1 code implementation • 19 Jan 2018 • Nina Poerner, Benjamin Roth, Hinrich Schütze
The behavior of deep neural networks (DNNs) is hard to understand.
1 code implementation • ACL 2018 • Nina Poerner, Hinrich Sch{\"u}tze, Benjamin Roth
The behavior of deep neural networks (DNNs) is hard to understand.
1 code implementation • ACL (RepL4NLP) 2021 • Anastasiia Sedova, Andreas Stephan, Marina Speranskaya, Benjamin Roth
Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture.
1 code implementation • 14 Apr 2022 • Anastasiia Sedova, Benjamin Roth
A cost-effective alternative to manual data labeling is weak supervision (WS), where data samples are automatically annotated using a predefined set of labeling functions (LFs), rule-based mechanisms that generate artificial labels for the associated classes.
1 code implementation • 9 Jul 2018 • Ivan Bilan, Benjamin Roth
The self-attention encoder also uses a custom implementation of relative positional encodings which allow each word in the sentence to take into account its left and right context.
1 code implementation • NAACL 2016 • Patrick Verga, David Belanger, Emma Strubell, Benjamin Roth, Andrew McCallum
In response, this paper introduces significant further improvements to the coverage and flexibility of universal schema relation extraction: predictions for entities unseen in training and multilingual transfer learning to domains with no annotation.
1 code implementation • NAACL 2018 • Pankaj Gupta, Benjamin Roth, Hinrich Schütze
Semi-supervised bootstrapping techniques for relationship extraction from text iteratively expand a set of initial seed instances.
1 code implementation • EMNLP 2021 • Luisa März, Ehsaneddin Asgari, Fabienne Braune, Franziska Zimmermann, Benjamin Roth
The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training.
2 code implementations • WS 2018 • Nina Poerner, Benjamin Roth, Hinrich Schütze
Input optimization methods, such as Google Deep Dream, create interpretable representations of neurons for computer vision DNNs.
1 code implementation • 5 Feb 2024 • Andreas Stephan, Lukas Miklautz, Kevin Sidak, Jan Philip Wahle, Bela Gipp, Claudia Plant, Benjamin Roth
We, therefore, propose Text-Guided Image Clustering, i. e., generating text using image captioning and visual question-answering (VQA) models and subsequently clustering the generated text.
1 code implementation • AKBC 2020 • Marina Speranskaya, Martin Schmitt, Benjamin Roth
We randomly remove some of these correct answers from the data set, simulating the realistic scenario of real-world entities missing from a KB.
1 code implementation • 10 May 2023 • Anastasiia Sedova, Benjamin Roth
In this paper, we attempt for the first time cold-start calibration for KGC, where no annotated examples exist initially for calibration, and only a limited number of tuples can be selected for annotation.
2 code implementations • 2 Jul 2021 • Luisa März, Stefan Schweter, Nina Poerner, Benjamin Roth, Hinrich Schütze
We propose new methods for in-domain and cross-domain Named Entity Recognition (NER) on historical data for Dutch and French.
1 code implementation • 28 May 2023 • Vasiliki Kougia, Simon Fetzel, Thomas Kirchmair, Erion Çano, Sina Moayed Baharlou, Sahand Sharifzadeh, Benjamin Roth
In this work, we propose to use scene graphs, that express images in terms of objects and their visual relations, and knowledge graphs as structured representations for meme classification with a Transformer-based architecture.
1 code implementation • 7 Jun 2023 • Anastasiia Sedova, Lena Zellinger, Benjamin Roth
Instead of cleaning the dataset prior to model training, the dataset is dynamically adjusted during the training process.
2 code implementations • 28 Apr 2022 • Andreas Stephan, Benjamin Roth
In this work, we explore a novel direction of generative modeling for weak supervision: Instead of modeling the output of the annotation process (the labeling function matches), we generatively model the input-side data distributions (the feature space) covered by labeling functions.
1 code implementation • 3 Jun 2022 • Luisa März, Ehsaneddin Asgari, Fabienne Braune, Franziska Zimmermann, Benjamin Roth
To verify this assumption, we introduce a novel method, XPASC (eXPlainability-Association SCore), for measuring the generalization of a model trained with a weakly supervised dataset.
1 code implementation • 19 Nov 2022 • Marina Speranskaya, Sameh Methias, Benjamin Roth
We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer.
1 code implementation • 11 Mar 2024 • Lena Zellinger, Andreas Stephan, Benjamin Roth
We further observe that KGEs adapted with COULDD solidly detect plausible counterfactual changes to the graph that follow these patterns.
no code implementations • 5 Mar 2018 • Benjamin Roth, Costanza Conforti, Nina Poerner, Sanjeev Karn, Hinrich Schütze
In this work, we introduce the task of Open-Type Relation Argument Extraction (ORAE): Given a corpus, a query entity Q and a knowledge base relation (e. g.,"Q authored notable work with title X"), the model has to extract an argument of non-standard entity type (entities that cannot be extracted by a standard named entity tagger, e. g. X: the title of a book or a work of art) from the corpus.
