Multimodal Neural Machine Translation Research Articles

Sanskrit to Hindi language translation using multimodal neural machine translation

Machine translation (MT) is a subfield of computer features that focuses on the automatic translation from one natural language into another without any human involvement. Due to native people interacting in a variety of languages, there is a great need for translating information between languages to send and communicate thoughts. However, they disregard the significance of semantic data encoded in the text features. In this paper, multimodal neural machine translation (MNMT) is proposed for Sanskrit-Hindi translation. The main goal of the proposed method is to fully utilize semantic text features on NMT architecture and to minimize testing and training time. The MNMT is validated on two different NMT architectures: recurrent neural network (RNN) and self-attention network (SAN). The MNMT method’s efficacy is demonstrated by employing the dataset of Sanskrit-Hindi Corpora. Extensive experimental outcomes represent the proposed method’s enhancement over baselines on both architectures. The existing methods, namely, English-to-Indian MT system, Sanskrit-Hindi MT system, and hybrid MT system are used to justify the efficacy of the MNMT method. When compared to the above-mentioned existing methods, RA-RNN respectively achieves a superior BLEU and METEOR of 80.5% and 75.3%, while the RA-SAN respectively achieves a superior BLEU and METEOR of 78.2% and 77.1%.

Progressive modality-complement aggregative multitransformer for domain multi-modal neural machine translation

Domain-specific Multi-modal Neural Machine Translation (DMNMT) aims to translate domain-specific sentences from a source language to a target language by incorporating text-related visual information. Generally, domain-specific text-image data often complement each other and have the potential to collaboratively enhance the representation of domain-specific information. Unfortunately, there is a considerable modality gap between image and text in data format and semantic expression, which leads to distinctive challenges in domain-text translation tasks. Narrowing the modality gap and improving domain-aware representation are two critical challenges in DMNMT. To this end, this paper proposes a progressive modality-complement aggregative MultiTransformer, which aims to simultaneously narrow the modality gap and capture domain-specific multi-modal representation. We first adopt a bidirectional progressive cross-modal interactive strategy to effectively narrow the text-to-text, text-to-visual, and visual-to-text semantics in the multi-modal representation space by integrating visual and text information layer-by-layer. Subsequently, we introduce a modality-complement MultiTransformer based on progressive cross-modal interaction to extract the domain-related multi-modal representation, thereby enhancing machine translation performance. Experiment results on the Fashion-MMT and Multi-30k datasets are conducted, and the results show that the proposed approach outperforms the compared state-of-the-art (SOTA) methods on the En-Zh task in E-commerce domain, En-De, En-Fr and En-Cs tasks of Multi-30k in general domain. The in-depth analysis confirms the validity of the proposed modality-complement MultiTransformer and bidirectional progressive cross-modal interactive strategy for DMNMT.

Multimodal Machine Translation

In recent years, neural network machine translation, especially in the field of multimodality, has developed rapidly. It has been widely used in natural languages processing tasks such as event detection and sentiment classification. The existing multimodal neural network machine translation is mostly based on the autoencoder framework of the attention mechanism, which further integrates spatial-visual features. However, due to the ubiquitous lack of corpus and the semantic interaction between multimodalities, the quality of machine translation is difficult to guarantee. Therefore, this paper proposes a multi-modal machine translation model that integrates external linguistic knowledge. Specifically, on the encoder side, we adopt the pre-trained Bert model to be used as an additional encoder to integrate with the original text encoder and picture encoder. Under the cooperation of the three encoders, a better text representation and picture representation at the source end is generated. Besides, the decoder decodes and generates a translation based on the image and text representation of the source. To sum up, this paper studies the visual-text semantic interaction on the encoder side and the visual-text semantic interaction on the decoder side, and further improves the quality of translation by introducing external linguistic knowledge. We compared the performance of the multimodal neural network machine translation model with pre-trained Bert and other baseline models in English German translation tasks on the multi30k data sets. The results show that the model can significantly improve the quality of multimodal neural network machine translation, which also verifies the importance of integrating external knowledge and visual text semantic interaction.

Multi-modal graph contrastive encoding for neural machine translation

As an important extension of conventional text-only neural machine translation (NMT), multi-modal neural machine translation (MNMT) aims to translate input source sentences paired with images into the target language. Although a lot of MNMT models have been proposed to perform multi-modal semantic fusion, they do not consider fine-grained semantic correspondences between semantic units of different modalities (i.e., words and visual objects), which can be exploited to refine multi-modal representation learning via fine-grained semantic interactions. To address this issue, we propose a graph-based multi-modal fusion encoder for NMT. Concretely, we first employ a unified multi-modal graph to represent the input sentence and image, in which the multi-modal semantic units are considered as the nodes in the graph, connected by two kinds of edges with different semantic relationships. Then, we stack multiple graph-based multi-modal fusion layers that iteratively conduct intra- and inter-modal interactions to learn node representations. Finally, via an attention mechanism, we induce a multi-modal context from the top node representations for the decoder. Particularly, we introduce a progressive contrastive learning strategy based on the multi-modal graph to refine the training of our proposed model, where hard negative samples are introduced gradually. To evaluate our model, we conduct experiments on commonly-used datasets. Experimental results and analysis show that our MNMT model obtains significant improvements over competitive baselines, achieving state-of-the-art performance on the Multi30K dataset.

