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
Proceedings ArticleDOI
Better Word Representations with Word Weight
TL;DR: This paper proposes an effective text classification scheme by incorporating word weight into word embedding, and extensive experimental results verify that the accuracy of the proposedText classification scheme outperforms the state-of-the-art ones.
Posted Content
Forget me not: A Gentle Reminder to Mind the Simple Multi-Layer Perceptron Baseline for Text Classification.
Lukas Galke,Ansgar Scherp +1 more
TL;DR: This paper showed that a simple MLP baseline achieves comparable performance on benchmark datasets, questioning the importance of synthetic graph structures, and suggested that future studies use at least anMLP baseline to contextualize the results.
Journal ArticleDOI
Sentence Embeddings using Definition Sentences
TL;DR: In this article , a Natural Language Inference (NLI) natural language detection system was proposed. But it is not a natural language processing system for English-to-Chinese translation.
Book ChapterDOI
Replacing Human Input in Spam Email Detection Using Deep Learning
TL;DR: A deep learning model, based on simple word embedding and global max pooling (SWEM-max) had higher accuracy than both Thunderbird and Mailwasher which are based on Bayesian spam filtering, and was compared with the accuracy of freeware spam detection tools.
Journal ArticleDOI
Applications of Natural Language Processing to Geoscience Text Data and Prospectivity Modeling
Christopher J.M. Lawley,M G Gadd,Mohammad Hossein Taghavi Parsa,Graham W. Lederer,Garth E. Graham,Arianne Ford +5 more
TL;DR: In this paper , the authors apply natural language processing (NLP) to geoscientific text data from Canada, the U.S., and Australia to address that knowledge gap.
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.