Head of Machine Learning at @AMPLYFItech
Lecturer at @cardiffuni #nlproc#machinelearning
Before: @savanamedica @FulbrightPrgrm @FundlaCaixa
Views my own
๐Release!๐ RoBERTa models pre-trained on millions of tweets. Also fine-tuned models for tweet classification for the #emnlp2020 Findings paper ๐TweetEval๐. Models and starter code now online in ๐ค@huggingface | https://t.co/rZv9IStVrq #NLProc
Check out the accepted papers from the Cardiff NLP group and collaborators at upcoming #NLProc and #ML conferences!
We'll be presenting several papers at #NAACL2025 (main conference, demos, and workshops), #ICLR2025, and #CVPR2025.
Preprints are available for the following papers ๐:
Highlights from #WikiWorkshop at #EMNLP2024: Presented our work on Hoax articles (https://t.co/7RDoSoZWhC) and participated in a panel on misinformation with @vlachos_nlp and @IAugenstein . Thanking the organizers and @frimelle for the incredible experience! 1/2
Stereotypes, social biases and topic classification. Three papers from Cardiff NLP presented simultaneously at the same poster session yesterday at #EMNLP2024! ๐ผ๏ธ
The First Workshop on Advancing Natural Language Processing for Wikipedia will happen tomorrow, 16th of November, in conjunction with @emnlpmeeting !
Website: https://t.co/XdrNXSYK8L
Proceedings: https://t.co/CSDmIWvPzb
"WiDe-analysis: Enabling One-click Content Moderation Analysis on Wikipediaโs Articles for Deletion"
(Borkakoty and Espinosa-Anke)
https://t.co/6VyLpYVHpq
๐จ NEW PAPER ALERT ๐จ
Introducing the GlobalBias datasetโฆ We ask Claude 3, GPT 3.5, GPT 4o, and Llama 3 to produce character profiles based on given names from GlobalBias for 40 different gender-by-ethnicity groups. We find that all models displayed stereotypical outputs (1/4)
Link to GitHub: https://t.co/pdFSEJhOO3
Link to paper: https://t.co/94rTvbkUTX
If youโd like to discuss anything related to the paper, drop me a DM or comment below.
* we refers to myself, @LiamDTurner and @espinosaanke
(4/4)
ART-AI PhD students at the Cardiff NLP Workshop.
Amazing event hosted by one of the biggest NLP labs in the UK @Cardiff_NLP ๐๐ด๓ ง๓ ข๓ ท๓ ฌ๓ ณ๓ ฟ
Thanks to @CamachoCollados & other organizers for the invitation to speak at @Cardiff_NLP! It's a really vibrant NLP group (over 30 people!) that grew in just 4 years. Prospective students, do add it to your list of labs to watch for positions! https://t.co/nmvwPUYWD5
ACL notification last week, LREC-COLING this week, NAACL happening next month... it's NLP conference season! ๐ฅณ
Check out the list of papers accepted by our team members for these conferences, with some presentations already this week at #LRECCOLING2024! #naacl2024#acl2024nlp
๐๐๐๐๐ - ๐๐๐ ๐๐ฏ๐๐ฅ๐ฎ๐๐ญ๐ข๐จ๐ง ๐ ๐ซ๐๐ฆ๐๐ฐ๐จ๐ซ๐ค
Ragas is a python based evaluation framework for your Retrieval Augmented Generation (RAG) pipelines.
RAG denotes a class of LLM applications that use external data to augment the LLMโs context.
There are existing tools and frameworks that help you build these pipelines but evaluating it and quantifying your pipeline performance can be hard.
Ragas provides you with the tools based on the latest research for evaluating LLM-generated text to give you insights about your RAG pipeline.
Ragas can be integrated with your CI/CD to provide continuous checks to ensure performance.
Ragas framework - https://t.co/pMKuBn7arN
#rag #evaluation #generativeai #llms #nlproc #deeplearning