#emnlp2023 — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #emnlp2023, aggregated by home.social.
-
RT by @wikiresearch: The video of the presentation w/ @rnav_arora of our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions predicting Wikipedia policies for content moderation is now online at
https://youtu.be/UUuC6Q1SIoM?t=2190 https://twitter.com/frimelle/status/1747919662405353701 -
RT by @wikiresearch: The video of the presentation w/ @rnav_arora of our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions predicting Wikipedia policies for content moderation is now online at
https://youtu.be/UUuC6Q1SIoM?t=2190 https://twitter.com/frimelle/status/1747919662405353701 -
RT by @wikiresearch: The video of the presentation w/ @rnav_arora of our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions predicting Wikipedia policies for content moderation is now online at
https://youtu.be/UUuC6Q1SIoM?t=2190 https://twitter.com/frimelle/status/1747919662405353701 -
RT by @wikiresearch: The video of the presentation w/ @rnav_arora of our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions predicting Wikipedia policies for content moderation is now online at
https://youtu.be/UUuC6Q1SIoM?t=2190 https://twitter.com/frimelle/status/1747919662405353701 -
Some highlights from EMNLP 2023
https://health-nlp.com/posts/emnlp23.html
#EMNLP2023 #ml #machinelearning #NLProc #NLP #ai #artificialintelligence #conference
-
Some highlights from EMNLP 2023
https://health-nlp.com/posts/emnlp23.html
#EMNLP2023 #ml #machinelearning #NLProc #NLP #ai #artificialintelligence #conference
-
RT by @wikiresearch: Excited to start the new year by presenting our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions w/ @rnav_arora @IAugenstein at the @Wikimedia Research Showcase!
Online, 17.01., 17:30 UTChttps://www.mediawiki.org/wiki/Wikimedia_Research/Showcase#January_2024 @wikiresearch https://twitter.com/frimelle/status/1746569501284368467
-
RT by @wikiresearch: Excited to start the new year by presenting our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions w/ @rnav_arora @IAugenstein at the @Wikimedia Research Showcase!
Online, 17.01., 17:30 UTChttps://www.mediawiki.org/wiki/Wikimedia_Research/Showcase#January_2024 @wikiresearch https://twitter.com/frimelle/status/1746569501284368467
-
RT by @wikiresearch: Excited to start the new year by presenting our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions w/ @rnav_arora @IAugenstein at the @Wikimedia Research Showcase!
Online, 17.01., 17:30 UTChttps://www.mediawiki.org/wiki/Wikimedia_Research/Showcase#January_2024 @wikiresearch https://twitter.com/frimelle/status/1746569501284368467
-
RT by @wikiresearch: Excited to start the new year by presenting our #EMNLP2023 paper on Transparent Stance Detection in Multilingual Wikipedia Editor Discussions w/ @rnav_arora @IAugenstein at the @Wikimedia Research Showcase!
Online, 17.01., 17:30 UTChttps://www.mediawiki.org/wiki/Wikimedia_Research/Showcase#January_2024 @wikiresearch https://twitter.com/frimelle/status/1746569501284368467
-
RT by @wikiresearch: Thanks @wikiresearch for sharing!
Our #emnlp2023 paper is also available on ACL Anthology now: https://aclanthology.org/2023.emnlp-main.100/ https://twitter.com/ConiaSimone/status/1740084544881963053
-
RT by @wikiresearch: Thanks @wikiresearch for sharing!
Our #emnlp2023 paper is also available on ACL Anthology now: https://aclanthology.org/2023.emnlp-main.100/ https://twitter.com/ConiaSimone/status/1740084544881963053
-
RT by @wikiresearch: Thanks @wikiresearch for sharing!
Our #emnlp2023 paper is also available on ACL Anthology now: https://aclanthology.org/2023.emnlp-main.100/ https://twitter.com/ConiaSimone/status/1740084544881963053
-
RT by @wikiresearch: Thanks @wikiresearch for sharing!
Our #emnlp2023 paper is also available on ACL Anthology now: https://aclanthology.org/2023.emnlp-main.100/ https://twitter.com/ConiaSimone/status/1740084544881963053
-
A paper on the topic by Max Glockner (UKP Lab), @ievaraminta Staliūnaitė (University of Cambridge), James Thorne (KAIST AI), Gisela Vallejo (University of Melbourne), Andreas Vlachos (University of Cambridge) and Iryna Gurevych was accepted to TACL and has just been presented at #EMNLP2023.
