scholarly journals Reinforcing Coherence for Sequence to Sequence Model in Dialogue Generation

2018 ◽  
Author(s):  
Hainan Zhang ◽  
Yanyan Lan ◽  
Jiafeng Guo ◽  
Jun Xu ◽  
Xueqi Cheng
Keyword(s):  
Similarity Function ◽  
Semantic Matching ◽  
Matching Function ◽  
True Probability ◽  
Reward Function ◽  
Learning Framework ◽  
Human Evaluation ◽  
Single Turn ◽  
Different Types ◽  
Coherence Degree

Sequence to sequence (Seq2Seq) approach has gained great attention in the field of single-turn dialogue generation. However, one serious problem is that most existing Seq2Seq based models tend to generate common responses lacking specific meanings. Our analysis show that the underlying reason is that Seq2Seq is equivalent to optimizing Kullback–Leibler (KL) divergence, thus does not penalize the case whose generated probability is high while the true probability is low. However, the true probability is unknown, which poses challenges for tackling this problem. Inspired by the fact that the coherence (i.e. similarity) between post and response is consistent with human evaluation, we hypothesize that the true probability of a response is proportional to the coherence degree. The coherence scores are then used as the reward function in a reinforcement learning framework to penalize the case whose generated probability is high while the true probability is low. Three different types of coherence models, including an unlearned similarity function, a pretrained semantic matching function, and an end-to-end dual learning architecture, are proposed in this paper. Experimental results on both Chinese Weibo dataset and English Subtitle dataset show that the proposed models produce more specific and meaningful responses, yielding better performances against Seq2Seq models in terms of both metric-based and human evaluations.

scholarly journals Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

Information ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 207
Author(s):  
Asma Baccouche ◽  
Begonya Garcia-Zapirain ◽  
Cristian Castillo Olea ◽  
Adel Elmaghraby
Keyword(s):  
Neural Network ◽  
Heart Disease ◽  
Ensemble Learning ◽  
Heart Diseases ◽  
Hypertensive Heart Disease ◽  
Network Models ◽  
Features Selection ◽  
Neural Network Models ◽  
Learning Framework ◽  
Different Types

Heart diseases are highly ranked among the leading causes of mortality in the world. They have various types including vascular, ischemic, and hypertensive heart disease. A large number of medical features are reported for patients in the Electronic Health Records (EHR) that allow physicians to diagnose and monitor heart disease. We collected a dataset from Medica Norte Hospital in Mexico that includes 800 records and 141 indicators such as age, weight, glucose, blood pressure rate, and clinical symptoms. Distribution of the collected records is very unbalanced on the different types of heart disease, where 17% of records have hypertensive heart disease, 16% of records have ischemic heart disease, 7% of records have mixed heart disease, and 8% of records have valvular heart disease. Herein, we propose an ensemble-learning framework of different neural network models, and a method of aggregating random under-sampling. To improve the performance of the classification algorithms, we implement a data preprocessing step with features selection. Experiments were conducted with unidirectional and bidirectional neural network models and results showed that an ensemble classifier with a BiLSTM or BiGRU model with a CNN model had the best classification performance with accuracy and F1-score between 91% and 96% for the different types of heart disease. These results are competitive and promising for heart disease dataset. We showed that ensemble-learning framework based on deep models could overcome the problem of classifying an unbalanced heart disease dataset. Our proposed framework can lead to highly accurate models that are adapted for clinical real data and diagnosis use.

scholarly journals What Makes A Good Story? Designing Composite Rewards for Visual Storytelling

2020 ◽  
Vol 34 (05) ◽  
pp. 7969-7976
Author(s):  
Junjie Hu ◽  
Yu Cheng ◽  
Zhe Gan ◽  
Jingjing Liu ◽  
Jianfeng Gao ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Quality Criteria ◽  
High Quality ◽  
Visual Storytelling ◽  
Learning Framework ◽  
Good Story ◽  
Human Evaluation ◽  
Reward Functions ◽  
New Criteria