Morphology & word sense disambiguation embedded multimodal neural machine translation system between Sanskrit and Malayalam

Machine translation is the process of conversion from one language to another using computers. In spite of the existence of several traditional machine translation systems like rule-based, statistical etc., the development of neural machine translation has significantly improved translation quality. However, the morphological richness and agglutinative nature of Indian languages hampers the usage of neural machine translation for translation among Indian languages despite its potential to overcome the difficulties posed by conventional translation systems. Hence the combination of neural machine translation with morphology, part of speech tagger and word sense disambiguation is proposed to address these challenges and adapt it for bidirectional translation between Sanskrit and Malayalam. Conventional neural machine translations are unimodal systems that utilize textual data for translation. Translation quality of conventional neural machine translation is enhanced with a novel multimodal bidirectional neural machine translation system with text & speech as the two modalities based on parallel text corpus and speech database. The best performance score is obtained for two level fusion, the feature vectors extracted from speech signals using different transforms (Wavelet transform, 1-D sequency mapped real transform & 1-D GCD based mapped real transform) are fused and which is further fused with a context vector from the text modality. Automatic and manual review methods are employed to assess quality of translation. Findings from the experiments reveal that addition of speech modality improved the overall quality of translation. BLEU scores of 43.89 and 42.72 are obtained for Sanskrit to Malayalam and Malayalam to Sanskrit multimodal translation respectively.

Learning to decode to future success for multi-modal neural machine translation

Existing only-text NMT (neural machine translation) systems can benefit from explicitly modelling target future contexts as recurrent states. However, the modelled target future context is implicit in the conventional only-text NMT as the target is invisible in inference. For the Multi-modal Neural Machine Translation (MNMT), the visual annotation presents the content described in the bilingual parallel sentence pair, so-called multi-modal consistency. This consistency provides an advantage that future target context can be simulated in visual features. This paper proposes a novel translation model that allows MNMT to encode the future target context from the visual annotation in auto-regressive decoding. Our model uses visual-target consistency to enhance the target generation. Moreover, we use the multi-modal consistency that fully uses the visual annotation to encourage the semantic agreement between bilingual parallel sentences and the pivoted visual annotation. Empirical results on several recent multi-model translation datasets demonstrated the MNMT model which we proposed significantly improved translation performance on a strong baseline, especially achieving new state-of-the-art results on all three language pairs with visual annotations. Our code will be available after acceptance.

Adding visual attention into encoder-decoder model for multi-modal machine translation

Multi-modal neural machine translation (MNMT) aims to integrate visual and textual information to translate source sentences into target and attracts a lot of attentions. Existing methods contribute a lot for capturing interactions between visual and textual features to improve the performance of neural machine translation (NMT). However, most of them don't consider the multi-modal consistency for MNMT. In fact, the image provides the semantic global consistency between different languages. We believe that adding bilingual-visual agreement into the encoder and decoder simultaneously can obtain bilingual representations and is useful for NMT. In this paper, we propose to simultaneously integrate visual information in encoder and decoder to learn the interactions between visual and textual features, in this paper called the model VMNMT. As the visual information provide global context, the encoder and decoder can learn the bilingual representations. Besides, we introduce a new bilingual-visual agreement decoder to learn to better representations of corresponding image-sentence pairs. In the experiment, the improvement was 2.02 BLEU on the English-German16 dataset and 1.9 BLEU on the English-German17 dataset. The results show that our method can outperform baselines on several widely-used datasets in terms of various metrics.

Layer-Level Progressive Transformer With Modality Difference Awareness for Multi-Modal Neural Machine Translation

Layer-Level Progressive Transformer With Modality Difference Awareness for Multi-Modal Neural Machine Translation

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.

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.

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).

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.

An error analysis for image-based multi-modal neural machine translation

In this article, we conduct an extensive quantitative error analysis of different multi-modal neural machine translation (MNMT) models which integrate visual features into different parts of both the encoder and the decoder. We investigate the scenario where models are trained on an in-domain training data set of parallel sentence pairs with images. We analyse two different types of MNMT models, that use global and local image features: the latter encode an image globally, i.e. there is one feature vector representing an entire image, whereas the former encode spatial information, i.e. there are multiple feature vectors, each encoding different portions of the image. We conduct an error analysis of translations generated by different MNMT models as well as text-only baselines, where we study how multi-modal models compare when translating both visual and non-visual terms. In general, we find that the additional multi-modal signals consistently improve translations, even more so when using simpler MNMT models that use global visual features. We also find that not only translations of terms with a strong visual connotation are improved, but almost all kinds of errors decreased when using multi-modal models.

Multimodal Neural Machine Translation With Weakly Labeled Images

Machine translation refers to a fully automated process that translates a user’s input text into a target language. To improve the accuracy of machine translation, studies usually exploit not only the input text itself but also various background knowledge related to the text, such as visual information or prior knowledge. Herein, in this paper, we propose a multimodal neural machine translation system that uses both texts and their related images to translate Korean image captions into English. The data in the experiment is a set of unlabeled images only containing bilingual captions. To train the system with a supervised learning approach, we propose a weak-labeling method that selects a keyword from an image caption using feature selection methods. The keywords are used to roughly determine an image label. We also introduce an improved feature selection method using sentence clustering to select keywords that reflect the characteristics of the image captions more accurately. We found that our multimodal system achieves an improved performance compared to a text-only neural machine translation system (baseline). Furthermore, the additional images have positive impacts on addressing the issue of under-translation, where some words in a source sentence are falsely translated or not translated at all.