An Enhanced Knowledge Injection Model for Commonsense Generation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DecodermodelPositionSimilar Papers 제목 키워드 기반
Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering
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 AnsweringKM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
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 ModelLexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection
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+3Commonsense Evidence Generation and Injection in Reading Comprehension
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 ComprehensionOn-the-Fly Attention Modulation for Neural Generation
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