Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Heike Adel"'
Publikováno v:
Natural Language Engineering. :1-24
Many research topics in natural language processing (NLP), such as explanation generation, dialog modeling, or machine translation, require evaluation that goes beyond standard metrics like accuracy or F1 score toward a more human-centered approach.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0827fc60244786cfd8863e8f821669fd
https://doi.org/10.1017/s1351324922000535
https://doi.org/10.1017/s1351324922000535
Publikováno v:
Proceedings of the 7th Workshop on Representation Learning for NLP.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dae5c503ef4396ab2e371c02ebfa836a
https://doi.org/10.18653/v1/2022.repl4nlp-1.19
https://doi.org/10.18653/v1/2022.repl4nlp-1.19
The field of natural language processing (NLP) has recently seen a large change towards using pre-trained language models for solving almost any task. Despite showing great improvements in benchmark datasets for various tasks, these models often perf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f25f7b8ec6094e2ccee06c4db2465c12
Publikováno v:
BioNLP-OST@EMNLP-IJNCLP
Named entity recognition has been extensively studied on English news texts. However, the transfer to other domains and languages is still a challenging problem. In this paper, we describe the system with which we participated in the first subtrack o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1009d199586e2467809ec4b41b9b717
http://arxiv.org/abs/2007.01022
http://arxiv.org/abs/2007.01022
Publikováno v:
ACL
Exploiting natural language processing in the clinical domain requires de-identification, i.e., anonymization of personal information in texts. However, current research considers de-identification and downstream tasks, such as concept extraction, on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8d97d34d8f901266d3974670ace1a91
http://arxiv.org/abs/2005.09397
http://arxiv.org/abs/2005.09397
Publikováno v:
EMNLP (1)
Explainable question answering systems predict an answer together with an explanation showing why the answer has been selected. The goal is to enable users to assess the correctness of the system and understand its reasoning process. However, we show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21675632dbf46367c8f83dee10a9ead0
Publikováno v:
NAACL-HLT
Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in low-resource settin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::167b307daeea6856ab801d42104f974d
Autor:
Xiang Dai, Heike Adel
Publikováno v:
COLING
Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design and compare data augmentation for named entity recognition, which is usu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::631382758ad9e7d8326eb489c3a8d1ba
https://doi.org/10.18653/v1/2020.coling-main.343
https://doi.org/10.18653/v1/2020.coling-main.343
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030624187
ISWC (1)
ISWC (1)
Clustering entities over knowledge graphs (KGs) is an asset for explorative search and knowledge discovery. KG embeddings have been intensively investigated, mostly for KG completion, and have potential also for entity clustering. However, embeddings
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4deecd32520f49c0254d1aa49e6f6039
https://doi.org/10.1007/978-3-030-62419-4_13
https://doi.org/10.1007/978-3-030-62419-4_13
This paper adds to the ongoing discussion in the natural language processing community on how to choose a good development set. Motivated by the real-life necessity of applying machine learning models to different data distributions, we propose a clu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d8ecbf0379a8c127aa2914edb45f9fc
https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/105662
https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/105662