Related papers: Hansel: A Chinese Few-Shot and Zero-Shot Entity Li…

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes…

While semantic segmentation has seen tremendous improvements in the past, there are still significant labeling efforts necessary and the problem of limited generalization to classes that have not been present during training. To address…

Existing evaluations of entity linking systems often say little about how the system is going to perform for a particular application. There are two fundamental reasons for this. One is that many evaluations only use aggregate measures…

We seek to address the lack of labeled data (and high cost of annotation) for textual entailment in some domains. To that end, we first create (for experimental purposes) an entailment dataset for the clinical domain, and a highly…

The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types. Few-shot learninghas not been investigated in this…

Understanding the semantic meaning of tabular data requires Entity Linking (EL), in order to associate each cell value to a real-world entity in a Knowledge Base (KB). In this work, we focus on end-to-end solutions for EL on tabular data…

Embedding commonsense knowledge is crucial for end-to-end models to generalize inference beyond training corpora. However, existing word analogy datasets have tended to be handcrafted, involving permutations of hundreds of words with only…

Rich entity representations are useful for a wide class of problems involving entities. Despite their importance, there is no standardized benchmark that evaluates the overall quality of entity representations. In this work, we propose…

Biomedical entity linking (EL) consists of named entity recognition (NER) and named entity disambiguation (NED). EL models are trained on corpora labeled by a predefined KB. However, it is a common scenario that only entities within a…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Event detection tasks can enable the quick detection of events from texts and provide powerful support for downstream natural language processing tasks. Most such methods can only detect a fixed set of predefined event classes. To extend…

The current state-of-the-art Entity Linking (EL) systems are geared towards corpora that are as heterogeneous as the Web, and therefore perform sub-optimally on domain-specific corpora. A key open problem is how to construct effective EL…

The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain a large proportion of mistakes in addition to being…

Entity Linking (EL), the task of mapping textual entity mentions to their corresponding entries in knowledge bases, constitutes a fundamental component of natural language understanding. Recent advancements in Large Language Models (LLMs)…

Named Entity Recognition (NER) is a critical task that requires substantial annotated data, making it challenging in low-resource scenarios where label acquisition is expensive. While zero-shot and instruction-tuned approaches have made…

We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly specialized domains, and so no metadata or alias tables are…

Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each class. We propose HyperShot - the fusion…

The prevalence of fake news across various online sources has had a significant influence on the public. Existing Chinese fake news detection datasets are limited to news sourced solely from Weibo. However, fake news originating from…

The grammatical analysis of texts in any written language typically involves a number of basic processing tasks, such as tokenization, morphological tagging, and dependency parsing. State-of-the-art systems can achieve high accuracy on…

Most computer aided pathology detection systems rely on large volumes of quality annotated data to aid diagnostics and follow up procedures. However, quality assuring large volumes of annotated medical image data can be subjective and…