Large Language Models (LLMs) such as ChatGPT have demonstrated remarkabl...
Online job ads serve as a valuable source of information for skill
requi...
Since performing exercises (including, e.g., practice tests) forms a cru...
Background: More than 400,000 biomedical concepts and some of their
rela...
Intent discovery is the task of inferring latent intents from a set of
u...
Timely and accurate extraction of Adverse Drug Events (ADE) from biomedi...
This paper shines a light on the potential of definition-based semantic
...
In our continuously evolving world, entities change over time and new,
p...
Bayesian Networks may be appealing for clinical decision-making due to t...
Multiple choice questions (MCQs) are widely used in digital learning sys...
This work introduces BioLORD, a new pre-training strategy for producing
...
For text classification tasks, finetuned language models perform remarka...
We introduce a high-quality dataset that contains 3,397 samples comprisi...
Skills play a central role in the job market and many human resources (H...
Models for bankruptcy prediction are useful in several real-world scenar...
This work presents a new dialog dataset, CookDial, that facilitates rese...
Job titles form a cornerstone of today's human resources (HR) processes....
We consider the task of document-level entity linking (EL), where it is
...
We consider a joint information extraction (IE) model, solving named ent...
In online domain-specific customer service applications, many companies
...
Powerful sentence encoders trained for multiple languages are on the ris...
This paper presents DWIE, the 'Deutsche Welle corpus for Information
Ext...
Solving math word problems is a cornerstone task in assessing language
u...
Information extracted from electrohysterography recordings could potenti...
Neural networks have achieved state of the art performance across a wide...
Established recurrent neural networks are well-suited to solve a wide va...
This paper introduces improved methods for sub-event detection in social...
Character-level features are currently used in different neural network-...
Inducing sparseness while training neural networks has been shown to yie...
Adversarial training (AT) is a regularization method that can be used to...
We extend sequence-to-sequence models with the possibility to control th...
Many Machine Reading and Natural Language Understanding tasks require re...
We introduce DeepProbLog, a probabilistic logic programming language tha...
State-of-the-art models for joint entity recognition and relation extrac...
Recurrent neural networks are nowadays successfully used in an abundance...
In this paper we develop a relatively simple and effective neural joint ...
The amount of content on online music streaming platforms is immense, an...
Comprehending lyrics, as found in songs and poems, can pose a challenge ...
In adversarial training, a set of models learn together by pursuing comp...
Short text messages such as tweets are very noisy and sparse in their us...
Methods based on representation learning currently hold the state-of-the...
We present four training and prediction schedules from the same
characte...
Levering data on social media, such as Twitter and Facebook, requires
in...
A crucial aspect of a knowledge base population system that extracts new...