Seattle Area, WA
Joined June 2009
- Tweets249
- Following482
- Followers314
- Likes577
Markus Dreyer retweeted
Apple's Xcode now has direct integration with the Claude Agent SDK, giving developers the full functionality of Claude Code for building on Apple platforms, from iPhone to Mac to Apple Vision Pro.
Read more: anthropic.com/news/apple-xco…
Markus Dreyer retweeted
Happy new year! Just a reminder to everyone who works on language modeling that COLM is a new conference that I am co-organizing with several esteemed colleagues from academia and industry. Abstract deadline is on March 22 followed by the paper deadline on March 29.
colmweb.org/cfp.html
Markus Dreyer retweeted
We are excited to announce the #NeurIPS2023 paper awards:
blog.neurips.cc/2023/12/12/a…
Markus Dreyer retweeted
I'm thrilled to announce our company, @essential_ai . We believe that breakthroughs in AI will unlock the most profound tools for thought, advancing humanity's collective knowledge and capability.
essential.ai
Markus Dreyer retweeted
Looking for something to read? The proceedings of #EACL2023 can be found on the @aclanthology !
aclanthology.org/events/eacl…
#NLProc #eacl #ACLAnthology
Markus Dreyer retweeted
Excited to announce that my work "Faithfulness-Aware Decoding Strategies for Abstractive Summarization" has been accepted to #EACL2023😃!
🔗arxiv.org/abs/2303.03278
cc: M. Liu, K. McKeown, @markusdr, @mohitban47
(@AmazonScience, @uncnlp)
See you in Dubrovnik, Croatia!
🧵👇 1/n
Markus Dreyer retweeted
Amazon's 20B language model has fewer than 1/8 the number of parameters of GPT-3, yet outperforms it in several NLP tasks! Seq2seq AlexaTeacherModel also tops GPT-3 by being multilingual. Seen at KDD. GitHub 👾 bit.ly/3LeDorN #NLP #gpt3 #ai #deeplearning @AmazonScience
Markus Dreyer retweeted
I’m really honored that our paper, "Automatic Correction of Human Translations," won multiple awards at #NAACL2022! 😊
This paper came out of working w/ @LiltHQ to ask: how can we use NLP to assist real humans (professional translators)?
arxiv.org/abs/2206.08593
More below: [1/]
#NAACL2022 is announcing best paper awards and outstanding papers: 2022.naacl.org/blog/best-pap…
Please check them out!
Markus Dreyer retweeted
Hello #NAACL2022! I’ll be presenting FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations at oral session 1B: Summarization 10:45-12:15 Columbia C. Drop by and say hello!
paper: arxiv.org/pdf/2204.06508.pdf Code and models: github.com/amazon-research/f…
Glad to share 𝗙𝗮𝗰𝘁𝗚𝗿𝗮𝗽𝗵, an evaluation method that uses core semantic information from both document & summary via graph representations to assess factuality! #NAACL2022
📜: arxiv.org/abs/2204.06508
Great collaboration w/ Mengwen @IGurevych @markusdr @mohitban47
🧵👇
Markus Dreyer retweeted
Glad to share 𝗙𝗮𝗰𝘁𝗚𝗿𝗮𝗽𝗵, an evaluation method that uses core semantic information from both document & summary via graph representations to assess factuality! #NAACL2022
📜: arxiv.org/abs/2204.06508
Great collaboration w/ Mengwen @IGurevych @markusdr @mohitban47
🧵👇
Markus Dreyer retweeted
An argument for *random* COVID-19 testing. Tesing is biased toward the sick & ill. So we don't know how much COVID-19 there is or how dangerous it is. This uncertainty => over and/or under reaction. We can't manage what we don't measure respresentatively.
statnews.com/2020/03/17/a-fi…
Markus Dreyer retweeted
#acl2020nlp received 3,429 submissions --- a new record for an #NLProc conference! In fact, this is the first time a *CL conference has received over 3,000 submissions.
Markus Dreyer retweeted
How words change meaning over time:
“Baseline” (in NLP)
1998: random choice
2005: majority class
2012: bag of words
2019: LSTM with attention & pre-trained embeddings
Markus Dreyer retweeted
Excited to introduce OpenNMT (opennmt.net/), an open-source neural machine translation developed for industrial and academic use.
Markus Dreyer retweeted
Introducing the ASK Built-in Library Developer Preview: Pre-Built Models for Hundreds of Slots and Intents: amzn.to/2h4n4vb
