📝 𝗪𝗵𝗮𝘁 𝗮𝘀𝗽𝗲𝗰𝘁𝘀 𝗱𝗼 𝗿𝗲𝘃𝗶𝗲𝘄𝗲𝗿𝘀 𝗳𝗼𝗰𝘂𝘀 𝗼𝗻 𝗶𝗻 𝗽𝗲𝗲𝗿 𝗿𝗲𝘃𝗶𝗲𝘄𝘀?
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
November 4, 2025 at 10:49 AM
📝 𝗪𝗵𝗮𝘁 𝗮𝘀𝗽𝗲𝗰𝘁𝘀 𝗱𝗼 𝗿𝗲𝘃𝗶𝗲𝘄𝗲𝗿𝘀 𝗳𝗼𝗰𝘂𝘀 𝗼𝗻 𝗶𝗻 𝗽𝗲𝗲𝗿 𝗿𝗲𝘃𝗶𝗲𝘄𝘀?
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
🚨 Negative results paper! 🚨 #EMNLP23
Everyone wants an NLG model that is best for their domain
But, labeling in NLG is hard and expensive
This is where "Active Learning for NLG" comes into the picture
Or maybe not?
https://t.co/xtAJRsEkHG https://t.co/IPa84pp43r
Everyone wants an NLG model that is best for their domain
But, labeling in NLG is hard and expensive
This is where "Active Learning for NLG" comes into the picture
Or maybe not?
https://t.co/xtAJRsEkHG https://t.co/IPa84pp43r
November 19, 2024 at 7:28 PM
🚨 Negative results paper! 🚨 #EMNLP23
Everyone wants an NLG model that is best for their domain
But, labeling in NLG is hard and expensive
This is where "Active Learning for NLG" comes into the picture
Or maybe not?
https://t.co/xtAJRsEkHG https://t.co/IPa84pp43r
Everyone wants an NLG model that is best for their domain
But, labeling in NLG is hard and expensive
This is where "Active Learning for NLG" comes into the picture
Or maybe not?
https://t.co/xtAJRsEkHG https://t.co/IPa84pp43r
We perform a systematic study with 9 datasets and 4 AL strategies and find that
AL does not consistently beat random sampling for NLG
Hear more at #EMNLP23 12/9 West 1 at 11AM
AL does not consistently beat random sampling for NLG
Hear more at #EMNLP23 12/9 West 1 at 11AM
November 19, 2024 at 7:28 PM
We perform a systematic study with 9 datasets and 4 AL strategies and find that
AL does not consistently beat random sampling for NLG
Hear more at #EMNLP23 12/9 West 1 at 11AM
AL does not consistently beat random sampling for NLG
Hear more at #EMNLP23 12/9 West 1 at 11AM
I really enjoyed the poster session today at #emnlp23. Thank you all for stopping by 😀 (Interestingly, we all seem to agree on the human disagreement) @mumblamb @barbara_plank @TYSSSantosh2 @LeonStaufer
March 11, 2025 at 10:30 PM
I really enjoyed the poster session today at #emnlp23. Thank you all for stopping by 😀 (Interestingly, we all seem to agree on the human disagreement) @mumblamb @barbara_plank @TYSSSantosh2 @LeonStaufer
Can't wait for this years #EMNLP24
Going to highlight interesting papers here. See y'all soon!
#throwback #EMNLP23
Going to highlight interesting papers here. See y'all soon!
#throwback #EMNLP23
November 11, 2024 at 3:29 PM
Can't wait for this years #EMNLP24
Going to highlight interesting papers here. See y'all soon!
#throwback #EMNLP23
Going to highlight interesting papers here. See y'all soon!
#throwback #EMNLP23
TUM LegalTech Rundown today (8. Dec)@EMNLP23: 11- 12:30 We’ll present our poster“From Dissonance to Insights: Dissecting Disagreements ...............” at East Foyer. Come and stop by to chat about Human Label Variation, Disagreement and LegalNLP 1/3🧵
March 11, 2025 at 10:35 PM
TUM LegalTech Rundown today (8. Dec)@EMNLP23: 11- 12:30 We’ll present our poster“From Dissonance to Insights: Dissecting Disagreements ...............” at East Foyer. Come and stop by to chat about Human Label Variation, Disagreement and LegalNLP 1/3🧵
when retiring a dataset,
why do we consider its difficulty, when intuitively we should look at discriminability?
came across this watching @adinamwilliams talk at #EMNLP23
IIUC, a dataset can be easy but discriminative (see IMBD in @stanfordnlp's HELM for example)
No?
why do we consider its difficulty, when intuitively we should look at discriminability?
came across this watching @adinamwilliams talk at #EMNLP23
IIUC, a dataset can be easy but discriminative (see IMBD in @stanfordnlp's HELM for example)
No?
November 19, 2024 at 7:28 PM
when retiring a dataset,
why do we consider its difficulty, when intuitively we should look at discriminability?
came across this watching @adinamwilliams talk at #EMNLP23
IIUC, a dataset can be easy but discriminative (see IMBD in @stanfordnlp's HELM for example)
No?
why do we consider its difficulty, when intuitively we should look at discriminability?
came across this watching @adinamwilliams talk at #EMNLP23
IIUC, a dataset can be easy but discriminative (see IMBD in @stanfordnlp's HELM for example)
No?