scholarly journals Agreement on Target-Bidirectional Recurrent Neural Networks for Sequence-to-Sequence Learning

2020 ◽  
Vol 67 ◽  
pp. 581-606 ◽  
Author(s):  
Lemao Liu ◽  
Andrew Finch ◽  
Masao Utiyama ◽  
Eiichiro Sumita
Keyword(s):  
Neural Networks ◽  
Machine Translation ◽  
Sequence Learning ◽  
Recurrent Neural Networks ◽  
State Of The Art ◽  
Great Success ◽  
Search Methods ◽  
Approximate Search ◽  
Standard Sequence ◽  
Learning Tasks

Recurrent neural networks are extremely appealing for sequence-to-sequence learning tasks. Despite their great success, they typically suffer from a shortcoming: they are prone to generate unbalanced targets with good prefixes but bad suffixes, and thus performance suffers when dealing with long sequences. We propose a simple yet effective approach to overcome this shortcoming. Our approach relies on the agreement between a pair of target-directional RNNs, which generates more balanced targets. In addition, we develop two efficient approximate search methods for agreement that are empirically shown to be almost optimal in terms of either sequence level or non-sequence level metrics. Extensive experiments were performed on three standard sequence-to-sequence transduction tasks: machine transliteration, grapheme-to-phoneme transformation and machine translation. The results show that the proposed approach achieves consistent and substantial improvements, compared to many state-of-the-art systems.

scholarly journals Sentence embeddings in NLI with iterative refinement encoders

2019 ◽  
Vol 25 (4) ◽  
pp. 467-482 ◽  
Author(s):  
Aarne Talman ◽  
Anssi Yli-Jyrä ◽  
Jörg Tiedemann
Keyword(s):  
Neural Networks ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Recurrent Neural Networks ◽  
State Of The Art ◽  
Iterative Refinement ◽  
Learning Tasks ◽  
Sentence Level ◽  
Refinement Strategy

AbstractSentence-level representations are necessary for various natural language processing tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We build on top of one such model and propose a hierarchy of bidirectional LSTM and max pooling layers that implements an iterative refinement strategy and yields state of the art results on the SciTail dataset as well as strong results for Stanford Natural Language Inference and Multi-Genre Natural Language Inference. We can show that the sentence embeddings learned in this way can be utilized in a wide variety of transfer learning tasks, outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval sentence embedding evaluation tasks. Furthermore, our model beats the InferSent model in 8 out of 10 recently published SentEval probing tasks designed to evaluate sentence embeddings’ ability to capture some of the important linguistic properties of sentences.

scholarly journals Unsupervised Representation Learning by Predicting Random Distances

2020 ◽  
Author(s):  
Hu Wang ◽  
Guansong Pang ◽  
Chunhua Shen ◽  
Congbo Ma
Keyword(s):  
Neural Networks ◽  
Anomaly Detection ◽  
Unsupervised Learning ◽  
Large Scale ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Representation Learning ◽  
Great Success ◽  
Learning Tasks ◽  
Real World Datasets

Deep neural networks have gained great success in a broad range of tasks due to its remarkable capability to learn semantically rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption in unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications to critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space. Random mapping is a theoretically proven approach to obtain approximately preserved distances. To well predict these distances, the representation learner is optimised to learn genuine class structures that are implicitly embedded in the randomly projected space. Empirical results on 19 real-world datasets show that our learned representations substantially outperform a few state-of-the-art methods for both anomaly detection and clustering tasks. Code is available at: \url{https://git.io/RDP}

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Tackling Contradiction Detection in German Using Machine Translation and End-to-End Recurrent Neural Networks

2021 ◽  
Author(s):  
Maren Pielka ◽  
Rafet Sifa ◽  
Lars Patrick Hillebrand ◽  
David Biesner ◽  
Rajkumar Ramamurthy ◽  
...  
Keyword(s):  
Neural Networks ◽  
Machine Translation ◽  
Recurrent Neural Networks ◽  
End To End

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

scholarly journals Empirical Investigation of Optimization Algorithms in Neural Machine Translation

2017 ◽  
Vol 108 (1) ◽  
pp. 13-25 ◽  
Author(s):  
Parnia Bahar ◽  
Tamer Alkhouli ◽  
Jan-Thorsten Peter ◽  
Christopher Jan-Steffen Brix ◽  
Hermann Ney
Keyword(s):  
Neural Networks ◽  
Machine Translation ◽  
Optimization Problem ◽  
Empirical Investigation ◽  
State Of The Art ◽  
Optimization Techniques ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
And Training ◽  
Dimensional Optimization

