Papers with Automatic generation

4 papers
Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks (N18-4)

Copied to clipboard

Challenge: Existing studies on image caption generation in English focus on Western languages, ignoring Semitic and Middle-Eastern languages like Arabic, Hebrew, Urdu and Persian.
Approach: They propose to leverage the critical dependency of Arabic to generate Arabic captions using root-word based Recurrent Neural Network and Deep Neural networks.
Outcome: The proposed model outperforms English-Arabic translated captions on a dataset from newspapers in the Middle East.
Paraphrase Generation with Deep Reinforcement Learning (D18-1)

Copied to clipboard

Challenge: Paraphrase generation is an important but challenging task in natural language processing . traditional symbolic approaches to paraphrase generation include rule-based methods, thesaurus-based approaches and statistical machine translation (SMT)
Approach: They propose a deep reinforcement learning approach to automatic paraphrase generation . they propose supervised learning and reinforcement learning for evaluators .
Outcome: The proposed framework outperforms state-of-the-art methods in paraphrase generation on two datasets.
Dynamic Knowledge Prompt for Chest X-ray Report Generation (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for radiology report generation fail to incorporate prior knowledge . data bias, sparse features of chest X-ray image make it difficult to generate reports .
Approach: They propose a dynamically integrated framework for chest X-ray report generation that incorporates pulmonary lesion knowledge at the instance-level.
Outcome: The proposed framework can dynamically incorporate pulmonary lesion knowledge at instance-level to facilitate report generation.
SpreadNaLa: A Naturalistic Code Generation Evaluation Dataset of Spreadsheet Formulas (2024.lrec-main)

Copied to clipboard

Challenge: Existing datasets primarily target the use of code generation models to aid expert programmers in writing code.
Approach: They propose a natural language code generation model that can translate English descriptions to spreadsheet formulas that can be used to do everyday data processing tasks.
Outcome: The proposed model performs best among the evaluated methods but generates formulas that differ from human-generated ones.

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