Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Marc Schulder"'
Publikováno v:
PLoS ONE, Vol 19, Iss 5, p e0304040 (2024)
This study investigates head nods in natural dyadic German Sign Language (DGS) interaction, with the aim of finding whether head nods serving different functions vary in their phonetic characteristics. Earlier research on spoken and sign language int
Externí odkaz:
https://doaj.org/article/5fd452aa495744c5aea02c827c3b5953
Publikováno v:
Natural Language Engineering. :1-38
We examine the binary classification of sentiment views for verbal multiword expressions (MWEs). Sentiment views denote the perspective of the holder of some opinion. We distinguish between MWEs conveying the view of the speaker of the utterance (e.g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2a5cba3f94b7d6ddd918e2d415a609f
https://doi.org/10.1017/s1351324923000153
https://doi.org/10.1017/s1351324923000153
Publikováno v:
Natural Language Engineering. 27:153-179
Alleviating pain is good and abandoning hope is bad. We instinctively understand how words like alleviate and abandon affect the polarity of a phrase, inverting or weakening it. When these words are content words, such as verbs, nouns, and adjectives
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a41ff68df84dcdf83714f36bdb2105f3
https://doi.org/10.1017/s135132492000039x
https://doi.org/10.1017/s135132492000039x
Publikováno v:
HLT-NAACL
We examine different features and classifiers for the categorization of opinion words into actor and speaker view. To our knowledge, this is the first comprehensive work to address sentiment views on the word level taking into consideration opinion v
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5247cf1be8ad139f8c750b182466a1e
https://doi.org/10.18653/v1/n16-1092
https://doi.org/10.18653/v1/n16-1092
Publikováno v:
INTERSPEECH
The use of prior situational/contextual knowledge about a given task can significantly improve automatic speech recognition (ASR) performance. This is typically done through adaptation of acoustic or language models if data is available or using know
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6da312c0df2caca46530bac9c09bedb
https://doi.org/10.21437/interspeech.2015-476
https://doi.org/10.21437/interspeech.2015-476
Publikováno v:
WASSA@EMNLP
We offer a critical review of the current state of opinion role extraction involving opinion verbs. We argue that neither the currently available lexical resources nor the manually annotated text corpora are sufficient to appropriately study this tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7a305e6845d77d002d79b02851f4fc4
https://doi.org/10.18653/v1/w15-2921
https://doi.org/10.18653/v1/w15-2921
Autor:
Oliver Ohneiser, Dietrich Klakow, Anna Schmidt, Arif Ullah Khan, Marc Schulder, Youssef Oualil, Hartmut Helmke, Matthias Kleinert
Publikováno v:
SLT
This paper presents an approach for incorporating situational context information into an on-line Automatic Speech Recognition (ASR) component of an Air Traffic Control (ATC) assistance system to improve recognition performance. Context information i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15110186fddc871577c4fa35f373711b
https://doi.org/10.1109/slt.2014.7078542
https://doi.org/10.1109/slt.2014.7078542
Autor:
Marc Schulder, Eduard Hovy
Publikováno v:
Proceedings of the Second Workshop on Metaphor in NLP.
Most computational approaches to metaphor detection try to leverage either conceptual metaphor mappings or selectional preferences. Both require extensive knowledge of the mappings/preferences in question, as well as sufficient data for all involved
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b847bf21df3d7431fa1ae69583a8f8d2
https://doi.org/10.3115/v1/w14-2303
https://doi.org/10.3115/v1/w14-2303
Autor:
Danet, Claire, Thomas, Chloé, Adrien, Contesse, Rébulard, Morgane, Bianchini, Claudia S., Chevrefils, Léa, Doan, Patrick
Research on sign languages (SLs) requires dedicated, efficient and comprehensive transcription systems to analyze and compare the sign parameters; at present, many transcription systems focus on manual parameters, relegating the non-manual component
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::00350c738aaa103d523b52bb1fcc1c09
https://hal.science/hal-03741152
https://hal.science/hal-03741152
