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
Legality Discrimination of Japanese Web Advertisements by Complex-valued SVM using Document Features based on Discrete Fourier Transform
TL;DR: In this article , a system that can effectively and quickly detect problematic advertisements is proposed. But, the system is not suitable for large scale advertisements and it cannot be used to classify advertisements based on word statistics alone.
Posted Content
Combining word embeddings and convolutional neural networks to detect duplicated questions.
TL;DR: This work proposes a simple approach to identifying semantically similar questions by combining the strengths of word embeddings and Convolutional Neural Networks (CNNs), and demonstrates how the cosine similarity metric can be used to effectively compare feature vectors.
Proceedings ArticleDOI
Research on Identification of Network Public Opinion Information based on Graph Convolutional Networks
TL;DR: In this paper, a public opinion information identification method based on Word2Vec and graph convolutional networks was proposed, which achieved the average identification accuracy of 85.58%.
Proceedings ArticleDOI
Intention Recognition Based on Multi-layer Attention and Label Embedding
TL;DR: Zhang et al. as mentioned in this paper proposed a Label Embedding Hierarchical Attention Networks (LE _HAN) algorithm with reference to the multi-layer attention model and the introduction of prior knowledge in semantic extraction.
Proceedings ArticleDOI
A Model for Quality Control of Customer Service
TL;DR: A problem detection model for quality control of customer service is proposed and experimental results on a dataset from a real-world industrial customer service Alime Assist show the model’s effect.
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.