TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge

• URL: http://arxiv.org/abs/2203.08517v1
• Date: Wed, 16 Mar 2022 10:37:59 GMT
• Title: TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge
• Authors: Chao-Hong Tan, Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu, Huang Hu, Xiubo Geng, Daxin Jiang
• Abstract summary: We propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework. Our model selects knowledge entries from two types of knowledge sources through dense retrieval and then injects them into the input encoding and output decoding stages respectively.
• Score: 83.55215993730326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki pages. However, their ability to access and manipulate the task-specific knowledge is still limited on downstream tasks, as this type of knowledge is usually not well covered in PLMs and is hard to acquire. To address the problem, we propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework. Our model selects knowledge entries from two types of knowledge sources through dense retrieval and then injects them into the input encoding and output decoding stages respectively on the basis of PLMs. With the help of these two types of knowledge, our model can learn what and how to generate. Experiments on two text generation tasks of dialogue generation and question generation, and on two datasets show that our method achieves better performance than various baseline models.

Related papers

• How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study [27.23388511249688]
  This paper investigates the layer-wise capability of large language models to encode knowledge. We leverage the powerful generative capability of ChatGPT to construct probing datasets. Experiments on conflicting and newly acquired knowledge show that LLMs prefer to encode more context knowledge in the upper layers.
  arXiv  Detail & Related papers  (2024-02-25T11:15:42Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization [41.20314472839442]
  We suggest a new framework: PromptMize, which targets table-to-text generation under few-shot settings. The design of our framework consists of two aspects: a prompt planner and a knowledge adapter. Our model achieves remarkable performance in generating quality as judged by human and automatic evaluations.
  arXiv  Detail & Related papers  (2023-02-09T03:04:11Z)
• A Survey of Knowledge Enhanced Pre-trained Language Models [78.56931125512295]
  We present a comprehensive review of Knowledge Enhanced Pre-trained Language Models (KE-PLMs) For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG) and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods.
  arXiv  Detail & Related papers  (2022-11-11T04:29:02Z)
• Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding [24.315130086787374]
  We propose a knowledge-prompting-based PLM framework KP-PLM. This framework can be flexibly combined with existing mainstream PLMs. To further leverage the factual knowledge from these prompts, we propose two novel knowledge-aware self-supervised tasks.
  arXiv  Detail & Related papers  (2022-10-16T13:36:57Z)
• Informative Text Generation from Knowledge Triples [56.939571343797304]
  We propose a novel memory augmented generator that employs a memory network to memorize the useful knowledge learned during the training. We derive a dataset from WebNLG for our new setting and conduct extensive experiments to investigate the effectiveness of our model.
  arXiv  Detail & Related papers  (2022-09-26T14:35:57Z)
• Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation [78.85622982191522]
  Existing systems perform poorly on unseen topics due to limited topics covered in the training data. We present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation. It can achieve comparable performance with state-of-the-art methods under a fully-supervised setting.
  arXiv  Detail & Related papers  (2021-12-15T07:11:02Z)
• A Survey of Knowledge-Enhanced Text Generation [81.24633231919137]
  The goal of text generation is to make machines express in human language. Various neural encoder-decoder models have been proposed to achieve the goal by learning to map input text to output text. To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.
  arXiv  Detail & Related papers  (2020-10-09T06:46:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.