paper-with-me

홈 › Papers

Imagination-Augmented Natural Language Understanding

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Human brains integrate linguistic and perceptual information simultaneously to understand natural language and hold the critical ability to render imaginations. Such abilities enable us to construct new abstract concepts or concrete objects and are essential in involving applicable knowledge to solve problems in low-resource scenarios. However, most existing methods for Natural Language Understanding (NLU) are mainly focused on textual signals. They do not simulate human visual imagination ability, which hinders models from inferring and learning efficiently from limited data samples.Therefore, we introduce an Imagination-Augmented Cross-modal Encoder (iACE) to solve natural language understanding tasks from a novel learning perspective---imagination-augmented cross-modal understanding. iACE enables visual imagination with the external knowledge transferred from the powerful generative model and pre-trained vision-and-language model.Extensive experiments on GLUE and SWAG datasets show that iACE achieves consistent improvement over visually-supervised pre-trained models. More importantly, results in extreme and normal few-shot settings validate the effectiveness of iACE in low-resource natural language understanding circumstances.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

Imagination-Augmented Natural Language Understanding

2022-04-18 · NAACL 2022 7 · Yujie Lu, Wanrong Zhu, Xin Eric Wang, Miguel Eckstein 외

Human brains integrate linguistic and perceptual information simultaneously to understand natural language, and hold the critical ability to render imaginations. Such abilities enable us to construct new abstract concept…

Natural Language Understanding

Learning to Imagine: Visually-Augmented Natural Language Generation

2023-05-26 · Tianyi Tang, Yushuo Chen, Yifan Du, Junyi Li 외

People often imagine relevant scenes to aid in the writing process. In this work, we aim to utilize visual information for composition in the same manner as humans. We propose a method, LIVE, that makes pre-trained langu…

SentenceText Generation

On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation

2026-02-06 · Wenbo Shang, Yuxi Sun, Jing Ma, Xin Huang arxiv

Humor is a commonly used and intricate human language in daily life. Humor generation, especially in multi-modal scenarios, is a challenging task for large language models (LLMs), which is typically as funny caption gene…

ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation

2021-06-10 · Wanrong Zhu, Xin Eric Wang, An Yan, Miguel Eckstein 외

Automatic evaluations for natural language generation (NLG) conventionally rely on token-level or embedding-level comparisons with text references. This differs from human language processing, for which visual imaginatio…

nlg evaluationText Generation

ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Automatic evaluations for natural language generation conventionally rely on token-level or embedding-level comparisons with the text references. This is different from human evaluation manners, in which people also form…

nlg evaluationText Generation