD @FBKcom @UniTrento. NLP | NLG | Psychology | Foodie

Katılım Temmuz 2020
435 Takip Edilen196 Takipçiler
Sabitlenmiş Tweet
Yi-Ling Chung
Yi-Ling Chung@yilingchung27·
Most people have experienced or witnessed #hate but struggle with how to respond to it. Our systematic review looks into the impact of various types of counterspeech, NLP approaches to it (e.g., dataset, generation, evaluation) and future directions 👉arxiv.org/pdf/2307.04761…
Turing Public Policy@TuringPubPol

📑 New publication from researchers @jonmbright, @FlorenceEnock and @yilingchung27 of our #OnlineSafety team A multidisciplinary review of research and methodologies around automatic counterspeech generation, to mitigate online harm ⬇️ bit.ly/458iDqu

English
2
4
12
1.1K
Yi-Ling Chung retweetledi
Guido Zuccon
Guido Zuccon@guidozuc·
Here my slides from the #ESSIR2024 lecture on Generative-IR: ielab.io/files/essir202…. Not a complete overview of using LLMs for search and ranking, but a starter for those interested, with pointers to more in-depth works. Mind the bias in my perspective on the field @essir_eu
English
3
17
78
4.8K
Yi-Ling Chung retweetledi
Rodrigo Agerri
Rodrigo Agerri@ragerri·
WE ARE HIRING!! 🥳The HiTZ Center for Language Technology (hitz.eus) at the University of the Basque Country (UPV/EHU) invites applications for predoctoral and postdoctoral positions in Natural Language and Speech Processing. CHECK IT HERE!! hitz.eus/job-offers
English
0
28
22
3.8K
Yi-Ling Chung retweetledi
Ehud Reiter
Ehud Reiter@EhudReiter·
New blog: Human eval: Subjects must understand the task ehudreiter.com/2024/05/28/hum… This sounds obvious, but it was repeatedly raised as a concern in the replication shared task at the COLING human evaluation workshop.
English
0
5
24
3.6K
Yi-Ling Chung retweetledi
Workshop on Online Abuse and Harms
Workshop on Online Abuse and Harms@WOAHWorkshop·
📆Save the date📆 WOAH will take place on Thursday, June 20th, 2024, at #NAACL2024 @naaclmeeting in Mexico City! Thank you for all the submissions, we're currently in the review phase. Best of luck!
English
0
4
10
1.5K
Yi-Ling Chung retweetledi
Akari Asai
Akari Asai@AkariAsai·
Amazing follow-up of Self-RAG by @ocolegro, which fine-tunes Self-RAG on top of Mistral-7b. Even stronger performance from the original LLama2-7b-based Self-RAG! Also, a nice API to retrieve documents and generate using the Self-RAG model is provided! sciphi.readthedocs.io/en/latest/setu…
Owen Colegrove@ocolegro

We encountered issues with accuracy in synthetic data generation. Fortunately, a great approach called self-rag was introduced by @AkariAsai et al. Introducing SciPhi-Self-RAG-Mistral-7B-32k I fine-tuned the SciPhi model with this and more. The result is powerful + efficient.

English
5
18
116
23.4K
Yi-Ling Chung retweetledi
Federico Botta
Federico Botta@Fede_Botta·
Ever wanted to study the cost of train journeys in Great Britain? Now you can! First version of my new python package is now available on GitHub (github.com/FedericoBotta/…) together with some related data sets, and it's all also described here: arxiv.org/pdf/2310.19754…
Federico Botta tweet media
English
5
47
246
37K
Yi-Ling Chung retweetledi
ACM FAccT
ACM FAccT@FAccTConference·
⏰ FAccT 2024 CALL FOR PAPERS POSTED! facctconference.org/2024/cfp 📝Abstract submission: 11 January 2024 📑Paper submission: 18 January 2024
English
2
63
146
41.9K
Yi-Ling Chung retweetledi
Sasha Rush
Sasha Rush@srush_nlp·
Introducing COLM (colmweb.org) the Conference on Language Modeling. A new research venue dedicated to the theory, practice, and applications of language models. Submissions: March 15 (it's pronounced "collum" 🕊️)
Sasha Rush tweet media
English
28
416
1.7K
505.5K
Yi-Ling Chung retweetledi
Workshop on Online Abuse and Harms
Workshop on Online Abuse and Harms@WOAHWorkshop·
We are excited to share that WOAH 2024, our 8th edition, will take place at #NAACL2024 in Mexico City! Our special theme this year will be "Online Harms in the Age of LLMs", covering emerging risks as well as LLM-based countermeasures. CfP and more details soon 🚀
Workshop on Online Abuse and Harms tweet media
English
2
18
57
11.5K

Keşfet

@essir_eu @gavin_does_nlp @naaclmeeting @helena_bonaldi @m_guerini @MikeKatell @TuringPubPol @ujaen