Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Alan Akbik"'
Publikováno v:
ACL/IJCNLP (1)
An important risk that children face today is online grooming, where a so-called sexual predator establishes an emotional connection with a minor online with the objective of sexual abuse. Prior work has sought to automatically identify grooming chat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6334e18532ab69207bc0b978793fe671
https://doi.org/10.18653/v1/2021.acl-long.386
https://doi.org/10.18653/v1/2021.acl-long.386
Publikováno v:
Bioinformatics
Summary: Named Entity Recognition (NER) is an important step in biomedical information extraction pipelines. Tools for NER should be easy to use, cover multiple entity types, highly accurate, and robust towards variations in text genre and style. To
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c89f7475140fdcbf7a7f8a6de4860ca9
https://gfzpublic.gfz-potsdam.de/pubman/item/item_5005588_2/component/file_5008100/5005588.pdf
https://gfzpublic.gfz-potsdam.de/pubman/item/item_5005588_2/component/file_5008100/5005588.pdf
Publikováno v:
COLING
State-of-the-art approaches for text classification leverage a transformer architecture with a linear layer on top that outputs a class distribution for a given prediction problem. While effective, this approach suffers from conceptual limitations th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::295a606206caf06ba6c3dbb18635e803
https://doi.org/10.18653/v1/2020.coling-main.285
https://doi.org/10.18653/v1/2020.coling-main.285
Autor:
Alan Akbik, Tanja Bergmann, Kashif Rasul, Duncan A. J. Blythe, Stefan Schweter, Roland Vollgraf
Publikováno v:
NAACL-HLT (Demonstrations)
We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models. The core idea of the framework is to present a simple, unified interface for conceptua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed896e12477c50c021aa161c1f8c2809
https://doi.org/10.18653/v1/n19-4010
https://doi.org/10.18653/v1/n19-4010
Publikováno v:
NAACL-HLT (1)
Contextual string embeddings are a recent type of contextualized word embedding that were shown to yield state-of-the-art results when utilized in a range of sequence labeling tasks. They are based on character-level language models which treat text
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94cf694180a0dda019f66376eac75299
https://doi.org/10.18653/v1/n19-1078
https://doi.org/10.18653/v1/n19-1078
Publikováno v:
EMNLP
Crowdsourcing has proven to be an effective method for generating labeled data for a range of NLP tasks. However, multiple recent attempts of using crowdsourcing to generate gold-labeled training data for semantic role labeling (SRL) reported only mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7dc20404f1d5d83f68b45602e99a7dd2
https://doi.org/10.18653/v1/d17-1205
https://doi.org/10.18653/v1/d17-1205
Autor:
Alan Akbik, Yunyao Li
Publikováno v:
ACL (System Demonstrations)
Semantic role labeling (SRL) identifies the predicate-argument structure in text with semantic labels. It plays a key role in understanding natural language. In this paper, we present POLYGLOT, a multilingual semantic role labeling system capable of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4d2421a43ed270412893fbbc90331a1
https://doi.org/10.18653/v1/p16-4001
https://doi.org/10.18653/v1/p16-4001
Publikováno v:
EMNLP
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dc2f1c49f1e70450e69dc48653063990
https://doi.org/10.18653/v1/d16-1102
https://doi.org/10.18653/v1/d16-1102
Autor:
Alan Akbik, Yunyao Li, Laura Chiticariu, Marina Danilevsky, Huaiyu Zhu, Shivakumar Vaithyanathan
Publikováno v:
ACL (1)
Semantic role labeling (SRL) is crucial to natural language understanding as it identifies the predicate-argument structure in text with semantic labels. Unfortunately, resources required to construct SRL models are expensive to obtain and simply do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::382b6dd222252c8927e8ffe917208689
https://doi.org/10.3115/v1/p15-1039
https://doi.org/10.3115/v1/p15-1039
Autor:
Alan Akbik, Roland Vollgraf
Publikováno v:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
EMNLP (System Demonstrations)
EMNLP (System Demonstrations)
Previous works proposed annotation projection in parallel corpora to inexpensively generate treebanks or propbanks for new languages. In this approach, linguistic annotation is automatically transferred from a resource-rich source language (SL) to tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::26b8e8532c8698cdbb7397e0e7b04700