no code implementations • 30 Nov 2022 • Kishaloy Halder, Josip Krapac, Alan Akbik, Anthony Brew, Matti Lyra
In a series of experiments, we show that this yields a number of interesting benefits: (1) The resulting order induced by distances in the embedding space can be used to directly explain classification decisions.
no code implementations • NAACL (ACL) 2022 • Angelo Ziletti, Alan Akbik, Christoph Berns, Thomas Herold, Marion Legler, Martina Viell
Medical coding (MC) is an essential pre-requisite for reliable data retrieval and reporting.
1 code implementation • ACL 2021 • Matthias Vogt, Ulf Leser, Alan Akbik
We define and study the task of early sexual predator detection (eSPD) in chats, where the goal is to analyze a running chat from its beginning and predict grooming attempts as early and as accurately as possible.
Ranked #1 on Early Sexual Predator Detection (eSPD) on PANC
1 code implementation • COLING 2020 • Kishaloy Halder, Alan Akbik, Josip Krapac, Roland Vollgraf
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.
1 code implementation • 13 Nov 2020 • Stefan Schweter, Alan Akbik
Current state-of-the-art approaches for named entity recognition (NER) typically consider text at the sentence-level and thus do not model information that crosses sentence boundaries.
2 code implementations • 17 Aug 2020 • Leon Weber, Mario Sänger, Jannes Münchmeyer, Maryam Habibi, Ulf Leser, Alan Akbik
Summary: Named Entity Recognition (NER) is an important step in biomedical information extraction pipelines.
1 code implementation • NAACL 2019 • Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, Rol Vollgraf,
We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models.
no code implementations • NAACL 2019 • Alan Akbik, Tanja Bergmann, Rol Vollgraf,
We make all code and pre-trained models available to the research community for use and reproduction.
1 code implementation • COLING 2018 • Alan Akbik, Duncan Blythe, Rol Vollgraf,
Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters.
Ranked #2 on Chunking on Penn Treebank
no code implementations • 2 Mar 2018 • Duncan Blythe, Alan Akbik, Roland Vollgraf
Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words.
no code implementations • EMNLP 2017 • Alan Akbik, Rol Vollgraf,
Previous works proposed annotation projection in parallel corpora to inexpensively generate treebanks or propbanks for new languages.
no code implementations • EMNLP 2017 • Chenguang Wang, Alan Akbik, Laura Chiticariu, Yunyao Li, Fei Xia, Anbang Xu
Crowdsourcing has proven to be an effective method for generating labeled data for a range of NLP tasks.
no code implementations • COLING 2016 • Alan Akbik, Xinyu Guan, Yunyao Li
To address these issues, we propose to manually alias TL verbs to existing English frames.
no code implementations • COLING 2016 • Alan Akbik, Yunyao Li
To overcome this challenge, we propose the use of instance-based learning that performs no explicit generalization, but rather extrapolates predictions from the most similar instances in the training data.
no code implementations • COLING 2016 • Alan Akbik, Laura Chiticariu, Marina Danilevsky, Yonas Kbrom, Yunyao Li, Huaiyu Zhu
We present PolyglotIE, a web-based tool for developing extractors that perform Information Extraction (IE) over multilingual data.
no code implementations • LREC 2014 • Johannes Kirschnick, Alan Akbik, Holmer Hemsen
The increasing availability and maturity of both scalable computing architectures and deep syntactic parsers is opening up new possibilities for Relation Extraction (RE) on large corpora of natural language text.
no code implementations • LREC 2014 • Alan Akbik, Thilo Michael
We present the Weltmodell, a commonsense knowledge base that was automatically generated from aggregated dependency parse fragments gathered from over 3. 5 million English language books.