Word-level saliency explanations ("heat maps over words") are often used...
This paper describes our system developed for the SemEval-2023 Task 12
"...
Prompting pre-trained language models leads to promising results across
...
The importance of explainability is increasingly acknowledged in natural...
The detection and normalization of temporal expressions is an important ...
While a lot of research in explainable AI focuses on producing effective...
The field of natural language processing (NLP) has recently seen a large...
In this paper, we explore possible improvements of transformer models in...
Natural language inference (NLI) requires models to learn and apply
comm...
When humans solve complex problems, they rarely come up with a decision
...
The performance of relation extraction models has increased considerably...
In low-resource settings, model transfer can help to overcome a lack of
...
The recognition and normalization of clinical information, such as tumor...
Current developments in natural language processing offer challenges and...
Certain embedding types outperform others in different scenarios, e.g.,
...
Simple yet effective data augmentation techniques have been proposed for...
Explainable question answering systems predict an answer together with a...
Natural language processing has huge potential in the medical domain whi...
Named entity recognition has been extensively studied on English news te...
This paper presents a new challenging information extraction task in the...
Exploiting natural language processing in the clinical domain requires
d...
Although temporal tagging is still dominated by rule-based systems, ther...
Recent work showed that embeddings from related languages can improve th...
The slot filling task aims at extracting answers for queries about entit...
The automatic detection of satire vs. regular news is relevant for downs...
This paper describes the CIS slot filling system for the TAC Cold Start
...
We study cross-lingual sequence tagging with little or no labeled data i...
Character-level models of tokens have been shown to be effective at deal...
In this paper, we demonstrate the importance of coreference resolution f...
This paper presents our latest investigations on different features for
...
This paper addresses the problem of corpus-level entity typing, i.e.,
in...
We introduce globally normalized convolutional neural networks for joint...
In this paper, we address two different types of noise in information
ex...
Neural networks with attention have proven effective for many natural
la...
We introduce the first generic text representation model that is complet...
This paper investigates two different neural architectures for the task ...
We address relation classification in the context of slot filling, the t...