Previous storytelling approaches mostly focused on optimizing traditional metrics such as BLEU, ROUGE and CIDEr. In this paper, we re-examine this problem from a different angle, by looking deep into what defines a natural and topically-coherent story. To this end, we propose three assessment criteria: relevance, coherence and expressiveness, which we observe through empirical analysis could constitute a “high-quality” story to the human eye. We further propose a reinforcement learning framework, ReCo-RL, with reward functions designed to capture the essence of these quality criteria. Experiments on the Visual Storytelling Dataset (VIST) with both automatic and human evaluation demonstrate that our ReCo-RL model achieves better performance than state-of-the-art baselines on both traditional metrics and the proposed new criteria.

scholarly journals Multi-view Feature Learning with Discriminative Regularization

2017 ◽  
Author(s):  
Jinglin Xu ◽  
Junwei Han ◽  
Feiping Nie
Keyword(s):  
Clustering Algorithms ◽  
Feature Learning ◽  
Feature Weighting ◽  
Learning Framework ◽  
Discriminative Feature ◽  
Heterogeneous Features ◽  
Real World Applications ◽  
Different Types ◽  
Rich Information ◽  
Low Dimensional

More and more multi-view data which can capture rich information from heterogeneous features are widely used in real world applications. How to integrate different types of features, and how to learn low dimensional and discriminative information from high dimensional data are two main challenges. To address these challenges, this paper proposes a novel multi-view feature learning framework, which is regularized by discriminative information and obtains a feature learning model that contains multiple discriminative feature weighting matrices for different views, and then yields multiple low dimensional features used for subsequent multi-view clustering. To optimize the formulated objective function, we transform the proposed framework into a trace optimization problem which obtains the global solution in a closed form. Experimental evaluations on four widely used datasets and comparisons with a number of state-of-the-art multi-view clustering algorithms demonstrate the superiority of the proposed work.

scholarly journals Development of swarm behavior in artificial learning agents that adapt to different foraging environments

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0243628
Author(s):  
Andrea López-Incera ◽  
Katja Ried ◽  
Thomas Müller ◽  
Hans J. Briegel
Keyword(s):  
Collective Behavior ◽  
Collective Motion ◽  
Learning Framework ◽  
Lévy Walks ◽  
Learning Agent ◽  
Swarm Behavior ◽  
Different Types ◽  
Artificial Learning ◽  
Learning Scenarios ◽  
The Individual

Collective behavior, and swarm formation in particular, has been studied from several perspectives within a large variety of fields, ranging from biology to physics. In this work, we apply Projective Simulation to model each individual as an artificial learning agent that interacts with its neighbors and surroundings in order to make decisions and learn from them. Within a reinforcement learning framework, we discuss one-dimensional learning scenarios where agents need to get to food resources to be rewarded. We observe how different types of collective motion emerge depending on the distance the agents need to travel to reach the resources. For instance, strongly aligned swarms emerge when the food source is placed far away from the region where agents are situated initially. In addition, we study the properties of the individual trajectories that occur within the different types of emergent collective dynamics. Agents trained to find distant resources exhibit individual trajectories that are in most cases best fit by composite correlated random walks with features that resemble Lévy walks. This composite motion emerges from the collective behavior developed under the specific foraging selection pressures. On the other hand, agents trained to reach nearby resources predominantly exhibit Brownian trajectories.

scholarly journals CURIOSITY-DRIVEN REINFORCEMENT LEARNING AGENT FOR MAPPING UNKNOWN INDOOR ENVIRONMENTS

2021 ◽  
Vol V-1-2021 ◽  
pp. 129-136
Author(s):  
N. Botteghi ◽  
R. Schulte ◽  
B. Sirmacek ◽  
M. Poel ◽  
C. Brune
Keyword(s):  
Artificial Intelligence ◽  
Reinforcement Learning ◽  
Mobile Robot ◽  
Indoor Environments ◽  
Reward Function ◽  
Learning Framework ◽  
Learning Agent ◽  
The World ◽  
Reward Functions ◽  
Slam Algorithm

