Filters








7 Hits in 5.9 sec

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches [article]

Tianze Shi, Lillian Lee
2020 arXiv   pre-print
We empirically compare these two common strategies--parsing and tagging--for predicting flat MWEs.  ...  Experimental results on the MWE-Aware English Dependency Corpus and on six non-English dependency treebanks with frequent flat structures show that: (1) tagging is more accurate than parsing for identifying  ...  Acknowledgments We thank the three anonymous reviewers for their comments, and Igor Malioutov, Ana Smith and the Cornell NLP group for discussion and comments.  ... 
arXiv:2005.03035v1 fatcat:wyj2riyvc5h4fazrgefxwdbnui

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches

Tianze Shi, Lillian Lee
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
We empirically compare these two common strategies-parsing and tagging-for predicting flat MWEs.  ...  Experimental results on the MWE-Aware English Dependency Corpus and on six non-English dependency treebanks with frequent flat structures show that: (1) tagging is more accurate than parsing for identifying  ...  Acknowledgments We thank the three anonymous reviewers for their comments, and Igor Malioutov, Ana Smith and the Cornell NLP group for discussion and comments.  ... 
doi:10.18653/v1/2020.acl-main.775 fatcat:aof4tvavnfbk7mfo4ghrupttcm

Enhanced Representations and Efficient Analysis of Syntactic Dependencies Within and Beyond Tree Structures

Tianze Shi
2021
designs that combine parsing and tagging modules.  ...  By integrating a tagging view of the MWEs into decoding processes, the parsers become more accurate in MWE identification.  ...  She has been an amazing collaborator, educator, mentor, and friend. I am constantly blown away by how sharp she is in capturing interesting research ideas from all kinds of seem-  ... 
doi:10.7298/jm0e-tj72 fatcat:uve5oocwrndizb3ervx6vmqva4

Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics [article]

Preslav Nakov
2019 arXiv   pre-print
Understanding noun compounds' syntax and semantics is important for many natural language applications, including question answering, machine translation, information retrieval, and information extraction  ...  I extend this approach by introducing novel surface features and paraphrases, which yield state-of-the-art results for the task of noun compound bracketing.  ...  This query will extract three-word noun compounds, provided that the POS tagging and the shallow-parse annotations are correct.  ... 
arXiv:1912.01113v1 fatcat:3ubstjtd7nhphmw4kbewls3onq

Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics (Dagstuhl Seminar 21351)

Timothy Baldwin, William Croft, Joakim Nivre, Agata Savary
2021
Computational linguistics builds models that can usefully process and produce language and that can increase our understanding of linguistic phenomena.  ...  Additionally, if models and methods are to be consistent and valid across languages, they have to face specificities inherent either to particular languages, or to various linguistic traditions.  ...  Part-of-speech tags are taken from a revised and extended version of the Google universal part-of-speech tag set containing a fixed inventory of 17 categories.  ... 
doi:10.4230/dagrep.11.7.89 fatcat:xuqth2nd3ndeppznp6sksxc2ha

Dagstuhl Reports, Volume 11, Issue 7, August 2021, Complete Issue [article]

2021
We have investigated the interplay of temporal and multi-way interactions in [3] and found effects, that differ from their projections.  ...  In my talk, I outline two ways of extending higher-order model research, motivated by my previous work on the interplay of dynamics and multi-body topology [1, 2].  ...  Overview -Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating Typed Dependency Parses from Phrase Structure Parses.  ... 
doi:10.4230/dagrep.11.7 fatcat:4b73kynisffo7payzzghe5rfiq

German clause-embedding predicates : an extraction and classification approach [article]

Ekaterina Lapshinova-Koltunski, Universität Stuttgart, Universität Stuttgart
2011
Our extraction and classification procedures are precision-oriented, which means that we focus on high accuracy of our extraction and classification results.  ...  This thesis describes a semi-automatic approach to the analysis of subcategorisation properties of verbal, nominal and multiword predicates in German.  ...  Acknowledgements Appendix We attach examples of the extracted and classified data in the appendix 3 . It contains also the description of annotations applied on the used corpora.  ... 
doi:10.18419/opus-2693 fatcat:oczpfca4fvd2fiizl7u2k7iche