paper-with-me

홈 › Papers

Informative Text Generation from Knowledge Triples

2022-09-26 · Zihao Fu, Yijiang River Dong, Lidong Bing, Wai Lam

As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data. Among them, KB-to-text aims at converting a set of knowledge triples into human readable sentences. In the original setting, the task assumes that the input triples and the text are exactly aligned in the perspective of the embodied knowledge/information. In this paper, we extend this setting and explore how to facilitate the trained model to generate more informative text, namely, containing more information about the triple entities but not conveyed by the input triples. To solve this problem, we propose a novel memory augmented generator that employs a memory network to memorize the useful knowledge learned during the training and utilizes such information together with the input triples to generate text in the operational or testing phase. We derive a dataset from WebNLG for our new setting and conduct extensive experiments to investigate the effectiveness of our model as well as uncover the intrinsic characteristics of the setting.

📄 PDF Abstract BibTeX arXiv:2209.12733

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderText Generation

Methods 이 논문이 사용한 방법론

Memory Network 설명 없음

Similar Papers 제목 키워드 기반

Predicting Informativeness of Semantic Triples

2021-09-01 · RANLP 2021 9 · Judita Preiss

Many automatic semantic relation extraction tools extract subject-predicate-object triples from unstructured text. However, a large quantity of these triples merely represent background knowledge. We explore using full t…

InformativenessRelation Extraction

Enhancing Question Generation with Commonsense Knowledge

2021-06-19 · CCL 2021 8 · Xin Jia, Hao Wang, Dawei Yin, Yunfang Wu

Question generation (QG) is to generate natural and grammatical questions that can be answered by a specific answer for a given context. Previous sequence-to-sequence models suffer from a problem that asking high-quality…

Multi-Task LearningQuestion GenerationQuestion-GenerationRelation Classification

Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

2022-04-24 · Feifei Xu, Shanlin Zhou, Xinpeng Wang, Yunpu Ma 외

Open-domain multi-turn conversations normally face the challenges of how to enrich and expand the content of the conversation. Recently, many approaches based on external knowledge are proposed to generate rich semantic …

Dialogue GenerationFormInformativenessKnowledge Graphs

Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning

2020-04-19 · Hongcai Xu, Junpeng Bao, Gaojie Zhang

Knowledge graph-based dialogue systems are capable of generating more informative responses and can implement sophisticated reasoning mechanisms. However, these models do not take into account the sparseness and incomple…

Adversarial AttackDialogue GenerationMeta-Learning

Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation

2023-06-23 · Qianji Di, Wenxi Ma, Zhongang Qi, Tianxiang Hou 외

Scene Graph Generation (SGG) aims to structurally and comprehensively represent objects and their connections in images, it can significantly benefit scene understanding and other related downstream tasks. Existing SGG m…

Graph GenerationScene Graph GenerationScene Understanding