-
A paper on the topic by Max Glockner (UKP Lab), @ievaraminta Staliūnaitė (University of Cambridge), James Thorne (KAIST AI), Gisela Vallejo (University of Melbourne), Andreas Vlachos (University of Cambridge) and Iryna Gurevych was accepted to TACL and has just been presented at #EMNLP2023.
-
A paper on the topic by Max Glockner (UKP Lab), @ievaraminta Staliūnaitė (University of Cambridge), James Thorne (KAIST AI), Gisela Vallejo (University of Melbourne), Andreas Vlachos (University of Cambridge) and Iryna Gurevych was accepted to TACL and has just been presented at #EMNLP2023.
-
At #EMNLP2023, our colleague Jonathan Tonglet presented his master thesis, conducted at the KU Leuven. Find out more about »SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA« in this thread 🧵:
-
At #EMNLP2023, our colleague Jonathan Tonglet presented his master thesis, conducted at the KU Leuven. Find out more about »SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA« in this thread 🧵:
-
At #EMNLP2023, our colleague Jonathan Tonglet presented his master thesis, conducted at the KU Leuven. Find out more about »SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA« in this thread 🧵:
-
Many models produce outputs that are hard to verify for an end user.
🏆 Our new #emnlp2023 paper won an outstanding paper award for showing that a secondary quality estimation model can help users decide when to rely on the model output.
We ran a controlled experiment showing that a calibrated quality estimation model can make physicians twice better at correctly deciding when to rely on a translation model output.
-
Many models produce outputs that are hard to verify for an end user.
🏆 Our new #emnlp2023 paper won an outstanding paper award for showing that a secondary quality estimation model can help users decide when to rely on the model output.
We ran a controlled experiment showing that a calibrated quality estimation model can make physicians twice better at correctly deciding when to rely on a translation model output.
-
Many models produce outputs that are hard to verify for an end user.
🏆 Our new #emnlp2023 paper won an outstanding paper award for showing that a secondary quality estimation model can help users decide when to rely on the model output.
We ran a controlled experiment showing that a calibrated quality estimation model can make physicians twice better at correctly deciding when to rely on a translation model output.
-
Many models produce outputs that are hard to verify for an end user.
🏆 Our new #emnlp2023 paper won an outstanding paper award for showing that a secondary quality estimation model can help users decide when to rely on the model output.
We ran a controlled experiment showing that a calibrated quality estimation model can make physicians twice better at correctly deciding when to rely on a translation model output.
-
A group photo from the poster presentation of »AmbiFC: Fact-Checking Ambiguous Claims with Evidence«, co-authored by our colleague Max Glockner, @ievaraminta, James Thorne, Gisela Vallejo, Andreas Vlachos and Iryna Gurevych. #EMNLP2023
-
A group photo from the poster presentation of »AmbiFC: Fact-Checking Ambiguous Claims with Evidence«, co-authored by our colleague Max Glockner, @ievaraminta, James Thorne, Gisela Vallejo, Andreas Vlachos and Iryna Gurevych. #EMNLP2023
-
A group photo from the poster presentation of »AmbiFC: Fact-Checking Ambiguous Claims with Evidence«, co-authored by our colleague Max Glockner, @ievaraminta, James Thorne, Gisela Vallejo, Andreas Vlachos and Iryna Gurevych. #EMNLP2023
-
A successful #EMNLPMeeting has come to an end! A group photo of our colleagues Yongxin Huang, Jonathan Tonglet, Aniket Pramanick, Sukannya Purkayastha, Dominic Petrak and Max Glockner, who represented the UKP Lab in Singapore! #EMNLP2023
-
A successful #EMNLPMeeting has come to an end! A group photo of our colleagues Yongxin Huang, Jonathan Tonglet, Aniket Pramanick, Sukannya Purkayastha, Dominic Petrak and Max Glockner, who represented the UKP Lab in Singapore! #EMNLP2023
-
A successful #EMNLPMeeting has come to an end! A group photo of our colleagues Yongxin Huang, Jonathan Tonglet, Aniket Pramanick, Sukannya Purkayastha, Dominic Petrak and Max Glockner, who represented the UKP Lab in Singapore! #EMNLP2023
-
You can find our paper here:
📃 https://arxiv.org/abs/2311.00408
and our code here:
💻 https://github.com/UKPLab/AdaSentCheck out the work of our authors Yongxin Huang, Kexin Wang, Sourav Dutta, Raj Nath Patel, Goran Glavaš and Iryna Gurevych! (6/🧵) #EMNLP2023 #AdaSent #NLProc
-
You can find our paper here:
📃 https://arxiv.org/abs/2311.00408
and our code here:
💻 https://github.com/UKPLab/AdaSentCheck out the work of our authors Yongxin Huang, Kexin Wang, Sourav Dutta, Raj Nath Patel, Goran Glavaš and Iryna Gurevych! (6/🧵) #EMNLP2023 #AdaSent #NLProc
-
You can find our paper here:
📃 https://arxiv.org/abs/2311.00408
and our code here:
💻 https://github.com/UKPLab/AdaSentCheck out the work of our authors Yongxin Huang, Kexin Wang, Sourav Dutta, Raj Nath Patel, Goran Glavaš and Iryna Gurevych! (6/🧵) #EMNLP2023 #AdaSent #NLProc
-
What makes the difference 🧐 ?
We attribute the effectiveness of the sentence encoding adapter to the consistency between the pre-training and DAPT objectives of the base PLM. If the base PLM is domain-adapted with another loss, the adapter won’t be compatible any more, reflected in a performance drop. (5/🧵) #EMNLP2023
-
What makes the difference 🧐 ?
We attribute the effectiveness of the sentence encoding adapter to the consistency between the pre-training and DAPT objectives of the base PLM. If the base PLM is domain-adapted with another loss, the adapter won’t be compatible any more, reflected in a performance drop. (5/🧵) #EMNLP2023
-
What makes the difference 🧐 ?
We attribute the effectiveness of the sentence encoding adapter to the consistency between the pre-training and DAPT objectives of the base PLM. If the base PLM is domain-adapted with another loss, the adapter won’t be compatible any more, reflected in a performance drop. (5/🧵) #EMNLP2023
-
AdaSent decouples DAPT and SEPT by storing the sentence encoding abilities into an adapter, which is trained only once in the general domain and plugged into various DAPT-ed PLMs. It can match or surpass the performance of DAPT→SEPT, with more efficient training. (4/🧵) #EMNLP2023
-
AdaSent decouples DAPT and SEPT by storing the sentence encoding abilities into an adapter, which is trained only once in the general domain and plugged into various DAPT-ed PLMs. It can match or surpass the performance of DAPT→SEPT, with more efficient training. (4/🧵) #EMNLP2023
-
AdaSent decouples DAPT and SEPT by storing the sentence encoding abilities into an adapter, which is trained only once in the general domain and plugged into various DAPT-ed PLMs. It can match or surpass the performance of DAPT→SEPT, with more efficient training. (4/🧵) #EMNLP2023
-
Domain-adapted sentence embeddings can be created by applying general-domain SEPT on top of a domain-adapted base PLM (DAPT→SEPT). But this requires the same SEPT procedure to be done on each DAPT-ed PLM for every domain, resulting in computational inefficiency. (3/🧵) #EMNLP2023
-
Domain-adapted sentence embeddings can be created by applying general-domain SEPT on top of a domain-adapted base PLM (DAPT→SEPT). But this requires the same SEPT procedure to be done on each DAPT-ed PLM for every domain, resulting in computational inefficiency. (3/🧵) #EMNLP2023
-
Domain-adapted sentence embeddings can be created by applying general-domain SEPT on top of a domain-adapted base PLM (DAPT→SEPT). But this requires the same SEPT procedure to be done on each DAPT-ed PLM for every domain, resulting in computational inefficiency. (3/🧵) #EMNLP2023
-
In our #EMNLP2023 paper we demonstrate AdaSent's effectiveness in extensive experiments on 17 different few-shot sentence classification datasets! It matches or surpasses the performance of full SEPT on DAPT-ed PLM (DAPT→SEPT) while substantially reducing training costs. (2/🧵)
-
In our #EMNLP2023 paper we demonstrate AdaSent's effectiveness in extensive experiments on 17 different few-shot sentence classification datasets! It matches or surpasses the performance of full SEPT on DAPT-ed PLM (DAPT→SEPT) while substantially reducing training costs. (2/🧵)
-
In our #EMNLP2023 paper we demonstrate AdaSent's effectiveness in extensive experiments on 17 different few-shot sentence classification datasets! It matches or surpasses the performance of full SEPT on DAPT-ed PLM (DAPT→SEPT) while substantially reducing training costs. (2/🧵)
-
Need a lightweight solution for few-shot domain-specific sentence classification?
