Search Results for author: Benjamin Roth

Found 40 papers, 15 papers with code

WeaNF”:" Weak Supervision with Normalizing Flows

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.

ReInform: Selecting paths with reinforcement learning for contextualized link prediction

1 code implementation19 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.

Link Prediction reinforcement-learning

SepLL: Separating Latent Class Labels from Weak Supervision Noise

1 code implementation25 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.

text-classification Text Classification

XPASC: Measuring Generalization in Weak Supervision by Explainability and Association

1 code implementation3 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.

Association

Topic Segmentation of Research Article Collections

no code implementations18 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.

named-entity-recognition Named Entity Recognition +1

Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?

no code implementations12 May 2022 Lukas Thoma, Benjamin Roth

In recent years, deep neural language models have made strong progress in various NLP tasks.

Language Acquisition

WeaNF: Weak Supervision with Normalizing Flows

2 code implementations28 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.

ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision

no code implementations14 Apr 2022 Anastasiia Sedova, Benjamin Roth

A way to overcome expensive and time-consuming manual data labeling is weak supervision - automatic annotation of data samples via a predefined set of labeling functions (LFs), rule-based mechanisms that generate potentially erroneous labels.

Denoising

Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection

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.

Hate Speech Detection

Focused Contrastive Training for Test-based Constituency Analysis

no code implementations30 Sep 2021 Benjamin Roth, Erion Çano

We propose a scheme for self-training of grammaticality models for constituency analysis based on linguistic tests.

Language Modelling

KnowMAN: Weakly Supervised Multinomial Adversarial Networks

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.

Language Modelling

Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)

no code implementations8 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.

Knodle: Modular Weakly Supervised Learning with PyTorch

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.

BIG-bench Machine Learning Sentiment Analysis +1

Ranking vs. Classifying: Measuring Knowledge Base Completion Quality

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.

Knowledge Base Completion Model Selection

Dirichlet-Smoothed Word Embeddings for Low-Resource Settings

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.

Word Embeddings Word Similarity

Intent Recognition in Doctor-Patient Interviews

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.

Information Retrieval Intent Recognition +1

Interpretable Question Answering on Knowledge Bases and Text

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.

Question Answering

Domain adaptation for part-of-speech tagging of noisy user-generated text

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.

Domain Adaptation Part-Of-Speech Tagging +2

UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages

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.

Sentiment Analysis Unsupervised Domain Adaptation

Interpretable Textual Neuron Representations for NLP

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.

Position-aware Self-attention with Relative Positional Encodings for Slot Filling

1 code implementation9 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.

Relation Extraction slot-filling +1

Joint Bootstrapping Machines for High Confidence Relation Extraction

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.

Relationship Extraction (Distant Supervised)

Neural Architectures for Open-Type Relation Argument Extraction

no code implementations5 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.

Question Answering

Comparing Convolutional Neural Networks to Traditional Models for Slot Filling

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".

Classification General Classification +3

Multilingual Relation Extraction using Compositional Universal Schema

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.

Relation Extraction slot-filling +3

Compositional Vector Space Models for Knowledge Base Completion

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).

Knowledge Base Completion Zero-Shot Learning

Assessing Wikipedia-Based Cross-Language Retrieval Models

no code implementations10 Jan 2014 Benjamin Roth

For a combined model, another interesting question is therefore how to integrate different weighting schemes.

Language Modelling Machine Translation +2

Effective Slot Filling Based on Shallow Distant Supervision Methods

no code implementations6 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%.

Relation Extraction Retrieval +3

Cannot find the paper you are looking for? You can Submit a new open access paper.