paper-with-me

홈 › Papers

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

2022-03-16 · Findings (ACL) 2022 5 · Chao-Hong Tan, Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu, Huang Hu, Xiubo Geng, Daxin Jiang

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.

📄 PDF Abstract BibTeX arXiv:2203.08517

Code (1)

lxchtan/tegtok 공식 구현 pytorch

Tasks

Dialogue GenerationKnowledge GraphsQuestion GenerationQuestion-GenerationRetrievalText GenerationWorld Knowledge

Similar Papers 제목 키워드 기반

Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt

2024-12-08 · Damien de Mijolla, Wen Yang, Philippa Duckett, Christopher Frye 외

Prompting and fine-tuning have emerged as two competing paradigms for augmenting language models with new capabilities, such as the use of tools. Prompting approaches are quick to set up but rely on providing explicit de…

Text Generation

Posterior Control of Blackbox Generation

2020-05-10 · ACL 2020 6 · Xiang Lisa Li, Alexander M. Rush

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural …

Text Generation

DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders

2021-06-25 · Shuming Ma, Li Dong, Shaohan Huang, Dongdong Zhang 외

While pretrained encoders have achieved success in various natural language understanding (NLU) tasks, there is a gap between these pretrained encoders and natural language generation (NLG). NLG tasks are often based on …

Abstractive Text SummarizationDecoderMachine TranslationNatural Language Understanding+5

kNN-BOX: A Unified Framework for Nearest Neighbor Generation

2023-02-27 · Wenhao Zhu, Qianfeng Zhao, Yunzhe Lv, ShuJian Huang 외

Augmenting the base neural model with a token-level symbolic datastore is a novel generation paradigm and has achieved promising results in machine translation (MT). In this paper, we introduce a unified framework kNN-BO…

Machine TranslationParaphrase GenerationQuestion GenerationQuestion-Generation+2

Augmenting Knowledge Graph Hierarchies Using Neural Transformers

2024-04-11 · Sanat Sharma, Mayank Poddar, Jayant Kumar, Kosta Blank 외

Knowledge graphs are useful tools to organize, recommend and sort data. Hierarchies in knowledge graphs provide significant benefit in improving understanding and compartmentalization of the data within a knowledge graph…

Knowledge Graphs