Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Niko Schenk"'
Autor:
Christian Chiarcos, Ilya Khait, Émilie Pagé-Perron, Niko Schenk, Jayanth, Christian Fäth, Julius Steuer, William Mcgrath, Jinyan Wang
Publikováno v:
Information, Vol 9, Iss 11, p 290 (2018)
This paper describes work on the morphological and syntactic annotation of Sumerian cuneiform as a model for low resource languages in general. Cuneiform texts are invaluable sources for the study of history, languages, economy, and cultures of Ancie
Externí odkaz:
https://doaj.org/article/0be8641633e24c25b7af1292b8656894
Autor:
Niko Schenk, Himanshu Choudhary, Rachit Bansal, Ravneet Punia, Jacob L. Dahl, Émilie Pagé-Perron
Publikováno v:
ACL (student)
Despite the recent advancements of attention-based deep learning architectures across a majority of Natural Language Processing tasks, their application remains limited in a low-resource setting because of a lack of pre-trained models for such langua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8ba0ec0a7f1a61ea2b65ef7a91c0416
https://doi.org/10.18653/v1/2021.acl-srw.5
https://doi.org/10.18653/v1/2021.acl-srw.5
Autor:
William Mcgrath, Émilie Pagé-Perron, Jinyan Wang, Niko Schenk, Jayanth, Christian Chiarcos, Christian Fäth, Julius Steuer, Ilya Khait
Publikováno v:
Information
Volume 9
Issue 11
Information, Vol 9, Iss 11, p 290 (2018)
Volume 9
Issue 11
Information, Vol 9, Iss 11, p 290 (2018)
This paper describes work on the morphological and syntactic annotation of Sumerian cuneiform as a model for low resource languages in general. Cuneiform texts are invaluable sources for the study of history, languages, economy, and cultures of Ancie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8920a1942d2dcdec5dd2e3a7ef033ab5
Autor:
Niko Schenk, Christian Chiarcos
Publikováno v:
LSDSem@EACL
We present a resource-lean neural recognizer for modeling coherence in commonsense stories. Our lightweight system is inspired by successful attempts to modeling discourse relations and stands out due to its simplicity and easy optimization compared
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc590b2bf62177afe80bebb8d9a8cbd1
https://doi.org/10.18653/v1/w17-0910
https://doi.org/10.18653/v1/w17-0910
Publikováno v:
ACL (2)
We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling scheme and is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a39b08c328b14c753de5db7b7745fbf2
Autor:
Christian Chiarcos, Niko Schenk
Publikováno v:
HLT-NAACL
Gold annotations for supervised implicit semantic role labeling are extremely sparse and costly. As a lightweight alternative, this paper describes an approach based on unsupervised parsing which can do without iSRL-specific training data: We induce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e85e0d19b8a5ec3ae0a4907150b0243e
https://doi.org/10.18653/v1/n16-1173
https://doi.org/10.18653/v1/n16-1173
Autor:
Evgeny A. Stepanov, Samuel Rönnqvist, Niko Schenk, Giuseppe Riccardi, Christian Chiarcos, Kathrin Donandt
Publikováno v:
CoNLL Shared Task
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::247f70e74f0a136ededa8d78d30e9492
https://doi.org/10.18653/v1/k16-2005
https://doi.org/10.18653/v1/k16-2005
Autor:
Christian Chiarcos, Niko Schenk
Publikováno v:
SIGDIAL Conference
We propose a generic, memory-based approach for the detection of implicit semantic roles. While state-of-the-art methods for this task combine hand-crafted rules with specialized and costly lexical resources, our models use large corpora with automat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3774b1453df02d5e093d47edd4cdffb
https://doi.org/10.18653/v1/w15-4626
https://doi.org/10.18653/v1/w15-4626
Autor:
Niko Schenk, Christian Chiarcos
Publikováno v:
CoNLL Shared Task
We describe a minimalist approach to shallow discourse parsing in the context of the CoNLL 2015 Shared Task. 1 Our parser integrates a rule-based component for argument identification and datadriven models for the classification of explicit and impli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::291d13fa2eabc3973d4ff9e07adddb9a
https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/103976
https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/103976
Publikováno v:
SEM@NAACL-HLT
We induce semantic association networks from translation relations in parallel corpora. The resulting semantic spaces are encoded in a single reference language, which ensures cross-language comparability. As our main contribution, we cluster the obt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b9a56a0e5b777cd1d2fbfeb3d9bf855
https://doi.org/10.18653/v1/s15-1014
https://doi.org/10.18653/v1/s15-1014