Multimodal logical inference system for visual-textual entailment
A large amount of research about multimodal inference across text and vision has been
recently developed to obtain visually grounded word and sentence representations. In this …
recently developed to obtain visually grounded word and sentence representations. In this …
Functional distributional semantics: Learning linguistically informed representations from a precisely annotated corpus
G Emerson - 2018 - repository.cam.ac.uk
The aim of distributional semantics is to design computational techniques that can
automatically learn the meanings of words from a body of text. The twin challenges are: how …
automatically learn the meanings of words from a body of text. The twin challenges are: how …
Points, paths, and playscapes: Large-scale spatial language understanding tasks set in the real world
Spatial language understanding is important for practical applications and as a building
block for better abstract language understanding. Much progress has been made through …
block for better abstract language understanding. Much progress has been made through …
Learning to generate descriptions of visual data anchored in spatial relations
The explosive growth of visual data both online and offline in private and public repositories
has led to urgent requirements for better ways to index, search, retrieve, process and …
has led to urgent requirements for better ways to index, search, retrieve, process and …
Transfer of isospace into a 3d environment for annotations and applications
People's visual perception is very pronounced and therefore it is usually no problem for
them to describe the space around them in words. Conversely, people also have no …
them to describe the space around them in words. Conversely, people also have no …
Natural language semantics with pictures: Some language & vision datasets and potential uses for computational semantics
D Schlangen - arxiv preprint arxiv:1904.07318, 2019 - arxiv.org
Propelling, and propelled by, the" deep learning revolution", recent years have seen the
introduction of ever larger corpora of images annotated with natural language expressions …
introduction of ever larger corpora of images annotated with natural language expressions …
Natural language generation with computational intelligence [guest editorial]
The articles in this special section focus on using natural language generation techniques
(NLG) and natural language processing (NLP) to build computational systems that generate …
(NLG) and natural language processing (NLP) to build computational systems that generate …
The clarity and correctness of visualized thrust actions: a description and insights from users and experts
I Van der sluis, G Matoušková… - Visual …, 2022 - journals.sagepub.com
This article presents three studies that evaluate the effectiveness of instructional pictures that
visualize Heimlich maneuver thrusts. Firstly, a corpus study is used to describe a collection …
visualize Heimlich maneuver thrusts. Firstly, a corpus study is used to describe a collection …
Visual-Textual Entailment with Quantities Using Model Checking and Knowledge Injection
N Iokawa, H Yanaka - Proceedings of the 2024 Joint International …, 2024 - aclanthology.org
In recent years, there has been great interest in multimodal inference. We concentrate on
visual-textual entailment (VTE), a critical task in multimodal inference. VTE is the task of …
visual-textual entailment (VTE), a critical task in multimodal inference. VTE is the task of …
What did this castle look like before? exploring referential relations in naturally occurring multimodal texts
R Utescher, S Zarrieß - Proceedings of the Third Workshop on …, 2021 - aclanthology.org
Multi-modal texts are abundant and diverse in structure, yet Language & Vision research of
these naturally occurring texts has mostly focused on genres that are comparatively light on …
these naturally occurring texts has mostly focused on genres that are comparatively light on …