Large-Scale Multi-label Text Classification — Revisiting Neural Networks

Nam, Jinseok; Kim, Jun-Gi; Mencía, Eneldo Loza; Gurevych, Iryna; Fürnkranz, Johannes

doi:10.1007/978-3-662-44851-9_28

Cited by 294 publications

(248 citation statements)

References 23 publications

Supporting

Mentioning

224

Contrasting

Order By: Relevance

“…The best performing network is the 2L-CNN with randomly initialized embeddings. The resulting F-measure is comparable to the value of 87.89% presented in (Nam et al, 2014).…”

Section: Results On the English Reuters Datasetsupporting

confidence: 78%

Word Embeddings for Multi-label Document Classification

Lenc

Král

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

In this paper, we analyze and evaluate word embeddings for representation of longer texts in the multi-label document classification scenario. The embeddings are used in three convolutional neural network topologies. The experiments are realized on the CzechČTK and English Reuters-21578 standard corpora. We compare the results of word2vec static and trainable embeddings with randomly initialized word vectors. We conclude that initialization does not play an important role for classification. However, learning of word vectors is crucial to obtain good results.

show abstract

“…The best performing network is the 2L-CNN with randomly initialized embeddings. The resulting F-measure is comparable to the value of 87.89% presented in (Nam et al, 2014).…”

Section: Results On the English Reuters Datasetsupporting

confidence: 78%

Word Embeddings for Multi-label Document Classification

Lenc

Král

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

show abstract

“…That is why we focused directly on deep-learning methods, as they are capable of learning and predicting a full label distribution (Nam et al, 2014).…”

Section: Predicting Full Multi-label Distributionmentioning

confidence: 99%

What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation

Habernal¹,

Gurevych²

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

This article tackles a new challenging task in computational argumentation. Given a pair of two arguments to a certain controversial topic, we aim to directly assess qualitative properties of the arguments in order to explain why one argument is more convincing than the other one. We approach this task in a fully empirical manner by annotating 26k explanations written in natural language. These explanations describe convincingness of arguments in the given argument pair, such as their strengths or flaws. We create a new crowd-sourced corpus containing 9,111 argument pairs, multilabeled with 17 classes, which was cleaned and curated by employing several strict quality measures. We propose two tasks on this data set, namely (1) predicting the full label distribution and (2) classifying types of flaws in less convincing arguments. Our experiments with feature-rich SVM learners and Bidirectional LSTM neural networks with convolution and attention mechanism reveal that such a novel fine-grained analysis of Web argument convincingness is a very challenging task. We release the new corpus UKPConvArg2 and the accompanying software under permissive licenses to the research community.

show abstract

“…There are also several relevant works that propose the inclusion of multi-label co-occurrence into loss functions such as pairwise ranking loss (Zhang and Zhou, 2006) and more recent work by Nam et al (2014), who report that binary crossentropy can outperform the pairwise ranking loss by leveraging rectified linear units (ReLUs) for nonlinearity.…”

Section: Related Workmentioning

confidence: 99%

Initializing neural networks for hierarchical multi-label text classification

Baker¹,

Korhonen²

2017

BioNLP 2017

View full text Add to dashboard Cite

Many tasks in the biomedical domain require the assignment of one or more predefined labels to input text, where the labels are a part of a hierarchical structure (such as a taxonomy). The conventional approach is to use a one-vs.-rest (OVR) classification setup, where a binary classifier is trained for each label in the taxonomy or ontology where all instances not belonging to the class are considered negative examples. The main drawbacks to this approach are that dependencies between classes are not leveraged in the training and classification process, and the additional computational cost of training parallel classifiers. In this paper, we apply a new method for hierarchical multi-label text classification that initializes a neural network model final hidden layer such that it leverages label co-occurrence relations such as hypernymy. This approach elegantly lends itself to hierarchical classification. We evaluated this approach using two hierarchical multi-label text classification tasks in the biomedical domain using both sentence-and document-level classification. Our evaluation shows promising results for this approach.

show abstract

Large-Scale Multi-label Text Classification — Revisiting Neural Networks

Cited by 294 publications

References 23 publications

Word Embeddings for Multi-label Document Classification

Word Embeddings for Multi-label Document Classification

What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation

Initializing neural networks for hierarchical multi-label text classification

Contact Info

Product

Resources

About