1

Neural Machine Translation Methods for Translating Text to Sign Language Glosses
State-of-the-art techniques common to low resource Machine Translation (MT) are applied to improve MT of spoken language text to Sign …
PDF Cite
Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods
Saliency maps can explain a neural model’s predictions by identifying important input features. They are difficult to interpret …
PDF Cite Code
Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes …
PDF Code DOI
MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset
Relation extraction (RE) is a fundamental task in information extraction, whose extension to multilingual settings has been hindered by …
PDF Cite Code Dataset Project Project Project DOI
VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets
The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between …
PDF Cite Code Project
Adapters for Resource-Efficient Deployment of NLU Models
Modern Transformer-based language models such as BERT are huge and, therefore, expensive to deploy in practical applications. In …
PDF Cite Code
Fighting Disinformation: Overview of Recent AI-Based Collaborative Human-Computer Interaction for Intelligent Decision Support Systems
Methods for automatic disinformation detection have gained much attention in recent years, as false information can have a severe …
PDF Cite
Findings of the WMT 2022 Biomedical Translation Shared Task: Monolingual Clinical Case Reports
In the seventh edition of the WMT Biomedical Task, we addressed a total of seven languagepairs, namely English/German, English/French, …
PDF Cite
Multilingual Relation Classification via Efficient and Effective Prompting
Prompting pre-trained language models has achieved impressive performance on various NLP tasks, especially in low data regimes. Despite …
PDF Cite Code Project DOI
Full-Text Argumentation Mining on Scientific Publications
Scholarly Argumentation Mining (SAM) has recently gained attention due to its potential to help scholars with the rapid growth of …
PDF Cite Code Project