paper-with-me

Papers

Curriculum Script Distillation for Multilingual Visual Question Answering

2023-01-17 · Khyathi Raghavi Chandu, Alborz Geramifard

Pre-trained models with dual and cross encoders have shown remarkable success in propelling the landscape of several tasks in vision and language in Visual Question Answering (VQA). However, since they are limited by the requirements of gold annotated data, most of these advancements do not see the light of day in other languages beyond English. We aim to address this problem by introducing a curriculum based on the source and target language translations to finetune the pre-trained models for the downstream task. Experimental results demonstrate that script plays a vital role in the performance of these models. Specifically, we show that target languages that share the same script perform better (~6%) than other languages and mixed-script code-switched languages perform better than their counterparts (~5-12%).

📄 PDF Abstract BibTeX arXiv:2301.07227

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation

2021-09-10 · Findings (EMNLP) 2021 11 · Humair Raj Khan, Deepak Gupta, Asif Ekbal

Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the reso…

Knowledge DistillationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

On the Design Fundamentals of Pixel Text Representation Learning

2026-09-01 · Chaohao Yuan, Ruifeng Yuan, Zhuoxu Huang, Yu Rong 외 hf

Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders struggle with fixed resolution pretraining, visual shortcut learning, weak v…

Representation LearningVisual Grounding

Neural Event Extraction from Movies Description

2018-06-01 · WS 2018 6 · Alex Tozzo, Dejan Jovanovi{\'c}, Mohamed Amer

We present a novel approach for event extraction and abstraction from movie descriptions. Our event frame consists of {``}who{''}, {``}did what{''} {``}to whom{''}, {``}where{''}, and {``}when{''}. We formulate our probl…

Event ExtractionMachine TranslationQuestion AnsweringStory Completion+1

Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset

2022-06-01 · LREC 2022 6 · Svetla Koeva, Ivelina Stoyanova, Jordan Kralev

One of the processing tasks for large multimodal data streams is automatic image description (image classification, object segmentation and classification). Although the number and the diversity of image datasets is cons…

Caption Generationimage-classificationImage ClassificationImage Description+7

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning

2026-05-26 · Zehao Liu, Yuanpu Cao, Jinghui Chen, Vasant G. Honavar arxiv

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-tea…

Reinforcement Learning