WNNLP 2021 program

In this post you will find the detailed program for the WNNLP 2021 workshop, which will be held on May 27th 12:00 - 14:00.

• 12:00 - 12:05 Welcome
• 12:05 - 12:10 Task overview: Natural Language Inference
• 12:10 - 12:15 Erik Andreas Johansson and Myrthe Lammerse "BERT for natural language inference on the MultiNLI and XNLI"
• 12:15 - 12:20 Sondre Wold "The Effect of Different Hyperparameters on BERT for Natural Language Inference"
• 12:20 - 12:25 Vilde A. Huseby and Bendik M. Aas "Cross-Lingual Natural Language Inference on XNLI using Multilingual BERT"
• 12:25 - 12:30 Daniel Clemeth Bjerkeland "Training BERT for Natural Language Inference or: How I Learned to Stop Worrying and Love Contextual Embeddings"
• 12:30 - 12:35 Adrian Nadau Semb, Daniel Sharifi and Haiyue Chen "Natural Language Inference with BERT"
• 12:35 - 12:40 Task overview: Word Sense Induction with contextualized language models
• 12:40 - 12:45 Tita Enstad and Markus Sverdvik Heiervang "Interpreting transformer (dis)ambiguity with word sense induction"
• 12:45 - 12:50 Justyna Ozog "Task of Word Sense Induction with Contextualized Language Models evaluated with Adjusted Rand Index"
• 12:50 - 12:55 Nikolas Martin and Anette Fredriksen "More than One Way to Cluster Lexical Ambiguity: Evaluating WSI Methods with Adjusted Rand Index"
• 12:55 - 13:10 Break
• 13:10 - 13:15 Task overview: Targeted Sentiment Analysis for Norwegian
• 13:15 - 13:20 Anthi Papadopoulou "A comparison of BiLSTM and BERT models for Norwegian Targeted Sentiment Analysis"
• 13:20 - 13:25 Nicholas Walker "To BERT or not to BERT: Design Choices Matter in Targeted Semantic Analysis"
• 13:25 - 13:30 Iver Wellerop, Bjørn-Andreas Lamo and Stian Skjold Granerød "Experiments in fine-grained sentiment analysis for Norwegian"
• 13:30 - 13:35 Yauhen Khutarniuk "Targeted Sentiment Analysis"
• 13:35 - 13:40 Torbjørn Dahl "Targeted Sentiment Analysis for Norwegian using NorBERT and NorELMo"
• 13:40 - 13:50 Per Halvorsen, Fabio Rodrigues Pereira and Eivind Grønlie Guren "Applying Multitask Learning to Targeted Sentiment Analysis using Transformer-Based Models" (BEST PAPER)
• 13:50 - 14:00 Closing