Related papers: Semantic Labeling Using a Deep Contextualized Lang…
Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from…
Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels…
Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…
Deep learning has attracted great attention recently and yielded the state of the art performance in dimension reduction and classification problems. However, it cannot effectively handle the structured output prediction, e.g. sequential…
We present a novel approach to feature labeling using gradient descent in token-space. While existing methods typically use language models to generate hypotheses about feature meanings, our method directly optimizes label representations…
We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described…
Phrase mining is a fundamental text mining task that aims to identify quality phrases from context. Nevertheless, the scarcity of extensive gold labels datasets, demanding substantial annotation efforts from experts, renders this task…
Understanding the semantics of columns in relational tables is an important pre-processing step for indexing data lakes in order to provide rich data search. An approach to establishing such understanding is column type annotation (CTA)…
Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a…
Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a…
Semantic information is often represented as the entities and the relationships among them with conventional semantic models. This approach is straightforward but is not suitable for many posteriori requests in semantic data modeling. In…
In-context learning (ICL) enables large language models (LLMs) to perform new tasks using only a few demonstrations. However, in Named Entity Recognition (NER), existing ICL methods typically rely on task-agnostic semantic similarity for…
Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects.…
Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…
Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interaction data, performance often suffers when such semantic…
In software system design, one of the purposes of diagrammatic modeling is to explain something (e.g., data tables) to others. Very often, syntax of diagrams is specified while the intended meaning of diagrammatic constructs remains…
Semantic tagging, which has extensive applications in text mining, predicts whether a given piece of text conveys the meaning of a given semantic tag. The problem of semantic tagging is largely solved with supervised learning and today,…
Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations…
Traditional dataset retrieval systems rely on metadata for indexing, rather than on the underlying data values. However, high-quality metadata creation and enrichment often require manual annotations, which is a labour-intensive and…