Related papers: Retrieving Versus Understanding Extractive Evidenc…
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…
Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the…
The most common tools for word-alignment rely on a large amount of parallel sentences, which are then usually processed according to one of the IBM model algorithms. The training data is, however, the same as for machine translation (MT)…
Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…
Few-Shot Relation Extraction aims at predicting the relation for a pair of entities in a sentence by training with a few labelled examples in each relation. Some recent works have introduced relation information (i.e., relation labels or…
We present a large-scale empirical investigation of the zero-shot learning phenomena in a specific recognizing textual entailment (RTE) task category, i.e. the automated mining of leaderboards for Empirical AI Research. The prior reported…
Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth…
Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document. In this paper, we pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided…
Uncertainty in machine learning models is a timely and vast field of research. In supervised learning, uncertainty can already occur in the first stage of the training process, the annotation phase. This scenario is particularly evident…
Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these…
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…
There is growing recognition that many NLP tasks lack a single ground truth, as human judgments reflect diverse perspectives. To capture this variation, models have been developed to predict full annotation distributions rather than…
Relation extraction (RE) is a standard information extraction task playing a major role in downstream applications such as knowledge discovery and question answering. Although decoder-only large language models are excelling in generative…
Multi-label classification is prevalent in real-world settings, but the behavior of Large Language Models (LLMs) in this setting is understudied. We investigate how autoregressive LLMs perform multi-label classification, focusing on…
Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of…
With the rise in edge-computing devices, there has been an increasing demand to deploy energy and resource-efficient models. A large body of research has been devoted to developing methods that can reduce the size of the model considerably…
An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from…
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…
Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…
One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…