conftrace_

2017 EACL EACL 2017

Nonsymbolic Text Representation

Abstract

AbstractWe introduce the first generic text representation model that is completely nonsymbolic, i.e., it does not require the availability of a segmentation or tokenization method that attempts to identify words or other symbolic units in text. This applies to training the parameters of the model on a training corpus as well as to applying it when computing the representation of a new text. We show that our model performs better than prior work on an information extraction and a text denoising task.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

📈 Trend Setter - Large Language Models

Authors

Hinrich Schütze

Topics

Machine Learning > Core Methods > Representation Learning Deep Learning > Models > Generative Models Natural Language Processing > Resources & Methods > Text Representation Deep Learning > Models > Large Language Models Deep Learning > Learning Types > Self-Supervised Learning

Keywords

information extraction text representation deep learning word embedding nonsymbolic representation text denoising neural network

More from EACL 2017

All EACL 2017 papers →

A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts

A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments

Online Learning of Task-specific Word Representations with a Joint Biconvex Passive-Aggressive Algorithm

Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings

Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings

End-to-end Relation Extraction using Neural Networks and Markov Logic Networks