Related papers: Context Aware Document Embedding
We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or…
The introduction of Transformer neural networks has changed the landscape of Natural Language Processing (NLP) during the last years. So far, none of the visualization systems has yet managed to examine all the facets of the Transformers.…
We address two challenges in topic models: (1) Context information around words helps in determining their actual meaning, e.g., "networks" used in the contexts "artificial neural networks" vs. "biological neuron networks". Generative topic…
Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…
To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…
Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on handcrafted transforms and heuristics, reflecting the limited understanding of weights as a data…
This paper aims at improving how machines can answer questions directly from text, with the focus of having models that can answer correctly multiple types of questions and from various types of texts, documents or even from large…
This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a…
Word2vec is one of the most used algorithms to generate word embeddings because of a good mix of efficiency, quality of the generated representations and cognitive grounding. However, word meaning is not static and depends on the context in…
This paper strives to find the sentence best describing the content of an image or video. Different from existing works, which rely on a joint subspace for image / video to sentence matching, we propose to do so in a visual space only. We…
In recent years, several studies on neural machine translation (NMT) have attempted to use document-level context by using a multi-encoder and two attention mechanisms to read the current and previous sentences to incorporate the context of…
Latent semantic representations of words or paragraphs, namely the embeddings, have been widely applied to information retrieval (IR). One of the common approaches of utilizing embeddings for IR is to estimate the document-to-query (D2Q)…
While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…
Wavelets have emerged as a cutting edge technology in a number of fields. Concrete results of their application in Image and Signal processing suggest that wavelets can be effectively applied to Natural Language Processing (NLP) tasks that…
Word Sense Induction (WSI) is the ability to automatically induce word senses from corpora. The WSI task was first proposed to overcome the limitations of manually annotated corpus that are required in word sense disambiguation systems.…
Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…
Modern industrial recommender systems use a deep ranking model to score N candidates against the same user and context features. Standard implementations broadcast context features early in the forward pass, redundantly computing…
We describe a modern deep learning system that automatically identifies informative contextual examples (\qu{contexts}) for first language vocabulary instruction for high school student. Our paper compares three modeling approaches: (i) an…
News will be biased so long as people have opinions. As social media becomes the primary entry point for news and partisan differences increase, it is increasingly important for informed citizens to be able to recognize bias. If people are…