[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki


[ Back to the navigation ]

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
udgroup [2023/04/22 19:12]
zeman Reference to UUParser.
udgroup [2023/05/15 22:33]
zeman Next meeting.
Line 7: Line 7:
 ===== Next Meeting ===== ===== Next Meeting =====
  
-The next meeting will be 2023-05-03 9:00 in S510. A paper will be presented by Dan, then discussed:+  * The next meeting will be 2023-05-24 9:00 in S510. A set of papers will be presented by Abishek, then discussed: 
 +    * [[https://aclanthology.org/W19-8007|Adam Przepiórkowski, Agnieszka Patejuk. 2019. Nested Coordination in Universal Dependencies. UDW-SyntaxFest 2019]] 
 +    * [[https://aclanthology.org/W18-6009|Hiroshi Kanayama et al. 2018. Coordinate Structures in Universal Dependencies for Head-final Languages]] 
 +    * [[https://aclanthology.org/2021.eacl-main.67|Grünewald et al. 2021. Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling. EACL 2021]] (optional)
  
-  * [[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 QiYuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher DManning. 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 interestwe can meet regardless of whether a semester is running (not necessarily with the same frequency)
-  * [[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]] +Kira has tentatively booked Wednesday 2023-06-07 to present a paper about semantic roles on top of UD. At presentSIS does not allow me to book the room for a date beyond the end of Mayso it is yet to be seen if we can meet in S510 again.
-  * [[https://aclanthology.org/K17-3009/|Milan Straka and Jana Straková. 2017. TokenizingPOS TaggingLemmatizing and Parsing UD 2.0 with UDPipe]]+
  
 ===== Papers to Read in the Future ===== ===== Papers to Read in the Future =====
Line 20: Line 22:
 Feel free to add your wishes to the list. Feel free to add your wishes to the list.
  
-  * [[https://aclanthology.org/R17-1077/|Ondřej Pražák and Miloslav Konopík2017Cross-Lingual SRL Based upon Universal Dependencies]] (Kira)+  * [[https://aclanthology.org/2022.lrec-1.181/|Ishan Jindal, Alexandre Rademaker, Michał Ulewicz, Linh Ha, Huyen Nguyen, Khoi-Nguyen Tran, Huaiyu Zhu and Yunyao Li2022. Universal Proposition Bank 2.0]] (Kira) 
 +  * A paper proposed by Saša (not yet officially published; parsing Polish, combined dependencies and constituents) 
 +  * [[https://aclanthology.org/2023.eacl-main.76/|Artur Kulmizev, Joakim Nivre. 2023. Investigating UD Treebanks via Dataset Difficulty Measures]] 
 +  * [[https://aclanthology.org/2023.eacl-main.158/|Jivnesh Sandhan, Laxmidhar Behera, Pawan Goyal. 2023. Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing]] 
 +  * [[https://aclanthology.org/2023.eacl-srw.2/|Tuğba Pamay Arslan and Gülşen Eryiğit. 2023. Incorporating Dropped Pronouns into Coreference Resolution: The case for Turkish]]
  
 ===== Past Meetings ===== ===== 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 looked 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:   * 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]]     * [[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 ]