Search Results for author:
Found 23 papers, 13 papers with code
What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns
From a human-centric perspective, through demonstration studies and a user study, we show that our token pattern approach helps users understand the systematic differences of language model outputs, and we are able to discover relevant differences caused by prompt and model changes (e. g. related to gender or culture), thus supporting the prompt engineering process and human-centric model behavior research.
Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set
Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations.
Semantic Component Analysis: Discovering Patterns in Short Texts Beyond Topics
Topic modeling is a key method in text analysis, but existing approaches are limited by assuming one topic per document or fail to scale efficiently for large, noisy datasets of short texts.
Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial.
The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs.
A Piece of Theatre: Investigating How Teachers Design LLM Chatbots to Assist Adolescent Cyberbullying Education
In offering this tool, we explore teachers' distinctive needs when designing chatbots to assist their teaching, and how chatbot design tools might better support them.
Understanding and Mitigating Classification Errors Through Interpretable Token Patterns
Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors, but also gives a way to act and improve the classifier.
Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages
However, text classification in low-resource languages is still challenging due to the lack of annotated data.
Meta Self-Refinement for Robust Learning with Weak Supervision
Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost.
MCSE: Multimodal Contrastive Learning of Sentence Embeddings
Learning semantically meaningful sentence embeddings is an open problem in natural language processing.
Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification
Incorrect labels in training data occur when human annotators make mistakes or when the data is generated via weak or distant supervision.
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.
ANEA: Distant Supervision for Low-Resource Named Entity Recognition
Distant supervision allows obtaining labeled training corpora for low-resource settings where only limited hand-annotated data exists.
Low Resource Named Entity Recognition
named-entity-recognition
+2
Analysing the Noise Model Error for Realistic Noisy Label Data
Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors.
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios
Deep neural networks and huge language models are becoming omnipresent in natural language applications.
Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages
Multilingual transformer models like mBERT and XLM-RoBERTa have obtained great improvements for many NLP tasks on a variety of languages.
On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers
Our analysis reveals that while fine-tuning indeed changes the representations of a pre-trained model and these changes are typically larger for higher layers, only in very few cases, fine-tuning has a positive effect on probing accuracy that is larger than just using the pre-trained model with a strong pooling method.
Learning Functions to Study the Benefit of Multitask Learning
Although multitask learning has achieved improved performance in some problems, there are also tasks that lose performance when trained together.
Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá
Techniques such as distant and weak supervision can be used to create labeled data in a (semi-) automatic way.
Low Resource Named Entity Recognition
named-entity-recognition
+3
Feature-Dependent Confusion Matrices for Low-Resource NER Labeling with Noisy Labels
In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but often noisy.
Low Resource Named Entity Recognition
named-entity-recognition
+4
Using Multi-Sense Vector Embeddings for Reverse Dictionaries
However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word.
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
In our experiments on Chunking and NER, this approach performs more robustly than the baselines.
Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data
Manually labeled corpora are expensive to create and often not available for low-resource languages or domains.