no code implementations • NAACL 2016 • Heike Adel, Benjamin Roth, Hinrich Schütze
We address relation classification in the context of slot filling, the task of finding and evaluating fillers like "Steve Jobs" for the slot X in "X founded Apple".
no code implementations • IJCNLP 2015 • Arvind Neelakantan, Benjamin Roth, Andrew McCallum
Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X, Y) from bornIn(X, Y).
no code implementations • 10 Jan 2014 • Benjamin Roth
For a combined model, another interesting question is therefore how to integrate different weighting schemes.
no code implementations • 6 Jan 2014 • Benjamin Roth, Tassilo Barth, Michael Wiegand, Mittul Singh, Dietrich Klakow
In the TAC KBP 2013 English Slotfilling evaluation, the submitted main run of the LSV RelationFactory system achieved the top-ranked F1-score of 37. 3%.
no code implementations • EMNLP 2018 • Martin Schmitt, Simon Steinheber, Konrad Schreiber, Benjamin Roth
In this work, we propose a new model for aspect-based sentiment analysis.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 31 Oct 2018 • Nina Poerner, Masoud Jalili Sabet, Benjamin Roth, Hinrich Schütze
Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora.
no code implementations • LREC 2012 • Michael Wiegand, Benjamin Roth, Eva Lasarcyk, Stephanie Köser, Dietrich Klakow
We present a gold standard for semantic relation extraction in the food domain for German.
no code implementations • LREC 2020 • Ehsaneddin Asgari, Fabienne Braune, Benjamin Roth, Christoph Ringlstetter, Mohammad R. K. Mofrad
We introduce a method called DomDrift to mitigate the huge domain mismatch between Bible and Twitter by a confidence weighting scheme that uses domain-specific embeddings to compare the nearest neighbors for a candidate sentiment word in the source (Bible) and target (Twitter) domain.
no code implementations • NAACL 2019 • Luisa März, Dietrich Trautmann, Benjamin Roth
We propose an architecture that trains an out-of-domain model on a large newswire corpus, and transfers those weights by using them as a prior for a model trained on the target domain (a data-set of German Tweets) for which there is very little an-notations available.
no code implementations • ACL 2019 • Alona Sydorova, Nina Poerner, Benjamin Roth
Our results suggest that IP provides better explanations than LIME or attention, according to both automatic and human evaluation.
no code implementations • LREC 2020 • Robin Rojowiec, Benjamin Roth, Maximilian Fink
For some intent classes, the data only contains a few samples, and we apply Information Retrieval and Deep Learning methods that are robust with respect to small amounts of training data for recognizing the intent of an utterance and providing the correct response.
no code implementations • LREC 2020 • Jakob Jungmaier, Nora Kassner, Benjamin Roth
We evaluate on standard word similarity data sets and compare to word2vec and the recent state of the art for low-resource settings: Positive and Unlabeled (PU) Learning for word embeddings.
no code implementations • 8 Jul 2021 • Michael A. Hedderich, Benjamin Roth, Katharina Kann, Barbara Plank, Alex Ratner, Dietrich Klakow
Welcome to WeaSuL 2021, the First Workshop on Weakly Supervised Learning, co-located with ICLR 2021.
no code implementations • 30 Sep 2021 • Benjamin Roth, Erion Çano
We propose a scheme for self-training of grammaticality models for constituency analysis based on linguistic tests.
1 code implementation • nlppower (ACL) 2022 • Pedro Henrique Luz de Araujo, Benjamin Roth
Behavioural testing -- verifying system capabilities by validating human-designed input-output pairs -- is an alternative evaluation method of natural language processing systems proposed to address the shortcomings of the standard approach: computing metrics on held-out data.
no code implementations • 12 May 2022 • Lukas Thoma, Benjamin Roth
In recent years, deep neural language models have made strong progress in various NLP tasks.
no code implementations • RepL4NLP (ACL) 2022 • Andreas Stephan, Benjamin Roth
In this work, we explore a novel direction of generative modeling for weak supervision”:" Instead of modeling the output of the annotation process (the labeling function matches), we generatively model the input-side data distributions (the feature space) covered by labeling functions.
no code implementations • 18 May 2022 • Erion Çano, Benjamin Roth
In this work, we perform topic segmentation of a paper data collection that we crawled and produce a multitopic dataset of roughly seven million paper data records.
1 code implementation • 25 Oct 2022 • Andreas Stephan, Vasiliki Kougia, Benjamin Roth
In this work, we provide a method for learning from weak labels by separating two types of complementary information associated with the labeling functions: information related to the target label and information specific to one labeling function only.
1 code implementation • 22 May 2023 • Pedro Henrique Luz de Araujo, Benjamin Roth
In behavioural testing, system functionalities underrepresented in the standard evaluation setting (with a held-out test set) are validated through controlled input-output pairs.
no code implementations • 14 Nov 2023 • Pedro Henrique Luz de Araujo, Benjamin Roth
A core aspect of our analysis is to measure the effect that including a set of specifications has on a held-out set of unseen, qualitatively different specifications.
no code implementations • 13 Mar 2024 • Benjamin Roth, Pedro Henrique Luz de Araujo, Yuxi Xia, Saskia Kaltenbrunner, Christoph Korab
Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency.