Papers Document Classification

Hierarchical Convolutional Attention Networks for Text Classification

Recent work in machine translation has demonstrated that self-attention mechanisms can be used in place of recurrent neural networks to increase training speed without sacrificing model accuracy. We propose combining thi…

Comparison of Representations of Named Entities for Document Classification

We explore representations for multi-word names in text classification tasks, on Reuters (RCV1) topic and sector classification. We find that: the best way to treat names is to split them into tokens and use each token a…

Multilingual Seq2seq Training with Similarity Loss for Cross-Lingual Document Classification

In this paper we continue experiments where neural machine translation training is used to produce joint cross-lingual fixed-dimensional sentence embeddings. In this framework we introduce a simple method of adding a los…

Learning Longer-term Dependencies in RNNs with Auxiliary Losses

Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is …

Inter and Intra Topic Structure Learning with Word Embeddings

One important task of topic modeling for text analysis is interpretability. By discovering structured topics one is able to yield improved interpretability as well as modeling accuracy. In this paper, we propose a n…

Variational learning across domains with triplet information

The work investigates deep generative models, which allow us to use training data from one domain to build a model for another domain. We propose the Variational Bi-domain Triplet Autoencoder (VBTA) that learns a joint d…

Paragraph-based complex networks: application to document classification and authenticity verification

With the increasing number of texts made available on the Internet, many applications have relied on text mining tools to tackle a diversity of problems. A relevant model to represent texts is the so-called word adjacenc…

Using J-K fold Cross Validation to Reduce Variance When Tuning NLP Models

K-fold cross validation (CV) is a popular method for estimating the true performance of machine learning models, allowing model selection and parameter tuning. However, the very process of CV requires random partitioning…

Improving Language Understanding by Generative Pre-Training

Natural language understanding comprises a wide range of diverse tasks such as textual entailment, question answering, semantic similarity assessment, and document classification. Although large unlabeled text corpora …

A Comparison of Two Paraphrase Models for Taxonomy Augmentation

Taxonomies are often used to look up the concepts they contain in text documents (for instance, to classify a document). The more comprehensive the taxonomy, the higher recall the application has that uses the taxonomy. …

SystemT: Declarative Text Understanding for Enterprise

The rise of enterprise applications over unstructured and semi-structured documents poses new challenges to text understanding systems across multiple dimensions. We present SystemT, a declarative text understanding syst…

T\"ubingen-Oslo at SemEval-2018 Task 2: SVMs perform better than RNNs in Emoji Prediction

This paper describes our participation in the SemEval-2018 task Multilingual Emoji Prediction. We participated in both English and Spanish subtasks, experimenting with support vector machines (SVMs) and recurrent neural …

Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization

We tackle the issue of classifier combinations when observations have multiple views. Our method jointly learns view-specific weighted majority vote classifiers (i.e. for each view) over a set of base voters, and a secon…

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations. However, there has not been a rigorous evaluat…

A Corpus for Multilingual Document Classification in Eight Languages

Cross-lingual document classification aims at training a document classifier on resources in one language and transferring it to a different language without any additional resources. Several approaches have been propose…

A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors

Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textual features. This paper introduces a la c…

RMDL: Random Multimodel Deep Learning for Classification

The continually increasing number of complex datasets each year necessitates ever improving machine learning methods for robust and accurate categorization of these data. This paper introduces Random Multimodel Deep Lear…

Multilingual Multi-class Sentiment Classification Using Convolutional Neural Networks

On the Vector Representation of Utterances in Dialogue Context

A Leveled Reading Corpus of Modern Standard Arabic