paper-with-me

Papers

An Enhanced Knowledge Injection Model for Commonsense Generation

2020-12-01 · COLING 2020 8 · Zhihao Fan, Yeyun Gong, Zhongyu Wei, Siyuan Wang, Yameng Huang, Jian Jiao, Xuanjing Huang, Nan Duan, Ruofei Zhang

Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external knowledge to assist the understanding of the scenario for better description generation. We integrate two additional modules, namely position indicator and scaling module, into the pretrained encoder-decoder model for prototype modeling to enhance the knowledge injection procedure. We conduct experiment on CommonGen benchmark, and experimental results show that our method significantly improves the performance on all the metrics.

📄 PDF Abstract BibTeX arXiv:2012.00366

Code (0)

등록된 구현이 없습니다.

Tasks

DecodermodelPosition

Similar Papers 제목 키워드 기반

Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering

2023-05-10 · Xin Guan, Biwei Cao, Qingqing Gao, Zheng Yin 외

Commonsense question answering (QA) research requires machines to answer questions based on commonsense knowledge. However, this research requires expensive labor costs to annotate data as the basis of research, and mode…

Contrastive LearningKnowledge GraphsQuestion Answering

KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation

2021-01-02 · ACL 2021 5 · Yiran Xing, Zai Shi, Zhao Meng, Gerhard Lakemeyer 외

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the g…

Knowledge GraphsLanguage ModelingLanguage ModellingLarge Language Model

Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection

2020-12-19 · Yikang Li, Pulkit Goel, Varsha Kuppur Rajendra, Har Simrat Singh 외

Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models. In this work, we specifically focus on the Commongen benchmark, wherein the aim is to gener…

Common Sense ReasoningConditional Text GenerationKnowledge GraphsLanguage Modeling+3

Commonsense Evidence Generation and Injection in Reading Comprehension

2020-05-11 · SIGDIAL (ACL) 2020 7 · Ye Liu, Tao Yang, Zeyu You, Wei Fan 외

Human tackle reading comprehension not only based on the given context itself but often rely on the commonsense beyond. To empower the machine with commonsense reasoning, in this paper, we propose a Commonsense Evidence …

Language ModelingLanguage ModellingReading Comprehension

On-the-Fly Attention Modulation for Neural Generation

2021-01-02 · Findings (ACL) 2021 8 · Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang 외

Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense…

Language ModellingSentenceText Generation