Papers with description generation

6 papers
Improving Image Captioning via Predicting Structured Concepts (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies on image captioning ignore the relationship between concepts . current methods for image caption generation ignore this relationship .
Approach: They propose a structured concept predictor to predict concepts and their structures . they integrate these predictions into captioning to enhance visual signals .
Outcome: The proposed approach improves image captioning performance by using semantic concepts as a bridge between images and texts.
An Enhanced Knowledge Injection Model for Commonsense Generation (2020.coling-main)

Copied to clipboard

Challenge: a recent study shows that digging the relationship of concepts from scratch is non-trivial for commonsense generation tasks.
Approach: They use a retrieve-and-edit framework to retrieve a prototype with these concepts . they use qt and qq to generate commonsense questions at scale .
Outcome: The proposed method significantly improves the performance on commonsense generation tasks.
Exploring the Capability of Multimodal LLMs with Yonkoma Manga: The YManga Dataset and Its Challenging Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: YManga dataset is the first specifically designed for yonkoma manga understanding .
Approach: They propose to use a dataset of 1,015 yonkoma strips with 10,150 human annotations to define three tasks for panel sequence detection, intent generation and description generation for masked panels.
Outcome: The proposed dataset contains 1,015 high-quality yonkoma strips with 10,150 human annotations.
IRR: Image Review Ranking Framework for Evaluating Vision-Language Models (2025.coling-main)

Copied to clipboard

Challenge: Large-scale vision language models excel at generating factual content, but their ability to rank images from multiple perspectives has not been explored.
Approach: They propose a framework to evaluate large-scale vision-language models by measuring their ability to rank image texts from multiple perspectives.
Outcome: The proposed evaluation framework measures how closely LVLMs' judgments align with human interpretations.
NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for Jupyter Notebooks focus on generating cell-level descriptions from code snippets or table outputs independently.
Approach: They propose a task to generate personalized cell-level descriptions using code, tables, and user-written guidelines in Jupyter Notebooks.
Outcome: The proposed task combines code, tables, and user-written guidelines with personalized descriptions to evaluate the performance of existing models.
MotifAgent: Learning Molecular Assembly through Multi-Agent Collaboration for Chemical Language Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to molecular understanding are limited to static motif recognition without understanding connection rules governing how motifs assemble into valid topological structures.
Approach: They propose a multi-agent reinforcement learning framework inspired by emergent collective intelligence to solve a problem where each motif is represented by an agent sharing a common LLM backbone.
Outcome: Extensive experiments show that the proposed framework surpasses specialized expert models in molecular understanding tasks.

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