4.0.0 | 2020-04-19 | Changed to UDv2 tokenization (“new” LDC Treebank,for English); handles multi-word-tokens; improved UDv2-based taggers and parsers for English, French, German, Spanish; new French NER;new Chinese segmenter; library updates, bug fixes | arabic, chinese , english , english (kbp), french , german , spanish |
3.9.2 | 2018-10-05 | improved NER pipeline and entity mention confidences; support for Java 11; new POS models for English; 4 methods for setting document dates; tokenizer improvements; CoreNLP runs as filter from stdin to stdout; bug fixes | arabic, chinese , english , english (kbp), french , german , spanish |
3.9.1 | 2018-02-27 | Improve French tokenization, UD POS tagging, parsing; better German, Chinese NER; add Arabic SR parser model; bug fixes; minor enhancements | arabic, chinese , english , english (kbp), french , german , spanish |
3.9.0 | 2018-01-31 | Spanish KBP and new dependency parse model, wrapper API for data, quote attribution improvements, easier use of coref info, bug fixes | arabic, chinese , english , english (kbp), french , german , spanish |
3.8.0 | 2017-06-09 | Web service annotator, discussion forum handling, new French and Spanish UD POS models, emoji support | arabic, chinese , english , english (kbp), french , german , spanish |
3.7.0 | 2016-10-31 | Add KBP Annotator, Arabic pipeline; new neural English + Chinese coreference; improved Spanish models, German + Chinese NER, neural dependency parser models | arabic, chinese , english , english (kbp), french , german , spanish |
3.6.0 | 2015-12-09 | Improved coreference, OpenIE integration, Stanford CoreNLP server | chinese , english , french , german , spanish |
3.5.2 | 2015-04-20 | Switch to Universal Dependencies, add Chinese coreference system to CoreNLP. Release prepared by Jason Bolton. | caseless , chinese , shift reduce parser , spanish |
3.5.1 | 2015-01-29 | Substantial NER and dependency parsing improvements; new annotators for natural logic, quotes, and entity mentions. Release prepared by Jon Gauthier. | caseless , chinese , shift reduce parser , spanish |
3.5.0 | 2014-10-31 | Upgrade to Java 1.8; add annotators for dependency parsing, relation extraction. Release prepared by Jon Gauthier. | caseless , chinese , shift reduce parser , spanish |
3.4.1 | 2014-08-27 | Spanish models added. Release prepared by John Bauer. Last version to support Java 6 and Java 7. | caseless , chinese , shift reduce parser , spanish |
3.4 | 2014-06-16 | Shift-reduce parser and bootstrapped pattern-based entity extraction added | caseless , chinese , shift reduce parser |
3.3.1 | 2014-01-04 | Bugfix release | caseless , chinese |
3.3.0 | 2013-11-12 | Sentiment model added, minor sutime improvements, English and Chinese dependency improvements. Release prepared by John Bauer. | caseless , chinese |
3.2.0 | 2013-06-20 | Improved tagger speed, new and more accurate parser model | caseless , chinese |
1.3.5 | 2013-04-04 | Bugs fixed, speed improvements, coref improvements, Chinese support. Release prepared by John Bauer. | caseless , chinese |
1.3.4 | 2012-11-12 | Upgrades to sutime, dependency extraction code and English 3-class NER model. Release prepared by John Bauer. | caseless |
1.3.3 | 2012-07-09 | Minor bug fixes | caseless |
1.3.2 | 2012-05-22 | Upgrades to sutime, include tokenregex annotator | caseless |
1.3.1 | 2012-04-09 | Fixed thread safety bugs, caseless models available | caseless |
1.3.0 | 2012-01-08 | Fix a crashing bug, fix excessive warnings, threadsafe. Last version to support Java 5. | |
1.2.0 | 2011-09-14 | Added SUTime time phrase recognizer to NER, bug fixes, reduced library dependencies | |
1.1.0 | 2011-06-19 | Greatly improved coref results | |
1.0.4 | 2011-05-15 | DCoref uses less memory, already tokenized input possible | |
1.0.3 | 2011-04-17 | Add the ability to specify an arbitrary annotator. Release prepared by John Bauer. | |
1.0.2 | 2010-11-11 | Remove wn.jar for license reasons | |
1.0.1 | 2010-11-10 | Add the ability to remove XML | |
1.0 | 2010-11-01 | Initial release | |