4 papers · 1 filter
Human Label Variation in Implicit Discourse Relation Recognition
Frances Yung, Daniil Ignatev, Merel Scholman +2
There is growing recognition that many NLP tasks lack a single ground truth, as human judgments reflect diverse perspectives. To capture this variation, models have been developed…
Don't Learn, Ground: A Case for Natural Language Inference with Visual Grounding
Daniil Ignatev, Ayman Santeer, Albert Gatt +1
We propose a zero-shot method for Natural Language Inference (NLI) that leverages multimodal representations by grounding language in visual contexts. Our approach generates visual…
DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning
Daniil Ignatev, Nan Li, Hugh Mee Wong +2
This system paper presents the DeMeVa team's approaches to the third edition of the Learning with Disagreements shared task (LeWiDi 2025; Leonardelli et al., 2025). We explore two…
Disentangling the Roles of Representation and Selection in Data Pruning
Yupei Du, Yingjin Song, Hugh Mee Wong +3
Data pruning, selecting small but impactful subsets, offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design c…