Explanation-based human debugging of nlp models: A survey
P Lertvittayakumjorn, F Toni - Transactions of the Association for …, 2021 - direct.mit.edu
Debugging a machine learning model is hard since the bug usually involves the training
data and the learning process. This becomes even harder for an opaque deep learning …
data and the learning process. This becomes even harder for an opaque deep learning …
Black-box error diagnosis in Deep Neural Networks for computer vision: a survey of tools
Abstract The application of Deep Neural Networks (DNNs) to a broad variety of tasks
demands methods for coping with the complex and opaque nature of these architectures …
demands methods for coping with the complex and opaque nature of these architectures …
ConvXAI: Delivering heterogeneous AI explanations via conversations to support human-AI scientific writing
Despite a surge collection of XAI methods, users still struggle to obtain required AI
explanations. Previous research suggests chatbots as dynamic solutions, but the effective …
explanations. Previous research suggests chatbots as dynamic solutions, but the effective …
ApplicaAI at SemEval-2020 task 11: On RoBERTa-CRF, span CLS and whether self-training helps them
D Jurkiewicz, Ł Borchmann, I Kosmala… - arXiv preprint arXiv …, 2020 - arxiv.org
This paper presents the winning system for the propaganda Technique Classification (TC)
task and the second-placed system for the propaganda Span Identification (SI) task. The …
task and the second-placed system for the propaganda Span Identification (SI) task. The …
Named Entity Recognition--Is there a glass ceiling?
T Stanislawek, A Wróblewska, A Wójcicka… - arXiv preprint arXiv …, 2019 - arxiv.org
Recent developments in Named Entity Recognition (NER) have resulted in better and better
models. However, is there a glass ceiling? Do we know which types of errors are still hard or …
models. However, is there a glass ceiling? Do we know which types of errors are still hard or …
Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models
Large Language Models (LLMs) have significantly impacted the writing process, enabling
collaborative content creation and enhancing productivity. However, generating high-quality …
collaborative content creation and enhancing productivity. However, generating high-quality …
Contract discovery: Dataset and a few-shot semantic retrieval challenge with competitive baselines
Ł Borchmann, D Wiśniewski, A Gretkowski… - arXiv preprint arXiv …, 2019 - arxiv.org
We propose a new shared task of semantic retrieval from legal texts, in which a so-called
contract discovery is to be performed, where legal clauses are extracted from documents …
contract discovery is to be performed, where legal clauses are extracted from documents …
Open challenge for correcting errors of speech recognition systems
M Kubis, Z Vetulani, M Wypych… - Language and Technology …, 2019 - Springer
The paper announces the new long-term challenge for improving the performance of
automatic speech recognition systems. The goal of the challenge is to investigate methods …
automatic speech recognition systems. The goal of the challenge is to investigate methods …
Seeking innovation: The research protocol for SMEs' networking
The paper aims to state the research protocol for the innovation-seeking behavior of Small-
to Medium-sized Enterprises (SMEs), related to the classification of knowledge needs …
to Medium-sized Enterprises (SMEs), related to the classification of knowledge needs …
GrASP: A library for extracting and exploring human-interpretable textual patterns
Data exploration is an important step of every data science and machine learning project,
including those involving textual data. We provide a novel language tool, in the form of a …
including those involving textual data. We provide a novel language tool, in the form of a …