Magnus Sahlgren

Active Learning and Visual Analytics for Stance Classification with ALVA

2017 · ACM Transactions on Interactive Intelligent Systems

The automatic detection and classification of stance (e.g., certainty or agreement) in text data using natural language processing and machine-learning methods creates an opportunity to gain insight into the speakers’ attitudes toward their own and …

Measuring Issue Ownership using Word Embeddings

2018 · arXiv (Cornell University)

Sentiment and topic analysis are common methods used for social media monitoring. Essentially, these methods answers questions such as, "what is being talked about, regarding X", and "what do people feel, regarding X". In this …

Semantic Re-tuning with Contrastive Tension

2021 · KTH Publication Database DiVA (KTH Royal Institute of Technology)

Extracting semantically useful natural language sentence representations frompre-trained deep neural networks such as Transformers remains a challenge. Wefirst demonstrate that pre-training objectives impose a significant task bias ontothe final layers of models, with a layer-wise …

Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead?

2021 · arXiv (Cornell University)

Most work in NLP makes the assumption that it is desirable to develop solutions in the native language in question. There is consequently a strong trend towards building native language models even for low-resource languages. …