Accepted Papers
- A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets
Iva Bojic, Josef Evan Halim, Verena Karina Suharman, Sreeja Tar, Qi Chwen Ong, Duy Phung, Mathieu Ravaut, Shafiq Joty and Josip Car
- An Empirical Study on Active Learning for Multi-label Text Classification
Mengqi Wang and Ming Liu
- Annotating PubMed Abstracts with MeSH Headings using Graph Neural Network
Faizan Mustafa, Rafika Boutalbi and Anastasiia Iurshina
- What Does BERT actually Learn about Event Coreference? Probing Structural Information in a Fine-Tuned Dutch Language Model
Loic De Langhe, Orphee De Clercq and Veronique Hoste
- Do not Trust the Experts: How the Lack of Standard Complicates NLP for Historical Irish
Oksana Dereza, Theodorus Fransen and John P. McCrae
- Edit Aware Representation Learning via Levenshtein Prediction
Edison Marrese-taylor, Machel Reid and Alfredo Solano
- Estimating Numbers without Regression
Avijit Thawani, Jay Pujara and Ashwin Kalyan
- What changes when you randomly choose BPE merge operations? Not much.
Jonne Saleva and Constantine Lignos
- SocBERT: A Pretrained Model for Social Media Text
Yuting Guo and Abeed Sarker
- Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation
Lorenzo Lupo, Marco Dinarelli and Laurent Besacier
- ERATE: Efficient Retrieval Augmented Text Embeddings
Vatsal Raina, Nora Kassner, Kashyap Popat, Patrick Lewis, Nicola Cancedda and Louis Martin
- Estimating Numbers without Regression
Avijit Thawani, Jay Pujara and Ashwin Kalyan
- Exploring the Reasons for Non-generalizability of KBQA systems
Sopan Khosla, Ritam Dutt, Vinayshekhar Bannihatti Kumar and Rashmi Gangadharaiah
- Hiding in Plain Sight: Insights into Abstractive Text Summarization
Vivek Srivastava, Savita Bhat and Niranjan Pedanekar
- Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
Anya Belz, Craig Thomson and Ehud Reiter