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

Learning numeral embeddings

Word embedding is an essential building block for deep learning methods for natural language processing. Expand abstract.
31 days ago
4/10 relevant
arXiv

Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection

Extensive experimental results on a series of natural language processing and computer vision tasks, including neural machine translation, image captioning, and language modeling, all demonstrate the advantages of Explicit Sparse Transformer in model performance. Expand abstract.
33 days ago
6/10 relevant
arXiv

A Multimodal Target-Source Classifier with Attention Branches to Understand Ambiguous Instructions for Fetching Daily Objects

This task consists of predicting a target object, as instructed by the user, given an image and an unstructured sentence, such as "Bring me the yellow box (from the wooden cabinet)." This is challenging because of the ambiguity of natural language, i.e., the relevant information may be missing or there might be several... Expand abstract.
35 days ago
4/10 relevant
arXiv

Probabilistic Simulation of Quantum Circuits with the Transformer

Using this framework, we have developed a practical algorithm to simulate quantum circuits with the Transformer, a powerful ansatz responsible for the most recent breakthroughs in natural language processing. Expand abstract.
35 days ago
4/10 relevant
arXiv

Hybrid Machine Learning Models of Classifying Residential Requests for Smart Dispatching

Residential requests in natural language descriptions cover almost every aspect of a city's daily operation. Expand abstract.
36 days ago
4/10 relevant
arXiv

Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval

Finding relevant context in a conversation's history is challenging because of the complexity of natural language and the evolution of a user's information need. Expand abstract.
36 days ago
4/10 relevant
arXiv

Analysis of Spatial Interaction between Different Food Cultures in South and North of China — Practices from People's Daily Life

Using machine learning methods such as the popular natural language processing (NLP), this paper can not only extract hotspot cultural elements from text data but also accurately detect the spatial interaction pattern of some specific cultures and the characteristics of emotions towards non-native cultures. Expand abstract.
37 days ago
4/10 relevant
Preprints.org

PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition

Recently in computer vision and natural language processing, systems pretrained on large datasets have generalized well to several tasks. Expand abstract.
37 days ago
4/10 relevant
arXiv

AdvCodec: Towards A Unified Framework for Adversarial Text Generation

While there has been great interest in generating imperceptible adversarial examples in continuous data domain (e.g. image and audio) to explore the model vulnerabilities, generating \emph{adversarial text} in the discrete domain is still challenging. Expand abstract.
37 days ago
4/10 relevant
arXiv

Measuring Compositional Generalization: A Comprehensive Method on Realistic Data

We present a large and realistic natural language question answering dataset that is constructed according to this method, and we use it to analyze the compositional generalization ability of three machine learning architectures. Expand abstract.
38 days ago
4/10 relevant
arXiv