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
Predicting Guesses and Slips Through Question Encoding with Complexity Hints
TL;DR: In this paper , the potential usefulness of complexity hints in predicting mastery of algebra problems is explored, where natural language processing methods were used to derive a complexity estimate of each assessment problem and applied to estimate guess and slip probabilities using individualized neural network models.
Proceedings ArticleDOI
Word Order is Considerable: Contextual Position-aware Graph Neural Network for Text Classification
TL;DR: Wang et al. as mentioned in this paper proposed a Contextual Position-Aware Graph Neural Network (CGAN) for text classification, which includes the Position-aware Graph Attention module and the Contextual Fusion module.
Journal ArticleDOI
Text classification on heterogeneous information network via enhanced GCN and knowledge
Proceedings ArticleDOI
An Emotional Comfort Framework for Improving User Satisfaction in E-Commerce Customer Service Chatbots.
TL;DR: Wang et al. as discussed by the authors presented AliMe Assist, a Chinese intelligent assistant designed for creating an innovative online shopping experience in E-commerce, which offers assistance service, customer service, and chatting service.
Book ChapterDOI
A New Method to Measure Similarity of Words in Japanese Twitter Based on Related Images
TL;DR: In this article , a method to use word-related images to measure the similarity between words was proposed, assuming that words with the same meaning have similar or common related images, and a manually annotated Japanese data set was created to evaluate the proposed method.
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.