scholarly journals Infobox-to-text Generation with Tree-like Planning based Attention Network

2020 ◽  
Author(s):  
Yang Bai ◽  
Ziran Li ◽  
Ning Ding ◽  
Ying Shen ◽  
Hai-Tao Zheng
Keyword(s):  
Error Propagation ◽  
Layer By Layer ◽  
Text Generation ◽  
Attention Network ◽  
Dynamic Tuning ◽  
Human Evaluation ◽  
Textual Description ◽  
End To End ◽  
Network Tree ◽  
Static Order

We study the problem of infobox-to-text generation that aims to generate a textual description from a key-value table. Representing the input infobox as a sequence, previous neural methods using end-to-end models without order-planning suffer from the problems of incoherence and inadaptability to disordered input. Recent planning-based models only implement static order-planning to guide the generation, which may cause error propagation between planning and generation. To address these issues, we propose a Tree-like PLanning based Attention Network (Tree-PLAN) which leverages both static order-planning and dynamic tuning to guide the generation. A novel tree-like tuning encoder is designed to dynamically tune the static order-plan for better planning by merging the most relevant attributes together layer by layer. Experiments conducted on two datasets show that our model outperforms previous methods on both automatic and human evaluation, and demonstrate that our model has better adaptability to disordered input.

scholarly journals Syntactically Look-Ahead Attention Network for Sentence Compression

2020 ◽  
Vol 34 (05) ◽  
pp. 8050-8057
Author(s):  
Hidetaka Kamigaito ◽  
Manabu Okumura
Keyword(s):  
Automatic Evaluation ◽  
Future Time ◽  
Attention Network ◽  
Human Evaluation ◽  
Sentence Compression ◽  
Look Ahead ◽  
The Future

Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot usually explicitly capture the relationships between decoded words and unseen words that will be decoded in the future time steps. Therefore, to avoid generating ungrammatical sentences, the decoder sometimes drops important words in compressing sentences. To solve this problem, we propose a novel Seq2Seq model, syntactically look-ahead attention network (SLAHAN), that can generate informative summaries by explicitly tracking both dependency parent and child words during decoding and capturing important words that will be decoded in the future. The results of the automatic evaluation on the Google sentence compression dataset showed that SLAHAN achieved the best kept-token-based-F1, ROUGE-1, ROUGE-2 and ROUGE-L scores of 85.5, 79.3, 71.3 and 79.1, respectively. SLAHAN also improved the summarization performance on longer sentences. Furthermore, in the human evaluation, SLAHAN improved informativeness without losing readability.

scholarly journals Data-to-Text Generation with Content Selection and Planning

2019 ◽  
Vol 33 ◽  
pp. 6908-6915 ◽  
Author(s):  
Ratish Puduppully ◽  
Li Dong ◽  
Mirella Lapata
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Network Models ◽  
Text Generation ◽  
Neural Network Models ◽  
Generation Task ◽  
Content Selection ◽  
End To End ◽  
Two Stages

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

scholarly journals An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos

2020 ◽  
Vol 34 (01) ◽  
pp. 303-311 ◽  
Author(s):  
Sicheng Zhao ◽  
Yunsheng Ma ◽  
Yang Gu ◽  
Jufeng Yang ◽  
Tengfei Xing ◽  
...  
Keyword(s):  
Neural Networks ◽  
Emotion Recognition ◽  
State Of The Art ◽  
Source Code ◽  
Cross Entropy ◽  
Attention Network ◽  
Audio Features ◽  
End To End ◽  
3D Cnn ◽  
And Training

Emotion recognition in user-generated videos plays an important role in human-centered computing. Existing methods mainly employ traditional two-stage shallow pipeline, i.e. extracting visual and/or audio features and training classifiers. In this paper, we propose to recognize video emotions in an end-to-end manner based on convolutional neural networks (CNNs). Specifically, we develop a deep Visual-Audio Attention Network (VAANet), a novel architecture that integrates spatial, channel-wise, and temporal attentions into a visual 3D CNN and temporal attentions into an audio 2D CNN. Further, we design a special classification loss, i.e. polarity-consistent cross-entropy loss, based on the polarity-emotion hierarchy constraint to guide the attention generation. Extensive experiments conducted on the challenging VideoEmotion-8 and Ekman-6 datasets demonstrate that the proposed VAANet outperforms the state-of-the-art approaches for video emotion recognition. Our source code is released at: https://github.com/maysonma/VAANet.

scholarly journals Learning Personalized End-to-End Goal-Oriented Dialog

2019 ◽  
Vol 33 ◽  
pp. 6794-6801 ◽  
Author(s):  
Liangchen Luo ◽  
Wenhao Huang ◽  
Qi Zeng ◽  
Zaiqing Nie ◽  
Xu Sun
Keyword(s):  
User Satisfaction ◽  
State Of The Art ◽  
User Preferences ◽  
Task Completion ◽  
Dialog Systems ◽  
Performance Improvements ◽  
Human Evaluation ◽  
Proposed Model ◽  
End To End ◽  
Qualitative Performance

Most existing works on dialog systems only consider conversation content while neglecting the personality of the user the bot is interacting with, which begets several unsolved issues. In this paper, we present a personalized end-to-end model in an attempt to leverage personalization in goal-oriented dialogs. We first introduce a PROFILE MODEL which encodes user profiles into distributed embeddings and refers to conversation history from other similar users. Then a PREFERENCE MODEL captures user preferences over knowledge base entities to handle the ambiguity in user requests. The two models are combined into the PERSONALIZED MEMN2N. Experiments show that the proposed model achieves qualitative performance improvements over state-of-the-art methods. As for human evaluation, it also outperforms other approaches in terms of task completion rate and user satisfaction.

