Multimodal Machine Translation Research Articles

Spatial Hierarchical Attention Network Based Video-guided Machine Translation

Video-guided machine translation, as one type of multimodal machine translation, aims to engage video contents as auxiliary information to address the word sense ambiguity problem in machine translation. Previous studies only use features from pre-trained action detection models as motion representations of the video to solve the verb sense ambiguity and neglect the noun sense ambiguity problem. To address this, we propose a video-guided machine translation system using both spatial and motion representations. For the spatial part, we propose a hierarchical attention network to model the spatial information from object-level to video-level. We investigate and discuss spatial features extracted from objects with pre-trained convolutional neural network models and spatial concept features extracted from object labels and attributes with pre-trained language models. We further investigate spatial feature filtering by referring to corresponding source sentences. Experiments on the VATEX dataset show that our system achieves a 35.86 BLEU-4 score, which is 0.51 score higher than the single model of the SOTA method. Experiments on the How2 dataset further verify the generalization ability of our proposed system.

Adding Visual Information to Improve Multimodal Machine Translation for Low-Resource Language

Machine translation makes it easy for people to communicate across languages. Multimodal machine translation is also one of the important directions of research in machine translation, which uses feature information such as images and audio to assist translation models in obtaining higher quality target languages. However, in the vast majority of current research work has been conducted on the basis of commonly used corpora such as English, French, German, less research has been done on low-resource languages, and this has left the translation of low-resource languages relatively behind. This paper selects the English-Hindi and English-Hausa corpus, researched on low-resource language translation. The different models we use for image feature information extraction are fusion of image features with text information in the text encoding process of translation, using image features to provide additional information, and assisting the translation model for translation. Compared with text-only machine translation, the experimental results show that our method improves 3 BLEU in the English-Hindi dataset and improves 0.47 BLEU in the English-Hausa dataset. In addition, we also analyze the effect of image feature information extracted by different feature extraction models on the translation results. Different models pay different attention to each region of the image, and ResNet model is able to extract more feature information compared to VGG model, which is more effective for translation.

Supervised Visual Attention for Simultaneous Multimodal Machine Translation

There has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality of textual systems. A particular use for such multimodal systems is the task of simultaneous machine translation, where visual context has been shown to complement the partial information provided by the source sentence, especially in the early phases of translation. In this paper, we propose the first Transformer-based simultaneous MMT architecture, which has not been previously explored in simultaneous translation. Additionally, we extend this model with an auxiliary supervision signal that guides the visual attention mechanism using labelled phrase-region alignments. We perform comprehensive experiments on three language directions and conduct thorough quantitative and qualitative analyses using both automatic metrics and manual inspection. Our results show that (i) supervised visual attention consistently improves the translation quality of the simultaneous MMT models, and (ii) fine-tuning the MMT with supervision loss enabled leads to better performance than training the MMT from scratch. Compared to the state-of-the-art, our proposed model achieves improvements of up to 2.3 BLEU and 3.5 METEOR points.

Image Visual Attention Mechanism-based Global and Local Semantic Information Fusion for Multi-modal English Machine Translation

<p>Machine translation is a hot research topic at present. Traditional machine translation methods are not effective because they require a large number of training samples. Image visual semantic information can improve the effect of the text machine translation model. Most of the existing works fuse the whole image visual semantic information into the translation model, but the image may contain different semantic objects. These different local semantic objects have different effects on the words prediction of the decoder. Therefore, this paper proposes a multi-modal machine translation model based on the image visual attention mechanism via global and local semantic information fusion. The global semantic information in the image and the local semantic information are fused into the text attention weight as the image attention. Thus, the alignment information between the hidden state of the decoder and the text of the source language is further enhanced. Experimental results on the English-German translation pair and the Indonesian-Chinese translation pair on the Multi30K dataset show that the proposed model has a better performance than the state-of-the-art multi-modal machine translation models, the BLEU values of English-German translation results and Indonesian-Chinese translation results exceed 43% and 29%, which proves the effectiveness of the proposed model.</p> <p> </p>

Dual-level interactive multimodal-mixup encoder for multi-modal neural machine translation

Dual-level interactive multimodal-mixup encoder for multi-modal neural machine translation

Region-attentive multimodal neural machine translation

We propose a multimodal neural machine translation (MNMT) method with semantic image regions called region-attentive multimodal neural machine translation (RA-NMT). Existing studies on MNMT have mainly focused on employing global visual features or equally sized grid local visual features extracted by convolutional neural networks (CNNs) to improve translation performance. However, they neglect the effect of semantic information captured inside the visual features. This study utilizes semantic image regions extracted by object detection for MNMT and integrates visual and textual features using two modality-dependent attention mechanisms. The proposed method was implemented and verified on two neural architectures of neural machine translation (NMT): recurrent neural network (RNN) and self-attention network (SAN). Experimental results on different language pairs of Multi30k dataset show that our proposed method improves over baselines and outperforms most of the state-of-the-art MNMT methods. Further analysis demonstrates that the proposed method can achieve better translation performance because of its better visual feature use.

