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

arXiv: https://arxiv.org/abs/2203.08517 · HTML: https://mlsanity.com/paper/2203.08517/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 57 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [Neural Responding Machine for Short-Text Conversation](https://mlsanity.com/paper/1503.02364/) (2015)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [A Survey of Knowledge-Enhanced Text Generation](https://mlsanity.com/paper/2010.04389/) (2020)
- [Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)](https://mlsanity.com/paper/1405.5869/) (2014)
- [KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning](https://mlsanity.com/paper/2009.12677/) (2020)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://mlsanity.com/paper/1506.06714/) (2015)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)

## Built on by (most cited first, 9 of 9)

- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects](https://mlsanity.com/paper/2501.18365/) (2025)
- [MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System](https://mlsanity.com/paper/2503.09600/) (2025)
- [Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception](https://mlsanity.com/paper/2410.12788/) (2024)
- [Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering](https://mlsanity.com/paper/2309.02233/) (2023)
- [Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation](https://mlsanity.com/paper/2410.08320/) (2024)
- [DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion](https://mlsanity.com/paper/2305.11517/) (2023)
- [QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate](https://mlsanity.com/paper/2603.11650/) (2026)

## Abstract (arXiv)

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.