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
Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases
TL;DR: The authors proposed a method for training effective language-specific sentence encoders without manually labeled data by automatically constructing a dataset of paraphrase pairs from sentence-aligned bilingual text corpora and then using the collected data to fine-tune a Transformer language model with an additional recurrent pooling layer.
Proceedings ArticleDOI
Scalable Few-Shot Learning of Robust Biomedical Name Representations.
TL;DR: In this paper, a few-shot learning approach is proposed to explore the impact of conceptual distinctions on robust biomedical name representations, which is effective for various types of input representations, both domain-specific or unsupervised.
Proceedings ArticleDOI
Efficient Sentence Embedding via Semantic Subspace Analysis
TL;DR: In this paper, a novel sentence embedding method built upon semantic subspace analysis is proposed, called Semantic Subspace Sentence Embedding (S3E), which constructs a sentence model from two aspects.
Posted Content
Re-evaluating Word Mover's Distance.
TL;DR: In this article, the authors re-evaluate the performance of WMD and the classical baselines and find that WMD in high-dimensional spaces behaves more similarly to BOW than in low-dimensional space due to the curse of dimensionality.
Journal ArticleDOI
Social world knowledge: Modeling and applications
Nir Lotan,Einat Minkov +1 more
TL;DR: SocialVec as discussed by the authors is a general framework for eliciting low-dimensional entity embeddings from the social contexts in which they occur in social networks, where entities correspond to highly popular accounts which invoke general interest.
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.