1 |
Come hither or go away? Recognising pre-electoral coalition signals in the news ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Come hither or go away? Recognising pre-electoral coalition signals in the news
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Treebanking user-generated content: a proposal for a unified representation in universal dependencies
|
|
|
|
In: Sanguinetti, Manuela orcid:0000-0002-0147-2208 , Bosco, Cristina, Cassidy, Lauren, Çetinoglu, Özlem, Cignarella, Alessandra Teresa orcid:0000-0002-4409-6679 , Lynn, Teresa, Rehbein, Ines, Ruppenhofer, Josef, Seddah, Djamé and Zeldes, Amir orcid:0000-0001-8016-6753 (2020) Treebanking user-generated content: a proposal for a unified representation in universal dependencies. In: 12th Language Resources and Evaluation Conference. (LREC 2020), 11-16 May 2020, Marseille, France. (2020)
|
|
BASE
|
|
Show details
|
|
11 |
Treebanking user-generated content: a proposal for a unified representation in universal dependencies
|
|
|
|
In: Sanguinetti, Manuela orcid:0000-0002-0147-2208 , Bosco, Cristina, Cassidy, Lauren, Çetinoglu, Özlem, Cignarella, Alessandra Teresa orcid:0000-0002-4409-6679 , Lynn, Teresa, Rehbein, Ines, Ruppenhofer, Josef, Seddah, Djamé and Zeldes, Amir orcid:0000-0001-8016-6753 (2020) Treebanking user-generated content: a proposal for a unified representation in universal dependencies. In: 12th Language Resources and Evaluation Conference. (LREC 2020), 11-16 May 2020, Marseille, France. (Virtual). (2020)
|
|
BASE
|
|
Show details
|
|
13 |
I got a construction looks funny - Representing and recovering non-standard constructions in UD ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Treebanking User-Generated Content: a UD Based Overview of Guidelines, Corpora and Unified Recommendations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Parsers Know Best: German PP Attachment Revisited ...
|
|
|
|
Abstract:
In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system's output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task. ...
|
|
Keyword:
Computer and Information Science; Natural Language Processing; Neural Network
|
|
URL: https://underline.io/lecture/6208-parsers-know-best-german-pp-attachment-revisited https://dx.doi.org/10.48448/nytj-y627
|
|
BASE
|
|
Hide details
|
|
16 |
German causal language annotations and lexicon (verbs, nouns, prepositions) (DE) ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Treebanking user-generated content: A proposal for a unified representation in universal dependencies
|
|
|
|
BASE
|
|
Show details
|
|
20 |
I’ve got a construction looks funny – representing and recovering non-standard constructions in UD
|
|
|
|
BASE
|
|
Show details
|
|
|
|