AbstractTraining neural networks is a non-convex and a high-dimensional optimization problem. In this paper, we provide a comparative study of the most popular stochastic optimization techniques used to train neural networks. We evaluate the methods in terms of convergence speed, translation quality, and training stability. In addition, we investigate combinations that seek to improve optimization in terms of these aspects. We train state-of-the-art attention-based models and apply them to perform neural machine translation. We demonstrate our results on two tasks: WMT 2016 En→Ro and WMT 2015 De→En.

scholarly journals Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

2021 ◽  
Author(s):  
Bojian Yin ◽  
Federico Corradi ◽  
Sander M. Bohté
Keyword(s):  
Neural Networks ◽  
Time Domain ◽  
Recurrent Neural Networks ◽  
State Of The Art ◽  
Spiking Neurons ◽  
Recurrent Networks ◽  
Computationally Efficient ◽  
Hardware Implementations ◽  
Comparable Performance ◽  
The Time Domain

ABSTRACTInspired by more detailed modeling of biological neurons, Spiking neural networks (SNNs) have been investigated both as more biologically plausible and potentially more powerful models of neural computation, and also with the aim of extracting biological neurons’ energy efficiency; the performance of such networks however has remained lacking compared to classical artificial neural networks (ANNs). Here, we demonstrate how a novel surrogate gradient combined with recurrent networks of tunable and adaptive spiking neurons yields state-of-the-art for SNNs on challenging benchmarks in the time-domain, like speech and gesture recognition. This also exceeds the performance of standard classical recurrent neural networks (RNNs) and approaches that of the best modern ANNs. As these SNNs exhibit sparse spiking, we show that they theoretically are one to three orders of magnitude more computationally efficient compared to RNNs with comparable performance. Together, this positions SNNs as an attractive solution for AI hardware implementations.

scholarly journals Neural Machine Translation between Vietnamese and English: an Empirical Study

2019 ◽  
Vol 35 (2) ◽  
pp. 147-166 ◽  
Author(s):  
Hong-Hai Phan-Vu ◽  
Viet Trung Tran ◽  
Van Nam Nguyen ◽  
Hoang Vu Dang ◽  
Phan Thuan Do
Keyword(s):  
Neural Networks ◽  
Empirical Study ◽  
Machine Translation ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Neural Models ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Parameter Search ◽  
Popular Language

Machine translation is shifting to an end-to-end approach based on deep neural networks. The state of the art achieves impressive results for popular language pairs such as English - French or English - Chinese. However for English - Vietnamese the shortage of parallel corpora and expensive hyper-parameter search present practical challenges to neural-based approaches. This paper highlights our efforts on improving English-Vietnamese translations in two directions: (1) Building the largest open Vietnamese - English corpus to date, and (2) Extensive experiments with the latest neural models to achieve the highest BLEU scores. Our experiments provide practical examples of effectively employing different neural machine translation models with low-resource language pairs.

scholarly journals An empirical study on temporal modeling for online action detection

2021 ◽  
Author(s):  
Wen Wang ◽  
Xiaojiang Peng ◽  
Yu Qiao ◽  
Jian Cheng
Keyword(s):  
Neural Networks ◽  
Empirical Study ◽  
Recurrent Neural Networks ◽  
State Of The Art ◽  
Deep Convolutional Neural Networks ◽  
Temporal Modeling ◽  
Action Detection ◽  
Modeling Methods ◽  
Feature Extractor ◽  
First Time

AbstractOnline action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. A typical OAD system mainly consists of three modules: a frame-level feature extractor which is usually based on pre-trained deep Convolutional Neural Networks (CNNs), a temporal modeling module, and an action classifier. Among them, the temporal modeling module is crucial which aggregates discriminative information from historical and current features. Though many temporal modeling methods have been developed for OAD and other topics, their effects are lack of investigation on OAD fairly. This paper aims to provide an empirical study on temporal modeling for OAD including four meta types of temporal modeling methods, i.e. temporal pooling, temporal convolution, recurrent neural networks, and temporal attention, and uncover some good practices to produce a state-of-the-art OAD system. Many of them are explored in OAD for the first time, and extensively evaluated with various hyper parameters. Furthermore, based on our empirical study, we present several hybrid temporal modeling methods. Our best networks, i.e. , the hybridization of DCC, LSTM and M-NL, and the hybridization of DCC and M-NL, which outperform previously published results with sizable margins on THUMOS-14 dataset (48.6% vs. 47.2%) and TVSeries dataset (84.3% vs. 83.7%).

Sign in / Sign up

Export Citation Format

Share Document