DualTKB: A Dual Learning Bridge between Text and Knowledge Base
In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak supervision by creating a weakly supervised dataset and show that even a slight amount of supervision can significantly improve the model performance and enable better-quality transfers. We examine different model architectures, and evaluation metrics, proposing a novel Commonsense KB completion metric tailored for generative models. Extensive experimental results show that the proposed method compares very favorably to the existing baselines. This approach is a viable step towards a more advanced system for automatic KB construction/expansion and the reverse operation of KB conversion to coherent textual descriptions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
KBGN: Knowledge-Bridge Graph Network for Adaptive Vision-Text Reasoning in Visual Dialogue
Visual dialogue is a challenging task that needs to extract implicit information from both visual (image) and textual (dialogue history) contexts. Classical approaches pay more attention to the integration of the current…
Information RetrievalRetrievalQuery Answering over Contextualized RDF/OWL Knowledge with Forall-Existential Bridge Rules: Attaining Decidability using Acyclicity (full version)
The recent outburst of context-dependent knowledge on the Semantic Web (SW) has led to the realization of the importance of the quads in the SW community. Quads, which extend a standard RDF triple, by adding a new parame…
Adapting Knowledge for Few-shot Table-to-Text Generation
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data an…
Table-to-Text GenerationText GenerationTAViS: Text-bridged Audio-Visual Segmentation with Foundation Models
Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-mo…
cross-modal alignmentSegmentationA Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering
Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image. This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever …
DecoderKnowledge DistillationQuestion AnsweringRetrieval+2