Differences

This shows you the differences between two versions of the page.

--- udgroup [2023/04/22 19:01]
zeman Reference to Udify.
+++ udgroup [2023/05/03 13:42]
zeman Next meeting --> last meeting.
@@ Line 7: / Line 7: @@
 ===== Next Meeting =====
-The next meeting will be 2023-05-03 9:00 in S510. A paper will be presented by Dan, then discussed:
+See the future plans below.
-  * [[https://aclanthology.org/2021.eacl-demos.10/|Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh, and Thien Huu Nguyen. 2021. Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing]]
+===== Future Plans =====
-  * [[https://aclanthology.org/2020.acl-demos.14/|Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages]]
-  * [[https://aclanthology.org/D19-1279/|Dan Kondratyuk and Milan Straka. 2019. 75 Languages, 1 Model: Parsing Universal Dependencies Universally]]
+If there is interest, we can meet regardless of whether a semester is running (not necessarily with the same frequency).
-  * [[https://aclanthology.org/K18-2020/|Milan Straka. 2018. UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task]]
-  * [[https://aclanthology.org/K17-3009/|Milan Straka and Jana Straková. 2017. Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe]]
+Kira has tentatively booked Wednesday 2023-06-07 to present a paper about semantic roles on top of UD. At present, SIS does not allow me to book the room for a date beyond the end of May, so it is yet to be seen if we can meet in S510 again.
 ===== Papers to Read in the Future =====
@@ Line 23: / Line 23: @@
 ===== Past Meetings =====
+  * 2023-05-03: Dan presented an overview of several parsers for UD. The papers below are relevant (the one by Stymne et al. has been already presented by Federica). We will focus more on how we can use the parsers rather than on implementation details, so this time it will look less like a reading group session. If you only feel like reading some of the papers, I suggest focusing on the newer ones (Trankit, Stanza, and Udify, in this order).
+    * [[https://aclanthology.org/2021.eacl-demos.10/|Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh, and Thien Huu Nguyen. 2021. Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing]]
+    * [[https://aclanthology.org/2020.acl-demos.14/|Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages]]
+    * [[https://aclanthology.org/D19-1279/|Dan Kondratyuk and Milan Straka. 2019. 75 Languages, 1 Model: Parsing Universal Dependencies Universally]]
+    * [[https://aclanthology.org/P18-2098/|Sara Stymne, Miryam de Lhoneux, Aaron Smith, and Joakim Nivre. 2018. Parser Training with Heterogeneous Treebanks]] (already presented on 2023-04-05)
+    * [[https://aclanthology.org/K18-2020/|Milan Straka. 2018. UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task]]
+    * [[https://aclanthology.org/K17-3009/|Milan Straka and Jana Straková. 2017. Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe]]
+    * {{ :ud-parsers-2023.pdf |Dan's notes on the parsers}}
   * 2023-04-19: Discussion of a paper presented by Johnatan:
     * [[https://aclanthology.org/W18-6005/|Kaja Dobrovoljc and Matej Martinc. 2018. Er... well, it matters, right? On the role of data representations in spoken language dependency parsing]]

[ Back to the navigation ] [ Back to the content ]

Institute of Formal and Applied Linguistics Wiki

Differences