A Topology Identification Algorithm Based on End-to-End Measurement in Wireless Sensor Networks

2014 ◽  
Vol 536-537 ◽  
pp. 756-759
Author(s):  
Wen Li Ji ◽  
Xue Lian Wang
Keyword(s):  
Hamming Distance ◽  
Packet Delay ◽  
Wireless Sensor ◽  
Identification Algorithm ◽  
Layer By Layer ◽  
It Use ◽  
Parent Child Relationship ◽  
Topology Identification ◽  
Child Relationship ◽  
End To End

Information of topology is significant for network planning and management in the Wireless Sensor Network (WSN). In this paper we propose a topology identification algorithm based on data fusion system in WSN. Firstly, the algorithm got the collections of approximate ancestors of each node according to the information of packet delay and/or packet loss. Secondly, it identifies parent-child relationship of the nodes by calculating the Hamming distance between the current node and approximate ancestors nodes; and infers the topology of the network layer by layer. It use end-to-end measurements and does not incur any additional burden on the network. NS2 simulation results show the high accuracy and efficiency of the proposed algorithm.

scholarly journals Neural data-to-text generation: A comparison between pipeline and end-to-end architectures

2019 ◽  
Author(s):  
Thiago Castro Ferreira ◽  
Chris van der Lee ◽  
Emiel van Miltenburg ◽  
Emiel Krahmer
Keyword(s):  
Text Generation ◽  
Neural Data ◽  
End To End

scholarly journals VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs

2021 ◽  
Author(s):  
Xudong Lin ◽  
Gedas Bertasius ◽  
Jue Wang ◽  
Shih-Fu Chang ◽  
Devi Parikh ◽  
...  
Keyword(s):  
Text Generation ◽  
End To End

scholarly journals A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues

2021 ◽  
Author(s):  
Ante Wang ◽  
Linfeng Song ◽  
Hui Jiang ◽  
Shaopeng Lai ◽  
Junfeng Yao ◽  
...  
Keyword(s):  
Error Propagation ◽  
State Of The Art ◽  
Representation Learning ◽  
Layer By Layer ◽  
Conversational Discourse ◽  
Incremental Methods ◽  
Discourse Parsing ◽  
Discourse Relations ◽  
Overall Performance ◽  
Dependency Structures

Conversational discourse structures aim to describe how a dialogue is organized, thus they are helpful for dialogue understanding and response generation. This paper focuses on predicting discourse dependency structures for multi-party dialogues. Previous work adopts incremental methods that take the features from the already predicted discourse relations to help generate the next one. Although the inter-correlations among predictions considered, we find that the error propagation is also very serious and hurts the overall performance. To alleviate error propagation, we propose a Structure Self-Aware (SSA) model, which adopts a novel edge-centric Graph Neural Network (GNN) to update the information between each Elementary Discourse Unit (EDU) pair layer by layer, so that expressive representations can be learned without historical predictions. In addition, we take auxiliary training signals (e.g. structure distillation) for better representation learning. Our model achieves the new state-of-the-art performances on two conversational discourse parsing benchmarks, largely outperforming the previous methods.

Effect of Welding Sequence on Deposition Geometry Control in GMAW Remanufacturing

2010 ◽  
Vol 139-141 ◽  
pp. 1937-1940
Author(s):  
Sheng Zhu ◽  
Yuan Yuan Liang ◽  
Qi Wei Wang
Keyword(s):  
Transient Heat Conduction ◽  
Element Model ◽  
Heating Time ◽  
Layer By Layer ◽  
Accuracy Control ◽  
Welding Sequence ◽  
Nonlinear Transient ◽  
End To End ◽  
Welding Sequences ◽  
Real Time Identification

GMAW welding remanufacturing is the process to form part layer by layer, that it is typical nonlinear transient heat conduction. During remanufacturing, parts undergo heating time after time that the thermal cycle fluctuates acutely and the distribution of temperature gradient is complex. And welding sequence is of significant for remanufacturing accuracy control. This paper has studied the effect of three typical welding sequences (sequential welding, spacing welding and end to end welding) on the deposition geometry control in GMAW remanufacturing, combining numerical with real-time identification. The comparison shows that the simulation results are in accordance with the actual data, which verified the valid of finite element model. From the analysis, it is found that the deformation of end to end welding is the least, and then is the sequential welding and the spacing welding is the largest.

Sign in / Sign up

Export Citation Format

Share Document