Abstract. Autonomously exploring and mapping is one of the open challenges of robotics and artificial intelligence. Especially when the environments are unknown, choosing the optimal navigation directive is not straightforward. In this paper, we propose a reinforcement learning framework for navigating, exploring, and mapping unknown environments. The reinforcement learning agent is in charge of selecting the commands for steering the mobile robot, while a SLAM algorithm estimates the robot pose and maps the environments. The agent, to select optimal actions, is trained to be curious about the world. This concept translates into the introduction of a curiosity-driven reward function that encourages the agent to steer the mobile robot towards unknown and unseen areas of the world and the map. We test our approach in explorations challenges in different indoor environments. The agent trained with the proposed reward function outperforms the agents trained with reward functions commonly used in the literature for solving such tasks.

scholarly journals Attention-based multi-label neural networks for integrated prediction and interpretation of twelve widely occurring RNA modifications

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Zitao Song ◽  
Daiyun Huang ◽  
Bowen Song ◽  
Kunqi Chen ◽  
Yiyou Song ◽  
...  
Keyword(s):  
Neural Networks ◽  
Strong Association ◽  
Regulatory Mechanisms ◽  
Rna Modification ◽  
Integrated Analysis ◽  
Rna Modifications ◽  
Rna Sequences ◽  
Learning Framework ◽  
Transcriptome Regulation ◽  
Different Types

AbstractRecent studies suggest that epi-transcriptome regulation via post-transcriptional RNA modifications is vital for all RNA types. Precise identification of RNA modification sites is essential for understanding the functions and regulatory mechanisms of RNAs. Here, we present MultiRM, a method for the integrated prediction and interpretation of post-transcriptional RNA modifications from RNA sequences. Built upon an attention-based multi-label deep learning framework, MultiRM not only simultaneously predicts the putative sites of twelve widely occurring transcriptome modifications (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um), but also returns the key sequence contents that contribute most to the positive predictions. Importantly, our model revealed a strong association among different types of RNA modifications from the perspective of their associated sequence contexts. Our work provides a solution for detecting multiple RNA modifications, enabling an integrated analysis of these RNA modifications, and gaining a better understanding of sequence-based RNA modification mechanisms.

EXPRESS: Dynamics of Musical Success: A Machine Learning Approach for Multimedia Data Fusion

2021 ◽  
pp. 002224372110164
Author(s):  
Khaled Boughanmi ◽  
Asim Ansari
Keyword(s):  
Machine Learning ◽  
Dirichlet Process ◽  
Penalized Splines ◽  
Multimedia Data ◽  
Acoustic Features ◽  
Modeling Framework ◽  
Learning Framework ◽  
Proposed Model ◽  
Machine Learning Approach ◽  
Different Types

The success of creative products depends upon the felt experience of consumers. Capturing such consumer reactions requires the fusing of different types of experiential covariates and perceptual data in an integrated modeling framework. In this paper, the authors develop a novel multimodal machine learning framework that combines multimedia data (e.g., metadata, acoustic features and user generated textual data) in creative product settings and apply it for predicting the success of musical albums and playlists. The authors estimate the proposed model on a unique dataset which they collected using different online sources. The model integrates different types of nonparametrics to flexibly accommodate diverse types of effects. It uses penalized splines to capture the nonlinear impact of acoustic features and a supervised hierarchical Dirichlet process to represent crowd-sourced textual tags. It captures dynamics via a state-space specification. The authors show the predictive superiority of the model with respect to several benchmarks. The results illuminate the dynamics of musical success over the past five decades. The authors then use the components of the model for marketing decisions such as forecasting the success of new albums, album tuning and diagnostics, construction of playlists for different generations of music listeners, and contextual recommendations.

scholarly journals A Joint Learning Framework for the CCKS-2020 Financial Event Extraction Task

2021 ◽  
pp. 1-11
Author(s):  
Jiawei Sheng ◽  
Qian Li ◽  
Yiming Hei ◽  
Shu Guo ◽  
Bowen Yu ◽  
...  
Keyword(s):  
Probability Model ◽  
Joint Probability ◽  
Event Extraction ◽  
Joint Learning ◽  
Low Resource ◽  
Learning Framework ◽  
High Resource ◽  
Different Types ◽  
Joint Probability Model

