paper-with-me

Papers

On Vision Features in Multimodal Machine Translation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular in computer vision, we experiment with various strong models (such as Vision Transformer) and enhanced features (such as object-detection and image captioning). We develop a selective attention model to study the patch-level contribution of an image in MMT. On detailed probing tasks, we find that stronger vision models are helpful for learning translation from the vision modality. Our results also suggest the need of carefully examining MMT models, especially when current benchmarks are small-scale and biased.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningMachine TranslationMultimodal Machine Translationobject-detectionObject DetectionTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

On Vision Features in Multimodal Machine Translation

2022-03-17 · ACL 2022 5 · Bei Li, Chuanhao Lv, Zefan Zhou, Tao Zhou 외

Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the imp…

Image CaptioningMachine TranslationMultimodal Machine Translationobject-detection+2

Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding

2020-12-18 · Dexin Wang, Deyi Xiong

Visual context provides grounding information for multimodal machine translation (MMT). However, previous MMT models and probing studies on visual features suggest that visual information is less explored in MMT as it is…

Machine TranslationMultimodal Machine TranslationObjectTranslation

CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation

2023-08-29 · ICCV 2023 1 · Devaansh Gupta, Siddhant Kharbanda, Jiawei Zhou, Wanhua Li 외

There has been a growing interest in developing multimodal machine translation (MMT) systems that enhance neural machine translation (NMT) with visual knowledge. This problem setup involves using images as auxiliary info…

Image CaptioningMachine TranslationMultimodal Machine TranslationNMT+1

Improved English to Hindi Multimodal Neural Machine Translation

2021-08-01 · ACL (WAT) 2021 8 · Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Darsh Kaushik, Partha Pakray 외

Machine translation performs automatic translation from one natural language to another. Neural machine translation attains a state-of-the-art approach in machine translation, but it requires adequate training data, whic…

Data AugmentationMachine TranslationNMTTranslation

Dynamic Context-guided Capsule Network for Multimodal Machine Translation

2020-09-04 · Huan Lin, Fandong Meng, Jinsong Su, Yongjing Yin 외

Multimodal machine translation (MMT), which mainly focuses on enhancing text-only translation with visual features, has attracted considerable attention from both computer vision and natural language processing communiti…

DecoderMachine TranslationMultimodal Machine TranslationRepresentation Learning+1