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

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.

Download Full-text

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

10.1109/cvpr46437.2021.00693 ◽

2021 ◽

Author(s):

Xudong Lin ◽

Gedas Bertasius ◽

Jue Wang ◽

Shih-Fu Chang ◽

Devi Parikh ◽

...

Keyword(s):

Text Generation ◽

End To End

Download Full-text

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

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/522 ◽

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.

Download Full-text

Neural data-to-text generation with dynamic content planning

Knowledge-Based Systems ◽

10.1016/j.knosys.2020.106610 ◽

2020 ◽

pp. 106610

Author(s):

Kai Chen ◽

Fayuan Li ◽

Baotian Hu ◽

Weihua Peng ◽

Qingcai Chen ◽

...

Keyword(s):

Text Generation ◽

Neural Data ◽

Dynamic Content

Download Full-text

End-to-End Argumentation Knowledge Graph Construction

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6231 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7367-7374

Author(s):

Khalid Al-Khatib ◽

Yufang Hou ◽

Henning Wachsmuth ◽

Charles Jochim ◽

Francesca Bonin ◽

...

Keyword(s):

Large Scale ◽

Question Answering ◽

Knowledge Graph ◽

Exploratory Search ◽

Text Generation ◽

Fake News ◽

High Quality ◽

Web Based ◽

Knowledge Graphs ◽

End To End

This paper studies the end-to-end construction of an argumentation knowledge graph that is intended to support argument synthesis, argumentative question answering, or fake news detection, among others. The study is motivated by the proven effectiveness of knowledge graphs for interpretable and controllable text generation and exploratory search. Original in our work is that we propose a model of the knowledge encapsulated in arguments. Based on this model, we build a new corpus that comprises about 16k manual annotations of 4740 claims with instances of the model's elements, and we develop an end-to-end framework that automatically identifies all modeled types of instances. The results of experiments show the potential of the framework for building a web-based argumentation graph that is of high quality and large scale.

Download Full-text