Abstract This paper presents a winning solution for the CCKS-2020 financial event extraction task, where the goal is to identify event types, triggers and arguments in sentences across multiple event types. In this task, we focus on resolving two challenging problems (i.e., low resources and element overlapping) by proposing a joint learning framework, named SaltyFishes. We first formulate the event extraction task as a joint probability model. By sharing parameters in the model across different types, we can learn to adapt to low-resource events based on high-resource events. We further address the element overlapping problems by a mechanism of Conditional Layer Normalization, achieving even better extraction accuracy. The overall approach achieves an F1-score of 87.8% which ranks the first place in the task.

scholarly journals A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Control

2021 ◽  
Vol 4 (3) ◽  
pp. 1-22
Author(s):  
Pei Xu ◽  
Ioannis Karamouzas
Keyword(s):  
Fine Tuning ◽  
Imitation Learning ◽  
Generative Adversarial Networks ◽  
External Control ◽  
Motion Generation ◽  
Interactive Control ◽  
Reward Function ◽  
Learning Framework ◽  
Reference Motion ◽  
Matching Mechanism

We present a simple and intuitive approach for interactive control of physically simulated characters. Our work builds upon generative adversarial networks (GAN) and reinforcement learning, and introduces an imitation learning framework where an ensemble of classifiers and an imitation policy are trained in tandem given pre-processed reference clips. The classifiers are trained to discriminate the reference motion from the motion generated by the imitation policy, while the policy is rewarded for fooling the discriminators. Using our GAN-like approach, multiple motor control policies can be trained separately to imitate different behaviors. In runtime, our system can respond to external control signal provided by the user and interactively switch between different policies. Compared to existing method, our proposed approach has the following attractive properties: 1) achieves state-of-the-art imitation performance without manually designing and fine tuning a reward function; 2) directly controls the character without having to track any target reference pose explicitly or implicitly through a phase state; and 3) supports interactive policy switching without requiring any motion generation or motion matching mechanism. We highlight the applicability of our approach in a range of imitation and interactive control tasks, while also demonstrating its ability to withstand external perturbations as well as to recover balance. Overall, our approach has low runtime cost and can be easily integrated into interactive applications and games.

scholarly journals Exploiting Sentence Embedding for Medical Question Answering

2019 ◽  
Vol 33 ◽  
pp. 938-945 ◽  
Author(s):  
Yu Hao ◽  
Xien Liu ◽  
Ji Wu ◽  
Ping Lv
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Question Answering ◽  
Great Success ◽  
Semantic Matching ◽  
Semantic Association ◽  
Learning Framework ◽  
Multi Scale ◽  
Comparison Results ◽  
Real World Applications

Despite the great success of word embedding, sentence embedding remains a not-well-solved problem. In this paper, we present a supervised learning framework to exploit sentence embedding for the medical question answering task. The learning framework consists of two main parts: 1) a sentence embedding producing module, and 2) a scoring module. The former is developed with contextual self-attention and multi-scale techniques to encode a sentence into an embedding tensor. This module is shortly called Contextual self-Attention Multi-scale Sentence Embedding (CAMSE). The latter employs two scoring strategies: Semantic Matching Scoring (SMS) and Semantic Association Scoring (SAS). SMS measures similarity while SAS captures association between sentence pairs: a medical question concatenated with a candidate choice, and a piece of corresponding supportive evidence. The proposed framework is examined by two Medical Question Answering(MedicalQA) datasets which are collected from real-world applications: medical exam and clinical diagnosis based on electronic medical records (EMR). The comparison results show that our proposed framework achieved significant improvements compared to competitive baseline approaches. Additionally, a series of controlled experiments are also conducted to illustrate that the multi-scale strategy and the contextual self-attention layer play important roles for producing effective sentence embedding, and the two kinds of scoring strategies are highly complementary to each other for question answering problems.

Sign in / Sign up

Export Citation Format

Share Document