paper-with-me

Papers

A Unified Framework for Multilingual and Code-Mixed Visual Question Answering

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Deepak Gupta, Pabitra Lenka, Asif Ekbal, Pushpak Bhattacharyya

In this paper, we propose an effective deep learning framework for multilingual and code- mixed visual question answering. The pro- posed model is capable of predicting answers from the questions in Hindi, English or Code- mixed (Hinglish: Hindi-English) languages. The majority of the existing techniques on Vi- sual Question Answering (VQA) focus on En- glish questions only. However, many applica- tions such as medical imaging, tourism, visual assistants require a multilinguality-enabled module for their widespread usages. As there is no available dataset in English-Hindi VQA, we firstly create Hindi and Code-mixed VQA datasets by exploiting the linguistic properties of these languages. We propose a robust tech- nique capable of handling the multilingual and code-mixed question to provide the answer against the visual information (image). To better encode the multilingual and code-mixed questions, we introduce a hierarchy of shared layers. We control the behaviour of these shared layers by an attention-based soft layer sharing mechanism, which learns how shared layers are applied in different ways for the dif- ferent languages of the question. Further, our model uses bi-linear attention with a residual connection to fuse the language and image fea- tures. We perform extensive evaluation and ablation studies for English, Hindi and Code- mixed VQA. The evaluation shows that the proposed multilingual model achieves state-of- the-art performance in all these settings.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Qtrade AI at SemEval-2022 Task 11: An Unified Framework for Multilingual NER Task

2022-04-14 · SemEval (NAACL) 2022 7 · Weichao Gan, Yuanping Lin, Guangbo Yu, Guimin Chen 외

This paper describes our system, which placed third in the Multilingual Track (subtask 11), fourth in the Code-Mixed Track (subtask 12), and seventh in the Chinese Track (subtask 9) in the SemEval 2022 Task 11: MultiCoNE…

Data Augmentationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1

Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders

2026-03-20 · Debajyoti Mazumder, Divyansh Pathak, Prashant Kodali, Jasabanta Patro arxiv

Multilingual encoder-based language models are widely adopted for code-mixed analysis tasks, yet we know surprisingly little about how they represent code-mixed inputs internally - or whether those representations meanin…

Hate Speech DetectionSentiment Analysis

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)

COMMENTATOR: A Code-mixed Multilingual Text Annotation Framework

2024-08-06 · Rajvee Sheth, Shubh Nisar, Heenaben Prajapati, Himanshu Beniwal 외

As the NLP community increasingly addresses challenges associated with multilingualism, robust annotation tools are essential to handle multilingual datasets efficiently. In this paper, we introduce a code-mixed multilin…

Sentencetext annotation

OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection

2026-08-31 · Xiaoyan Wei, Zhimin Yao, Ruilin Yang, Wei Zhang 외 arxiv

Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but often rely on increasingly complex designs such as heavy cross-modal fu…