Search Results for author:
Found 48 papers, 22 papers with code
Evaluating neural network explanation methods using hybrid documents and morphological agreement
The behavior of deep neural networks (DNNs) is hard to understand.
Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement
The behavior of deep neural networks (DNNs) is hard to understand.
Knodle: Modular Weakly Supervised Learning with PyTorch
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.
ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision
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.
Position-aware Self-attention with Relative Positional Encodings for Slot Filling
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.
Multilingual Relation Extraction using Compositional Universal Schema
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.
Joint Bootstrapping Machines for High Confidence Relation Extraction
Semi-supervised bootstrapping techniques for relationship extraction from text iteratively expand a set of initial seed instances.
KnowMAN: Weakly Supervised Multinomial Adversarial Networks
The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training.
Interpretable Textual Neuron Representations for NLP
Input optimization methods, such as Google Deep Dream, create interpretable representations of neurons for computer vision DNNs.
Text-Guided Image Clustering
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.
Ranking vs. Classifying: Measuring Knowledge Base Completion Quality
We randomly remove some of these correct answers from the data set, simulating the realistic scenario of real-world entities missing from a KB.
ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion
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.
Data Centric Domain Adaptation for Historical Text with OCR Errors
We propose new methods for in-domain and cross-domain Named Entity Recognition (NER) on historical data for Dutch and French.
MemeGraphs: Linking Memes to Knowledge Graphs
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.
Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal
Instead of cleaning the dataset prior to model training, the dataset is dynamically adjusted during the training process.
WeaNF: Weak Supervision with Normalizing Flows
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.
XPASC: Measuring Generalization in Weak Supervision by Explainability and Association
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.
ReInform: Selecting paths with reinforcement learning for contextualized link prediction
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.
Counterfactual Reasoning with Knowledge Graph Embeddings
We further observe that KGEs adapted with COULDD solidly detect plausible counterfactual changes to the graph that follow these patterns.
Neural Architectures for Open-Type Relation Argument Extraction
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.
Comparing Convolutional Neural Networks to Traditional Models for Slot Filling
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".
Compositional Vector Space Models for Knowledge Base Completion
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).
Assessing Wikipedia-Based Cross-Language Retrieval Models
For a combined model, another interesting question is therefore how to integrate different weighting schemes.
Effective Slot Filling Based on Shallow Distant Supervision Methods
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%.
Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks
In this work, we propose a new model for aspect-based sentiment analysis.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Aligning Very Small Parallel Corpora Using Cross-Lingual Word Embeddings and a Monogamy Objective
Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora.
A Gold Standard for Relation Extraction in the Food Domain
We present a gold standard for semantic relation extraction in the food domain for German.
UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages
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.
Domain adaptation for part-of-speech tagging of noisy user-generated text
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.
Interpretable Question Answering on Knowledge Bases and Text
Our results suggest that IP provides better explanations than LIME or attention, according to both automatic and human evaluation.
Intent Recognition in Doctor-Patient Interviews
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.
Dirichlet-Smoothed Word Embeddings for Low-Resource Settings
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.
Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)
Welcome to WeaSuL 2021, the First Workshop on Weakly Supervised Learning, co-located with ICLR 2021.
Focused Contrastive Training for Test-based Constituency Analysis
We propose a scheme for self-training of grammaticality models for constituency analysis based on linguistic tests.
Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection
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.
Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?
In recent years, deep neural language models have made strong progress in various NLP tasks.
WeaNF”:" Weak Supervision with Normalizing Flows
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.
Topic Segmentation of Research Article Collections
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.
SepLL: Separating Latent Class Labels from Weak Supervision Noise
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.
Cross-functional Analysis of Generalisation in Behavioural Learning
In behavioural testing, system functionalities underrepresented in the standard evaluation setting (with a held-out test set) are validated through controlled input-output pairs.
Functionality learning through specification instructions
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.
Specification Overfitting in Artificial Intelligence
Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency.
