Extract content of judgements

phHartl / eu-judgement-analyse

Quantitative analysis of judgments of the European Court of Justice

MIT License

6 stars 0 forks source link

Extract content of judgements #4

Open phHartl opened 4 years ago

phHartl commented 4 years ago

What is each judgement about?

phHartl commented 3 years ago

Could be done by keyword extraction.

phHartl commented 3 years ago

Added keyword extraction with 8befa59. N-grams are already present for corpora and single documents. Topic modeling might be the way to go for corpora, but this will take a lot of computational time, so we should pre-compute those for specific corpora.

phHartl commented 3 years ago

Part of the content extraction process is also named entity recognition (which has already been implemented).

phHartl commented 3 years ago

I'm currently thinking about implementing a summary algorithm for single documents (transformer models) or topic modeling for a bigger corpus.