Papers by Måns Magnusson
Detecting Legal Citations in United Kingdom Court Judgments (2025.emnlp-main)
Copied to clipboard
| Challenge: | citation detection in court judgments is challenging because of the complexity of legal language . citation analysis is critical for many legal applications, but the complexity is not always easy to solve. |
| Approach: | They compare three different models for citation detection in court judgments using the Cambridge Law Corpus . they compare rulebased regular expressions, transformer-based encoders and large language models . |
| Outcome: | The proposed model outperforms the existing models in the citation analysis and analysis of 190 court judgments. |
Interpretable Word Embeddings via Informative Priors (D19-1)
Copied to clipboard
| Challenge: | Existing word embeddings lack interpretability and are unsupervised . this limitation limits their use within computational social science and digital humanities. |
| Approach: | They propose to use informative priors to create interpretable dimensions for probabilistic word embeddings using a priori model. |
| Outcome: | The proposed models capture latent semantic concepts better than or on-par with the current state of the art while maintaining the simplicity and generalizability of priors. |
The Swedish Parliament Corpus 1867 – 2022 (2024.lrec-main)
Copied to clipboard
Väinö Aleksi Yrjänäinen, Fredrik Mohammadi Norén, Robert Borges, Johan Jarlbrink, Lotta Åberg Brorsson, Anders P. Olsson, Pelle Snickars, Måns Magnusson
| Challenge: | The Swedish Parliament Corpus is a new research corpus for the Swedish parliament. |
| Approach: | They propose to expand the Swedish Parliament corpus by providing a database of all members of parliament over 150 years. |
| Outcome: | The new corpus facilitates detailed analysis of parliamentary speeches in several research fields. |
Sparse Parallel Training of Hierarchical Dirichlet Process Topic Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | To scale non-parametric extensions of probabilistic topic models, practitioners rely increasingly on parallel and distributed systems. |
| Approach: | They propose a data-parallel sampler that utilizes all available sources of sparsity found in natural language to control memory requirements and computational complexity. |
| Outcome: | The proposed sampler is able to train a hierarchical Dirichlet process topic model on a well-known corpus (PubMed) with 8m documents and 768m tokens, using a single multi-core machine in under four days. |