🔍 Research in Reasoning and Explainable AI 🔍 NLP, Semantics, Model Interpretability and Cross-Disciplinary Applications of AI 🔍 @OfficialUoM and @idiap_ch
Joined October 2020
- Tweets23
- Following64
- Followers98
- Likes32
We will be at @iwcs2021 today, presenting our work! So if you are around, please come and have a chat.
This Post is from an account that no longer exists. Learn more
We had one paper accepted at ACL2021! 🎉🎊🎉🎊
Congrats to the authors @Mokanarangan @mrc_valentino @andrenfreitas
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
Last week @alex_bogatu presented the paper Cost–effective Variational Active Entity Resolution at ICDE.
lnkd.in/d5QUxvH
Thanks to Alex Bogatu, Norman Paton, Mark Douthwaite and Stuart Davie for collaborating on this project!
Blog post: lnkd.in/dZFi6CJ
This is one of the outcomes of the collaboration with Peak AI (@Peak_HQ) funded by the @innovateuk KTP programme.
We are happy to announce we had 3 papers accepted at IWCS2021!
(1)🗒️Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards
😎@mrc_valentino, Ian Pratt-Hartmann and @andrenfreitas
(1/2) 🧵
We are happy to announce our two great keynote speakers: Rachel Rudinger (@rachelrudinger) and Mirella Lapata (@mlapata)!
iwcs2021.github.io/keynotes.…
Moreover, the list of accepted papers is now available:
iwcs2021.github.io/program.h…
(2)📄Switching Contexts: Transportability Measures for NLP
😎@Mokanarangan, @fuzaguy, Philip Osborne and @andrenfreitas
(3)📄Encoding Abstractive Knowledge Transitivity for Zero-shot Science Question Answering
😎Zili Zhou, @mrc_valentino , Donal Landers and @andrenfreitas
This week we will be presenting two long papers at EACL2021 @eaclmeeting
Unification-based Reconstruction of Multi-hop Explanations for Science Questions
and
STAR: Cross-modal STAtement Representation for selecting relevant mathematical premises
#EACL2021
🧵
1/3
Unification-based Reconstruction of Multi-hop Explanations for Science Questions (bit.ly/3eec0Ku) @mrc_valentino @Mokanarangan @andrenfreitas
🗣️We propose an explanation retrieval method for QA that leverages explanatory patterns in the form of unification
#EACL2021
2/3
STAR: Cross-modal STAtement Representation for selecting relevant mathematical premises (bit.ly/3aoUeTx) @debs_mf @andrenfreitas
🗣️ We combine Mathematical Language and Natural Language using STAR!
#EACL2021
3/3
We've found ourselves doing a lot of probing recently! To simplify the process, we've developed Probe-Ably:
An extendable probing framework that automates the training, complexity control and results processing
for your own representations and auxiliary task labels.
Some references that have guided this work so far:
arxiv.org/pdf/1909.03368.pdf (Hewitt et al)
arxiv.org/pdf/2004.03061.pdf,
arxiv.org/pdf/2010.02180.pdf (Pimentel et al)
arxiv.org/pdf/2009.07364.pdf (Zhu et al)
ExplAIn Lab retweeted
🐎🐎 .@SheffieldNLP has 10 papers accepted at
#NAACL2021 and #EACL2021! Congratulations to all
@SheffieldNLP authors! #NLProc
Our lab head @andrenfreitas joins @idiap_ch, with the @explAIn_lab now becoming a cross-institution research group idiap.ch/en/allnews/four-new…
ExplAIn Lab retweeted
Sometimes the contributions of smaller labs get overlooked in a big way! 😅
We're a pretty new group, but we've got big ideas and are just getting going!
Give @debs_mf and our lab @explAIn_lab a follow - time to work on our visibility! 👀
it's a double-embarrassment day. NaturalProof in wellecks.github.io/naturalpr…, which i loved working on, turned out also to be a repetition of the work by Deborah Ferreira arxiv.org/abs/2004.14959.