Pre-Trained Word Embedding and Language Model Improve Multimodal Machine Translation: A Case Study in Multi30K

Multimodal machine translation (MMT) is an attractive application of neural machine translation (NMT) that is commonly incorporated with image information. However, the MMT models proposed thus far have only comparable or slightly better performance than their text-only counterparts. One potential cause of this infeasibility is a lack of large-scale data. Most previous studies mitigate this limitation by employing large-scale textual parallel corpora, which are more accessible than multimodal parallel corpora, in various ways. However, these corpora are still available on only a limited scale in low-resource language pairs or domains. In this study, we leveraged monolingual (or multimodal monolingual) corpora, which are available at scale in most languages and domains, to improve MMT models. Our approach follows that of previous unimodal works that use monolingual corpora to train the word embedding or language model and incorporate them into NMT systems. While these methods demonstrated the advantage of using pre-trained representations, there is still room for MMT models to improve. To this end, our system employs debiasing procedures for the word embedding and multimodal extension of the language model (visual-language model, VLM) to make better use of the pre-trained knowledge in the MMT task. The results of evaluations conducted on the de facto MMT dataset for the English–German translation indicate that the improvement obtained using well-tailored word embedding and VLM is approximately +1.84 BLEU and +1.63 BLEU, respectively. The evaluation on multiple language pairs reveals their adoptability across the languages. Beyond the success of our system, we also conducted an extensive analysis on VLM manipulation and showed promising areas for developing better MMT models by exploiting VLM; some benefits brought by either modality are missing, and MMT with VLM generates less fluent translations. Our code is available at https://github.com/toshohirasawa/mmt-with-monolingual-data.

Enhancing Neural Machine Translation With Dual-Side Multimodal Awareness

Multimodal machine translation (MMT) aims to translate a sentence in the source language into the target language with the context of an associated image. According to where the visual information is employed, previous approaches can be categorized into two types: directly injecting the visual information at the input side or exploiting it as a visual constraint at the objective side. In this work, we propose an IO-MMT model which exploits the visual assistance in dual sides to fully exploit the visual information for multimodal machine translation. It contains a relation-aware multimodal transformer to simultaneously exploit the objects and their spatial relationships in the image with a graph at the input-side and a novel visual assistance structure to further improve visual consistency of the translation at the objective-side. Experimental results under both normal setting and input degradation settings on the Multi30k benchmark dataset show that combining the visual assistance in dual sides consistently outperforms single-side MMT models and achieves the state-of-the-art results on EN-DE and EN-FR translation tasks. We will release the codes and models at https://github.com/syuqings/MMT.

Word-Region Alignment-Guided Multimodal Neural Machine Translation

We propose word-region alignment-guided multimodal neural machine translation (MNMT), a novel model for MNMT that links the semantic correlation between textual and visual modalities using word-region alignment (WRA). Existing studies on MNMT have mainly focused on the effect of integrating visual and textual modalities. However, they do not leverage the semantic relevance between the two modalities. We advance the semantic correlation between textual and visual modalities in MNMT by incorporating WRA as a bridge. This proposal has been implemented on two mainstream architectures of neural machine translation (NMT): the recurrent neural network (RNN) and the transformer. Experiments on two public benchmarks, English–German and English–French translation tasks using the Multi30k dataset and English–Japanese translation tasks using the Flickr30kEnt-JP dataset prove that our model has a significant improvement with respect to the competitive baselines across different evaluation metrics and outperforms most of the existing MNMT models. For example, 1.0 BLEU scores are improved for the English–German task and 1.1 BLEU scores are improved for the English–French task on the Multi30k test2016 set; and 0.7 BLEU scores are improved for the English–Japanese task on the Flickr30kEnt-JP test set. Further analysis demonstrates that our model can achieve better translation performance by integrating WRA, leading to better visual information use.

Video Pivoting Unsupervised Multi-Modal Machine Translation.

