Found 900 results, showing the newest relevant preprints. Sort by relevancy only.Update me on new preprints

Using Dynamic Embeddings to Improve Static Embeddings

How to build high-quality word embeddings is a fundamental research question in the field of natural language processing. Expand abstract.
81 days ago
4/10 relevant
arXiv

Neural Graph Embedding Methods for Natural Language Processing

However, graphs in Natural Language Processing (NLP) are prominent. Expand abstract.
81 days ago
9/10 relevant
arXiv

Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase interactions. Expand abstract.
81 days ago
4/10 relevant
arXiv

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces

This is a problem that appears across areas, from natural language processing to bioinformatics, and is typically solved by appeal to outside knowledge bases and label-textual similarity. Expand abstract.
82 days ago
4/10 relevant
arXiv

Shaping Visual Representations with Language for Few-shot Classification

We explore this question in the setting of few-shot visual classification, proposing models which learn to perform visual classification while jointly predicting natural language task descriptions at train time. Expand abstract.
82 days ago
5/10 relevant
arXiv

Learning to Annotate: Modularizing Data Augmentation for Text Classifiers with Natural Language Explanations

Natural language (NL) explanations have been demonstrated very useful additional supervision, which can provide sufficient domain knowledge for generating more labeled data over new instances, while the annotation time only doubles. Expand abstract.
84 days ago
10/10 relevant
arXiv

VASTA: A Vision and Language-assisted Smartphone Task Automation System

To address the second and third challenges, VASTA takes advantage of advanced natural language understanding algorithms for analyzing the user utterance to trigger the VASTA automation scripts, and to determine the automation parameters for generalization. Expand abstract.
84 days ago
4/10 relevant
arXiv

Assessing Social and Intersectional Biases in Contextualized Word Representations

In natural language processing, gender bias has been shown to exist in context-free word embeddings. Expand abstract.
84 days ago
4/10 relevant
arXiv

Artificial Intelligence Strategies for National Security and Safety Standards

Recent advances in artificial intelligence (AI) have lead to an explosion of multimedia applications (e.g., computer vision (CV) and natural language processing (NLP)) for different domains such as commercial, industrial, and intelligence. Expand abstract.
85 days ago
4/10 relevant
arXiv

Chat-Bot-Kit: A web-based tool to simulate text-based interactions between humans and with computers

The tool is also designed to be used in wizard-of-oz studies in Human-Computer Interaction (HCI) and for the evaluation of chatbots (dialogue systems) in Natural Language Processing (NLP). Expand abstract.
86 days ago
4/10 relevant
arXiv