i am searching for sequence labeling / tagging tasks in natural language processing (NLP).
Right now we are developing a system to solve a bunch (all?) of them and evaluated our current general architecture on part-of-speech tagging, named-entity recognition and classification tasks for English and German data.
We are thinking about adding chunking, anaphora detection (coreference mention detection) and predicate detection. Opinions on the sense of that are welcome.
Besides the tasks themselves, the appropriate data from shared-tasks/workshops are definitely of interest.
To summarize, this are the current tasks + data sources:
1. Part-of-Speech Tagging
2. Named-Entity Recognition and Classification
Additional data sets to the report ones are welcome.
Many Thanks in advance!