Related papers: Nested Dictionary Learning for Hierarchical Organi…

Dependency trees help relation extraction models capture long-range relations between words. However, existing dependency-based models either neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively, or…

This paper have two parts. In the first part we discuss word embeddings. We discuss the need for them, some of the methods to create them, and some of their interesting properties. We also compare them to image embeddings and see how word…

We introduce an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentences, which in turn are bags of words). This framework can be…

Bilingual word embeddings, which representlexicons of different languages in a shared em-bedding space, are essential for supporting se-mantic and knowledge transfers in a variety ofcross-lingual NLP tasks. Existing approachesto training…

Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text…

Mining structured knowledge from tweets using named entity recognition (NER) can be beneficial for many down stream applications such as recommendation and intention understanding. With tweet posts tending to be multimodal, multimodal named…

Automatically generating a natural language description of an image is a task close to the heart of image understanding. In this paper, we present a multi-model neural network method closely related to the human visual system that…

Neural network techniques are widely applied to obtain high-quality distributed representations of words, i.e., word embeddings, to address text mining, information retrieval, and natural language processing tasks. Recently, efficient…

We study the problem of automatically building hypernym taxonomies from textual and visual data. Previous works in taxonomy induction generally ignore the increasingly prominent visual data, which encode important perceptual semantics.…

Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the…

Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a…

This study investigates a hybrid method for text classification that integrates deep feature extraction from large language models, multi-scale fusion through feature pyramids, and structured modeling with graph neural networks to enhance…

Named entity recognition (NER), which focuses on the extraction of semantically meaningful named entities and their semantic classes from text, serves as an indispensable component for several down-stream natural language processing (NLP)…

Edge detection is a very essential part of image processing, as quality and accuracy of detection determines the success of further processing. We have developed a new self learning technique for edge detection using dictionary comprised of…

Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of…

Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…

We design a new technique for the distributional semantic modeling with a neural network-based approach to learn distributed term representations (or term embeddings) - term vector space models as a result, inspired by the recent…

With the fast development of Deep Learning techniques, Named Entity Recognition (NER) is becoming more and more important in the information extraction task. The greatest difficulty that the NER task faces is to keep the detectability even…

In this paper we introduce Latent Tree Language Model (LTLM), a novel approach to language modeling that encodes syntax and semantics of a given sentence as a tree of word roles. The learning phase iteratively updates the trees by moving…

Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of…