no code implementations • EMNLP 2020 • Philipp Dufter, Hinrich Sch{\"u}tze
We aim to identify architectural properties of BERT and linguistic properties of languages that are necessary for BERT to become multilingual.
no code implementations • EACL 2021 • Lutfi Kerem Senel, Hinrich Sch{\"u}tze
Recent progress in pretraining language models on large corpora has resulted in significant performance gains on many NLP tasks.
1 code implementation • EACL 2021 • Timo Schick, Hinrich Sch{\"u}tze
Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with {``}task descriptions{''} in natural language (e. g., Radford et al., 2019).
1 code implementation • SEMEVAL 2020 • Ehsaneddin Asgari, Christoph Ringlstetter, Hinrich Sch{\"u}tze
This paper describes EmbLexChange, a system introduced by the {``}Life-Language{''} team for SemEval-2020 Task 1, on unsupervised detection of lexical-semantic changes.
no code implementations • COLING 2020 • Silvia Severini, Viktor Hangya, Alexander Fraser, Hinrich Sch{\"u}tze
In this paper, we enrich BWE-based BDI with transliteration information by using Bilingual Orthography Embeddings (BOEs).
1 code implementation • COLING 2020 • Sheng Liang, Philipp Dufter, Hinrich Sch{\"u}tze
Pretrained language models (PLMs) learn stereotypes held by humans and reflected in text from their training corpora, including gender bias.
1 code implementation • COLING 2020 • Philipp Dufter, Martin Schmitt, Hinrich Sch{\"u}tze
Self-Attention Networks (SANs) are an integral part of successful neural architectures such as Transformer (Vaswani et al., 2017), and thus of pretrained language models such as BERT (Devlin et al., 2019) or GPT-3 (Brown et al., 2020).
no code implementations • ACL 2020 • Valentin Hofmann, Hinrich Sch{\"u}tze, Janet Pierrehumbert
The auto-encoder models MWF in English surprisingly well by combining syntactic and semantic information with associative information from the mental lexicon.
no code implementations • ACL 2020 • Valentin Hofmann, Janet Pierrehumbert, Hinrich Sch{\"u}tze
We present the first study that examines the evolution of morphological families, i. e., sets of morphologically related words such as {``}trump{''}, {``}antitrumpism{''}, and {``}detrumpify{''}, in social media.
no code implementations • LREC 2020 • Anne Beyer, G{\"o}ran Kauermann, Hinrich Sch{\"u}tze
Prior work has determined domain similarity using text-based features of a corpus.
no code implementations • LREC 2020 • Silvia Severini, Viktor Hangya, Alex Fraser, er, Hinrich Sch{\"u}tze
We participate in both the open and closed tracks of the shared task and we show improved results of our method compared to simple vector similarity based approaches.
1 code implementation • LREC 2020 • Suteera Seeha, Ivan Bilan, Liliana Mamani Sanchez, Johannes Huber, Michael Matuschek, Hinrich Sch{\"u}tze
We propose ThaiLMCut, a semi-supervised approach for Thai word segmentation which utilizes a bi-directional character language model (LM) as a way to leverage useful linguistic knowledge from unlabeled data.
Ranked #3 on Thai Word Segmentation on BEST-2010
no code implementations • IJCNLP 2019 • Nina Poerner, Hinrich Sch{\"u}tze
We address the problem of Duplicate Question Detection (DQD) in low-resource domain-specific Community Question Answering forums.
no code implementations • WS 2019 • Shahbaz Syed, Michael V{\"o}lske, Nedim Lipka, Benno Stein, Hinrich Sch{\"u}tze, Martin Potthast
In this paper, we report on the results of the TL;DR challenge, discussing an extensive manual evaluation of the expected properties of a good summary based on analyzing the comments provided by human annotators.
no code implementations • ACL 2019 • Mengjie Zhao, Hinrich Sch{\"u}tze
We present a new method for sentiment lexicon induction that is designed to be applicable to the entire range of typological diversity of the world{'}s languages.
no code implementations • WS 2018 • Shahbaz Syed, Michael V{\"o}lske, Martin Potthast, Nedim Lipka, Benno Stein, Hinrich Sch{\"u}tze
The TL;DR challenge fosters research in abstractive summarization of informal text, the largest and fastest-growing source of textual data on the web, which has been overlooked by summarization research so far.
1 code implementation • ACL 2018 • Viktor Hangya, Fabienne Braune, Alex Fraser, er, Hinrich Sch{\"u}tze
Bilingual tasks, such as bilingual lexicon induction and cross-lingual classification, are crucial for overcoming data sparsity in the target language.
1 code implementation • ACL 2018 • Nina Poerner, Hinrich Sch{\"u}tze, Benjamin Roth
The behavior of deep neural networks (DNNs) is hard to understand.
no code implementations • CL 2017 • Sascha Rothe, Hinrich Sch{\"u}tze
We present AutoExtend, a system that combines word embeddings with semantic resources by learning embeddings for non-word objects like synsets and entities and learning word embeddings that incorporate the semantic information from the resource.
no code implementations • CL 2017 • Hassan Sajjad, Helmut Schmid, Alex Fraser, er, Hinrich Sch{\"u}tze
After training, the unlabeled data is disambiguated based on the posterior probabilities of the two sub-models.
no code implementations • EACL 2017 • Sanjeev Karn, Ulli Waltinger, Hinrich Sch{\"u}tze
We address fine-grained entity classification and propose a novel attention-based recurrent neural network (RNN) encoder-decoder that generates paths in the type hierarchy and can be trained end-to-end.
no code implementations • EACL 2017 • Hinrich Sch{\"u}tze
We introduce the first generic text representation model that is completely nonsymbolic, i. e., it does not require the availability of a segmentation or tokenization method that attempts to identify words or other symbolic units in text.
1 code implementation • COLING 2016 • Pankaj Gupta, Hinrich Sch{\"u}tze, Bernt Andrassy
This paper proposes a novel context-aware joint entity and word-level relation extraction approach through semantic composition of words, introducing a Table Filling Multi-Task Recurrent Neural Network (TF-MTRNN) model that reduces the entity recognition and relation classification tasks to a table-filling problem and models their interdependencies.
no code implementations • TACL 2014 • Tobias Schnabel, Hinrich Sch{\"u}tze
We present FLORS, a new part-of-speech tagger for domain adaptation.
no code implementations • LREC 2012 • Christian Scheible, Hinrich Sch{\"u}tze
We present a novel graph-theoretic method for the initial annotation of high-confidence training data for bootstrapping sentiment classifiers.