We propose #AdaSent!
🚀 Up to 7.2 acc. gain in 8-shot classification with 10K unlabeled data
🪶 Small backbone with 82M parameters
🧩 Reusable general sentence adapter across domains
(1/🧵) #EMNLP2023 -
Need a lightweight solution for few-shot domain-specific sentence classification?
We propose #AdaSent!
🚀 Up to 7.2 acc. gain in 8-shot classification with 10K unlabeled data
🪶 Small backbone with 82M parameters
🧩 Reusable general sentence adapter across domains
(1/🧵) #EMNLP2023 -
Need a lightweight solution for few-shot domain-specific sentence classification?
We propose #AdaSent!
🚀 Up to 7.2 acc. gain in 8-shot classification with 10K unlabeled data
🪶 Small backbone with 82M parameters
🧩 Reusable general sentence adapter across domains
(1/🧵) #EMNLP2023 -
Which factors shape #NLProc research over time? This was the topic of the talk by our colleague Aniket Pramanick at #EMNLP2023!
Learn more about the paper by him, Yufang Hou, Saif M. Mohammad & Iryna Gurevych here: 📑 https://arxiv.org/abs/2305.12920
-
Which factors shape #NLProc research over time? This was the topic of the talk by our colleague Aniket Pramanick at #EMNLP2023!
Learn more about the paper by him, Yufang Hou, Saif M. Mohammad & Iryna Gurevych here: 📑 https://arxiv.org/abs/2305.12920
-
Which factors shape #NLProc research over time? This was the topic of the talk by our colleague Aniket Pramanick at #EMNLP2023!
Learn more about the paper by him, Yufang Hou, Saif M. Mohammad & Iryna Gurevych here: 📑 https://arxiv.org/abs/2305.12920
-
If you are around at #EMNLP2023, look out for our colleague Sukannya Purkayastha, who presented today our paper on the use of Jiu-Jitsu argumentation in #PeerReview, authored by her, Anne Lauscher (Universität Hamburg) and Iryna Gurevych.
-
If you are around at #EMNLP2023, look out for our colleague Sukannya Purkayastha, who presented today our paper on the use of Jiu-Jitsu argumentation in #PeerReview, authored by her, Anne Lauscher (Universität Hamburg) and Iryna Gurevych.
-
If you are around at #EMNLP2023, look out for our colleague Sukannya Purkayastha, who presented today our paper on the use of Jiu-Jitsu argumentation in #PeerReview, authored by her, Anne Lauscher (Universität Hamburg) and Iryna Gurevych.
-
Check out the full paper on arXiv and the code on GitLab – we look forward to your thoughts and feedback! (9/9) #NLProc #eRisk #EMNLP2023
Paper 📄 https://arxiv.org/abs/2211.07624
Code ⌨️ https://gitlab.irlab.org/anxo.pvila/semantic-4-depression -
Check out the full paper on arXiv and the code on GitLab – we look forward to your thoughts and feedback! (9/9) #NLProc #eRisk #EMNLP2023
Paper 📄 https://arxiv.org/abs/2211.07624
Code ⌨️ https://gitlab.irlab.org/anxo.pvila/semantic-4-depression -
Check out the full paper on arXiv and the code on GitLab – we look forward to your thoughts and feedback! (9/9) #NLProc #eRisk #EMNLP2023
Paper 📄 https://arxiv.org/abs/2211.07624
Code ⌨️ https://gitlab.irlab.org/anxo.pvila/semantic-4-depression -
We also illustrate how our semantic retrieval pipeline provides interpretability of the symptom estimation, highlighting the most relevant sentences. (8/🧵) #EMNLP2023 #NLProc
-
We also illustrate how our semantic retrieval pipeline provides interpretability of the symptom estimation, highlighting the most relevant sentences. (8/🧵) #EMNLP2023 #NLProc
