paper-with-me

홈 › Papers

Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps

2021-08-01 · ACL (splurobonlp) 2021 8 · Miltiadis Marios Katsakioris, Ioannis Konstas, Pierre Yves Mignotte, Helen Hastie

Robust situated dialog requires the ability to process instructions based on spatial information, which may or may not be available. We propose a model, based on LXMERT, that can extract spatial information from text instructions and attend to landmarks on OpenStreetMap (OSM) referred to in a natural language instruction. Whilst, OSM is a valuable resource, as with any open-sourced data, there is noise and variation in the names referred to on the map, as well as, variation in natural language instructions, hence the need for data-driven methods over rule-based systems. This paper demonstrates that the gold GPS location can be accurately predicted from the natural language instruction and metadata with 72% accuracy for previously seen maps and 64% for unseen maps.

📄 PDF Abstract BibTeX

Code (1)

marioskatsak/mapert 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

LXMERT LXMERT is a model for learning vision-and-language cross-modality representations. It consists of a Transformer model that consists three encoders: object relationship encoder, a…

Similar Papers 제목 키워드 기반

Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model

2024-07-09 · Wenqi Zhang, Zhenglin Cheng, Yuanyu He, Mengna Wang 외

Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilitie…

Chart UnderstandingLanguage ModelingLanguage ModellingVisual Reasoning

Cross-Task Generalization via Natural Language Crowdsourcing Instructions

2021-04-18 · ACL 2022 5 · Swaroop Mishra, Daniel Khashabi, Chitta Baral, Hannaneh Hajishirzi

Humans (e.g., crowdworkers) have a remarkable ability in solving different tasks, by simply reading textual instructions that define them and looking at a few examples. Despite the success of the conventional supervised …

Question Answering

Cross-Task Generalization via Natural Language Crowdsourcing Instructions

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Humans (e.g., crowdworkers) have a remarkable ability in solving different tasks, by simply reading textual instructions that define them and looking at a few examples. Despite the success of the conventional supervised …

Question Answering

FollowNet: Robot Navigation by Following Natural Language Directions with Deep Reinforcement Learning

2018-05-16 · Shah Pararth, Fiser Marek, Faust Aleksandra, Kew J. Chase 외

Understanding and following directions provided by humans can enable robots to navigate effectively in unknown situations. We present FollowNet, an end-to-end differentiable neural architecture for learning multi-modal n…

Deep Reinforcement LearningNavigatereinforcement-learningReinforcement Learning (RL)+1

Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation

2020-07-01 · EACL 2021 2 · Wanrong Zhu, Xin Eric Wang, Tsu-Jui Fu, An Yan 외

One of the most challenging topics in Natural Language Processing (NLP) is visually-grounded language understanding and reasoning. Outdoor vision-and-language navigation (VLN) is such a task where an agent follows natura…

Style TransferText Style TransferVision and Language Navigation