The main challenge in the field of unsupervised machine translation (UMT) is to associate source-target sentences in the latent space. As people who speak different languages share biologically similar visual systems, various unsupervised multi-modal machine translation (UMMT) models have been proposed to improve the performances of UMT by employing visual contents in natural images to facilitate alignment. Commonly, relation information is the important semantic in a sentence. Compared with images, videos can better present the interactions between objects and the ways in which an object transforms over time. However, current state-of-the-art methods only explore scene-level or object-level information from images without explicitly modeling objects relation; thus, they are sensitive to spurious correlations, which poses a new challenge for UMMT models. In this paper, we employ a spatial-temporal graph obtained from videos to exploit object interactions in space and time for disambiguation purposes and to promote latent space alignment in UMMT. Our model employs multi-modal back-translation and features pseudo-visual pivoting, in which we learn a shared multilingual visual-semantic embedding space and incorporate visually pivoted captioning as additional weak supervision. Experimental results on the VATEX Translation 2020 and HowToWorld datasets validate the translation capabilities of our model on both sentence-level and word-level and generalizes well when videos are not available during the testing phase.

MSVD-Turkish: a comprehensive multimodal video dataset for integrated vision and language research in Turkish

Automatic generation of video descriptions in natural language, also called video captioning, aims to understand the visual content of the video and produce a natural language sentence depicting the objects and actions in the scene. This challenging integrated vision and language problem, however, has been predominantly addressed for English. The lack of data and the linguistic properties of other languages limit the success of existing approaches for such languages. In this paper we target Turkish, a morphologically rich and agglutinative language that has very different properties compared to English. To do so, we create the first large-scale video captioning dataset for this language by carefully translating the English descriptions of the videos in the MSVD (Microsoft Research Video Description Corpus) dataset into Turkish. In addition to enabling research in video captioning in Turkish, the parallel English–Turkish descriptions also enable the study of the role of video context in (multimodal) machine translation. In our experiments, we build models for both video captioning and multimodal machine translation and investigate the effect of different word segmentation approaches and different neural architectures to better address the properties of Turkish. We hope that the MSVD-Turkish dataset and the results reported in this work will lead to better video captioning and multimodal machine translation models for Turkish and other morphology rich and agglutinative languages.

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

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 often redundant to textual information. In this paper, we propose an Object-level Visual Context modeling framework (OVC) to efficiently capture and explore visual information for multimodal machine translation. With detected objects, the proposed OVC encourages MMT to ground translation on desirable visual objects by masking irrelevant objects in the visual modality. We equip the proposed with an additional object-masking loss to achieve this goal. The object-masking loss is estimated according to the similarity between masked objects and the source texts so as to encourage masking source-irrelevant objects. Additionally, in order to generate vision-consistent target words, we further propose a vision-weighted translation loss for OVC. Experiments on MMT datasets demonstrate that the proposed OVC model outperforms state-of-the-art MMT models and analyses show that masking irrelevant objects helps grounding in MMT.

Read, spot and translate

We propose multimodal machine translation (MMT) approaches that exploit the correspondences between words and image regions. In contrast to existing work, our referential grounding method considers objects as the visual unit for grounding, rather than whole images or abstract image regions, and performs visual grounding in the source language, rather than at the decoding stage via attention. We explore two referential grounding approaches: (i) implicit grounding, where the model jointly learns how to ground the source language in the visual representation and to translate; and (ii) explicit grounding, where grounding is performed independent of the translation model, and is subsequently used to guide machine translation. We performed experiments on the Multi30K dataset for three language pairs: English–German, English–French and English–Czech. Our referential grounding models outperform existing MMT models according to automatic and human evaluation metrics.

Supervised Visual Attention for Multimodal Neural Machine Translation

This paper proposed a supervised visual attention mechanism for multimodal neural machine translation (MNMT), trained with constraints based on manual alignments between words in a sentence and their corresponding regions of an image. The proposed visual attention mechanism captures the relationship between a word and an image region more precisely than a conventional visual attention mechanism trained through MNMT in an unsupervised manner. Our experiments on English-German and German-English translation tasks using the Multi30k dataset and on English-Japanese and Japanese-English translation tasks using the Flickr30k Entities JP dataset show that a Transformer-based MNMT model can be improved by incorporating our proposed supervised visual attention mechanism and that further improvements can be achieved by combining it with a supervised cross-lingual attention mechanism (up to +1.61 BLEU, +1.7 METEOR).

Variational multimodal machine translation with underlying semantic alignment

Capturing the underlying semantic relationships of sentences is helpful for machine translation. Variational neural machine translation approaches provide an effective way to model the uncertain underlying semantics in languages by introducing latent variables. Multitask learning is applied in multimodal machine translation to integrate multimodal data. However, these approaches usually lack a strong interpretation in utilizing out-of-text information in machine translation tasks. In this paper, we propose a novel architecture-free multimodal translation model, called variational multimodal machine translation (VMMT), under the variational framework which can model the uncertainty in languages caused by ambiguity through utilizing visual and textual information. In addition, the proposed model can eliminate the discrepancy between training and prediction in the existing variational translation models by constructing encoders only relying on source data. More importantly, the proposed multimodal translation model is designed as multitask learning in which the shared semantic representation for different modes is learned and the gap among semantic representation from various modes is reduced by incorporating additional constraints. Moreover, the information bottleneck theory is adopted in our variational encoder–decoder model, which helps the encoder to filter redundancy and the decoder to concentrate on useful information. Experiments on multimodal machine translation demonstrate that the proposed model is competitive.

