Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Dinghan Shen,Guoyin Wang,Wenlin Wang,Martin Renqiang Min,Qinliang Su,Yizhe Zhang,Chunyuan Li,Ricardo Henao,Lawrence Carin +8 more
- Vol. 1, pp 440-450
TLDR
This paper conducted a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models.Abstract:
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper, we conduct a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models. Surprisingly, SWEMs exhibit comparable or even superior performance in the majority of cases considered. Based upon this understanding, we propose two additional pooling strategies over learned word embeddings: (i) a max-pooling operation for improved interpretability; and (ii) a hierarchical pooling operation, which preserves spatial (n-gram) information within text sequences. We present experiments on 17 datasets encompassing three tasks: (i) (long) document classification; (ii) text sequence matching; and (iii) short text tasks, including classification and tagging.read more
Citations
More filters
Journal ArticleDOI
A deep neural network model for fashion collocation recommendation using side information in e-commerce
Siyu Wang,Jiangtao Qiu +1 more
TL;DR: Wang et al. as mentioned in this paper developed a fashion collocation recommendation model that leverages accessible side information in e-commerce, such as textual descriptions, purchase data and category information of items, generally bear valuable information regarding this task.
Proceedings ArticleDOI
Neural Self-Training through Spaced Repetition
TL;DR: This work introduces a new data sampling technique based on spaced repetition that dynamically samples informative and diverse unlabeled instances with respect to individual learner and instance characteristics that outperforms current semi-supervised learning approaches developed for neural networks on publicly-available datasets.
Book ChapterDOI
A Weighted Word Embedding Model for Text Classification
TL;DR: A model called weighted word embedding model (WWEM) is proposed, a variant of NBOW model introducing term weighting schemes and n-grams that generates informative sentence or document representation considering the important degree of words and the word-order information.
Posted Content
Recursive Graphical Neural Networks for Text Classification.
TL;DR: A novel Recursive Graphical Neural Networks model (ReGNN) is proposed to represent text organized in the form of graph to alleviating the over-smoothing problem and to encourage the exchange between the local and global information, a global graph-level node is designed.
Journal ArticleDOI
Time-sync comments denoising via graph convolutional and contextual encoding
TL;DR: This study proposes GCCED, a graph convolutional and contextual encoding denoising model for TSC semantic Denoising problem, which demonstrates the proposed model outperforming other baselines in almost all classification metrics.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.