Challenge: a dataset for visual reasoning with natural language and images is available.
Approach: They propose a dataset for joint reasoning about natural language and images . they crowdsource 107,292 examples of English sentences paired with web photographs .
Outcome: The proposed dataset combines 107,292 examples of English sentences with web photographs . Qualitative analysis shows the data requires compositional joint reasoning .

Similar Papers

Visually Grounded Reasoning across Languages and Cultures (2021.emnlp-main)

Copied to clipboard

Challenge: a new protocol allows for a multilingual hierarchy of concepts and images based on native speakers . the results suggest that the current models are not robust enough to handle multilingual data .
Approach: They propose a protocol to construct an ImageNet-style hierarchy representative of more languages and cultures.
Outcome: The proposed protocol lets the selection of concepts and images be entirely driven by native speakers, rather than scraping them automatically.
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing models that use natural language rationales provide intuitive, higher-level explanations that are easily understandable by humans.
Approach: They propose a model that generates free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs.
Outcome: The proposed model generates free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs.
Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information (P18-3)

Copied to clipboard

Challenge: Recent research has focused on the intersection of computer vision and natural language processing, but its adaption to the medical domain is not fully explored.
Approach: They aim to develop machine learning models that can reason jointly on medical images and clinical text for advanced search, retrieval, annotation and description of medical images.
Outcome: The proposed models can reason jointly on medical images and clinical text for advanced search, retrieval, annotation and description of medical images.
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference (N18-1)

Copied to clipboard

Challenge: et al., 1996, show that many of the most actively studied problems in NLP depend in large part on natural language understanding (NLU).
Approach: They propose a dataset for machine learning that uses ten different genres of English to evaluate sentences for their meanings.
Outcome: The multi-genre natural language inference corpus is one of the largest available for natural language understanding.
Neural Naturalist: Generating Fine-Grained Image Comparisons (D19-1)

Copied to clipboard

Challenge: a dataset of 41k sentences describes fine-grained differences between photographs of birds . human observers are adept at making fine-grain comparisons, but sometimes require aid in distinguishing visually similar classes.
Approach: They propose a model that generates comparative language from a dataset of 41k sentences describing fine-grained differences between photographs of birds.
Outcome: The proposed model can explain differences in visual embedding space using natural language . it evaluates the results with humans who must use the descriptions to distinguish real images .
Representing Verbs with Visual Argument Vectors (2020.lrec-1)

Copied to clipboard

Challenge: Existing models for verb semantic similarities are based on linguistic data, but they do not register intuitive attributes.
Approach: They evaluated two textual distributional semantic models and a visual one to explore verb semantic similarities.
Outcome: The proposed models extract meaningful information and capture semantic similarity between verbs using visual distributional models.
CITE: A Corpus of Image-Text Discourse Relations (N19-1)

Copied to clipboard

Challenge: a crowd-sourced resource characterizes inferences in image-text contexts in the domain of cooking recipes . a recent study has found that image-image presentations are more effective at integrating text and image .
Approach: They propose a crowd-sourced resource for multimodal discourse characterizing inferences in image-text contexts in the domain of cooking recipes in the form of coherence relations.
Outcome: The proposed corpus enables a better understanding of communication and common-sense reasoning . it is particularly important for automating the understanding and generation of text-image presentations .
A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images (D18-1)

Copied to clipboard

Challenge: Existing approaches combine language and perception to infer word embeddings . however, the embeddables produced by such models do not reflect the actual word representations.
Approach: They propose a probabilistic model that integrates linguistic and perceptual inputs to explain observed word-context pairs in a text corpus.
Outcome: The proposed model achieves competitive or stronger results on tasks of assessing pairwise word similarity and image/caption retrieval compared to other state-of-the-art models.
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (D18-1)

Copied to clipboard

Challenge: a plethora of new natural language inference datasets has been created in recent years . however, these datasets do not provide clear insight into what type of reasoning or inference a model may be performing.
Approach: They propose to recast 13 existing natural language inference datasets into a common structure.
Outcome: The proposed datasets provide insight into how well a sentence representation captures distinct types of reasoning.
Probing Image-Language Transformers for Verb Understanding (2021.findings-acl)

Copied to clipboard

Challenge: Multimodal image-language transformers have achieved impressive results on a variety of tasks that rely on fine-tuning.
Approach: They collect a dataset of image-sentence pairs consisting of 421 verbs . they evaluate pretrained image-language transformers and find they fail more in situations that require verb understanding compared to other parts of speech.
Outcome: The proposed model trains on a manually-annotated and smaller dataset does better on the task.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations