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
An Embedding Model for Estimating Legislative Preferences from the Frequency and Sentiment of Tweets.
TL;DR: This paper presents an embedding-based model for predicting the frequency and sentiment of legislator tweets, and model legislators’ attitudes towards President Donald Trump as vector embeddings that interact withembeddings for Trump himself constructed using a neural network from the text of his daily tweets.
Posted Content
Political Text Scaling Meets Computational Semantics
TL;DR: An extensive quantitative analysis over a collection of speeches from the European Parliament in five different languages and from two different legislative terms is conducted, and it is shown that a scaling approach relying on semantic document representations is often better at capturing known underlying political dimensions than the established frequency-based scaling method.
Posted Content
DeepCVA: Automated Commit-level Vulnerability Assessment with Deep Multi-task Learning
TL;DR: DeepCVA as mentioned in this paper proposes a deep multi-task learning model to automate seven commit-level vulnerability assessment tasks simultaneously based on Common Vulnerability Scoring System (CVSS) metrics.
Posted Content
Adaptive Region Embedding for Text Classification.
TL;DR: The experimental results prove that the Adaptive Region Embedding to learn context representation to improve text classification achieves state-of-the-art performances and effectively avoids word ambiguity.
Journal ArticleDOI
An automated approach to identify scientific publications reporting pharmacokinetic parameters.
Ferran Gonzalez Hernandez,Ferran Gonzalez Hernandez,Simon J Carter,Simon J Carter,Juha Iso-Sipilä,Paul Goldsmith,Ahmed A Almousa,Silke Gastine,Watjana Lilaonitkul,Frank Kloprogge,Joseph F. Standing +10 more
TL;DR: This work proposes a machine learning approach to automatically identify and characterise scientific publications reporting PK parameters from in vivo data, providing a centralised repository of PK literature.
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.