arXiv:1704.03693
Trainable Referring Expression Generation using Overspecification Preferences
원문 초록
Referring expression generation (REG) models that use speaker-dependent information require a considerable amount of training data produced by every individual speaker, or may otherwise perform poorly. In this work we present a simple REG experiment that allows the use of larger training data sets by grouping speakers according to their overspecification preferences. Intrinsic evaluation shows that this method generally outperforms the personalised method found in previous work.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation
Grounding Language in Multi-Perspective Referential Communication
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding
Resilience through Scene Context in Visual Referring Expression Generation
Elysium: Exploring Object-level Perception in Videos via MLLM
토론
이 논문과 연결된 포럼 글이 아직 없습니다.