Related papers: Simplified DOM Trees for Transferable Attribute Ex…
Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain…
Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the…
Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact. Such domains employ atypical language models, have `long tails' and…
Unsupervised domain adaptation (UDA) has increasingly gained interests for its capacity to transfer the knowledge learned from a labeled source domain to an unlabeled target domain. However, typical UDA methods require concurrent access to…
Understanding the response of an output variable to multi-dimensional inputs lies at the heart of many data exploration endeavours. Topology-based methods, in particular Morse theory and persistent homology, provide a useful framework for…
Event argument extraction (EAE) has been well studied at the sentence level but under-explored at the document level. In this paper, we study to capture event arguments that actually spread across sentences in documents. Prior works usually…
Fine-grained aspect extraction is an essential sub-task in aspect based opinion analysis. It aims to identify the aspect terms (a.k.a. opinion targets) of a product or service in each sentence. However, expensive annotation process is…
Aspect-based sentiment analysis (ABSA) aims at extracting opinionated aspect terms in review texts and determining their sentiment polarities, which is widely studied in both academia and industry. As a fine-grained classification task, the…
Cross-modal feature extraction and integration have led to steady performance improvements in few-shot learning tasks due to generating richer features. However, existing multi-modal object detection (MM-OD) methods degrade when facing…
Extracting main content from web pages provides primary informative blocks that remove a web page's minor areas like navigation menu, ads, and site templates. The main content extraction has various applications: information retrieval,…
Aspect-based sentiment analysis has gained significant attention in recent years due to its ability to provide fine-grained insights for sentiment expressions related to specific features of entities. An important component of aspect-based…
Web Data Extraction is an important problem that has been studied by means of different scientific tools and in a broad range of applications. Many approaches to extracting data from the Web have been designed to solve specific problems and…
Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…
In this paper, a new approach called HDNA (HTML DNA) is introduced for analyzing and comparing Document Object Model (DOM) trees in order to detect differences in HTML pages. This method assigns an identifier to each HTML page based on its…
Recommending a diversity of product types (PTs) is important for a good shopping experience when customers are looking for products around their high-level shopping interests (SIs) such as hiking. However, the SI-PT connection is typically…
This paper presents several strategies to automatically obtain additional examples for in-context learning of one-shot relation extraction. Specifically, we introduce a novel strategy for example selection, in which new examples are…
In this paper, the problem of semantic information extraction for resource constrained text data transmission is studied. In the considered model, a sequence of text data need to be transmitted within a communication resource-constrained…
Document-level Relation Extraction (DocRE) is a more challenging task compared to its sentence-level counterpart. It aims to extract relations from multiple sentences at once. In this paper, we propose a semi-supervised framework for DocRE…
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instances. To this end, we…
In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation. We propose domain adaptation by sampling and exploiting only a meaningful subset from source data for training. Our…