Multi-modal neural machine translation with deep semantic interactions

Based on the conventional attentional encoder-decoder framework, multi-modal neural machine translation (NMT) further incorporates spatial visual features through a separate visual attention mechanism. In this aspect, most current multi-modal NMT models first separately learn the semantic representations of text and image and then independently produce two modalities of context vectors for word predictions, neglecting their semantic interactions. In this paper, we argue that learning text-image semantic interactions is more reasonable in the sense of jointly modeling two modalities for multi-modal NMT and propose a novel multi-modal NMT model with deep semantic interactions. Specifically, our model extends the conventional multi-modal NMT by introducing the following two attention neural networks: (1) a bi-directional attention network for modeling text and image representations, where the semantic representations of text are learned by referring to the image representations, and vice versa; (2) a co-attention network for refining text and image context vectors, which first summarizes the text into a context vector, then attends it to the image for obtaining the text-aware visual context vector. The final context vector is calculated by re-attending the visual context vector to the text. Results on the Multi30k dataset for different language pairs show that our model significantly improves on the state-of-the-art baselines. We have released our code athttps://github.com/DeepLearnXMU/MNMT.

Multimodal machine translation through visuals and speech

Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively. These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language. This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. The paper concludes with a discussion of directions for future research in these areas: the need for more expansive and challenging datasets, for targeted evaluations of model performance, and for multimodality in both the input and output space.

A text-based visual context modulation neural model for multimodal machine translation

We introduce a novel multimodal machine translation model that integrates image features modulated by its caption. Generally, images contain vastly more information rather than just their description. Furthermore, in multimodal machine translation task, feature maps are commonly extracted from pre-trained network for objects. Therefore, it is not appropriate to utilize these feature map directly. To extract the visual features associated with the text, we design a modulation network based on the textual information from the encoder and visual information from the pretrained CNN. However, because multimodal translation data is scarce, using overly complicated models could result in poor performance. For simplicity, we apply a feature-wise multiplicative transformation. Therefore, our model is a modular trainable network embedded in the architecture in existing multimodal translation models. We verified our model by conducting experiments on the Transformer model with the Multi30k dataset and evaluating translation quality using the BLEU and METEOR metrics. In general, our model was an improvements over a text-based model and other existing models.

Visual Agreement Regularized Training for Multi-Modal Machine Translation

Multi-modal machine translation aims at translating the source sentence into a different language in the presence of the paired image. Previous work suggests that additional visual information only provides dispensable help to translation, which is needed in several very special cases such as translating ambiguous words. To make better use of visual information, this work presents visual agreement regularized training. The proposed approach jointly trains the source-to-target and target-to-source translation models and encourages them to share the same focus on the visual information when generating semantically equivalent visual words (e.g. “ball” in English and “ballon” in French). Besides, a simple yet effective multi-head co-attention model is also introduced to capture interactions between visual and textual features. The results show that our approaches can outperform competitive baselines by a large margin on the Multi30k dataset. Further analysis demonstrates that the proposed regularized training can effectively improve the agreement of attention on the image, leading to better use of visual information.

Hindi Visual Genome: A Dataset for Multi-Modal English to Hindi Machine Translation

Visual Genome is a dataset connecting structured image information with English language. We present “Hindi Visual Genome”, a multi-modal dataset consisting of text and images suitable for English-Hindi multi-modal machine translation task and multi-modal research. We have selected short English segments (captions) from Visual Genome along with the associated images and automatically translated them to Hindi. A careful manual post-editing followed which took the associated images into account. Overall, we prepared a set of 31,525 segments (which we conveniently split into training, development and testdata), accompanied by a challenge test set of 1,400 segments. This challenge test set was created by searching for particularly ambiguous English words based on the embedding similarity and manually selecting those where the image helps to resolvethe ambiguity. Our dataset is the first manually revised dataset for multi-modal English-Hindi machine translation, freely available for non-commercial research purposes. Our Hindi version of Visual Genome also allows to create Hindi image labelers or other practical tools. Hindi Visual Genome also served in Workshop on Asian Translation (WAT) 2019 Multi-Modal Translation Task.