Hey Guys, The low resource anaphora resolution module <https://github.com/apertium/apertium-anaphora> of Apertium has a new release <https://github.com/apertium/apertium-anaphora/releases/tag/v1.0.0> .
A summary of the new features: - Arx files now accept multiple anaphor-antecedent types using parameters. - Scores can be given to individual parameters. - exclude-tags and lemma can also be used in pattern matching. - apertium-validate-anaphora is installed, which validates arx files using a dtd file. - Automated tests added. Run using make test. These features make the module a lot more customisable, and can help you tailor the arx file to your language pair and the kind of data you want to deal with. If you need anaphora resolution in your language pair then you can reply to this email or contact me on the IRC and I'll help you set it up. You can refer to the documentation <https://wiki.apertium.org/wiki/Anaphora_resolution_module> if you want to get an idea about what it looks like. Francis and I are writing a paper on this module so if your language pair needs anaphora resolution then we can work on it and it will help us evaluate the module on other languages as well. Any clarifications can be asked here or on the IRC. I'd also appreciate it if you guys let me know about any feature requests you might have from a module like this. :) Thanks and Regards, *तन्मय खन्ना * *Tanmai Khanna*
_______________________________________________ Apertium-stuff mailing list Apertium-stuff@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/apertium-stuff
