# Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination

arXiv: https://arxiv.org/abs/2305.12256 · HTML: https://mlsanity.com/paper/2305.12256/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 75 references that are in the map.
- First posted on arXiv 20 May 2023.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Multi30K: Multilingual English-German Image Descriptions](https://mlsanity.com/paper/1605.00459/) (2016)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [An efficient framework for learning sentence representations](https://mlsanity.com/paper/1803.02893/) (2018)
- [Unsupervised Neural Machine Translation](https://mlsanity.com/paper/1710.11041/) (2017)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus](https://mlsanity.com/paper/2004.06295/) (2020)
- [Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation](https://mlsanity.com/paper/2105.14462/) (2021)
- [LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model](https://mlsanity.com/paper/2304.06248/) (2023)
- [Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge](https://mlsanity.com/paper/2105.02520/) (2021)
- [VALHALLA: Visual Hallucination for Machine Translation](https://mlsanity.com/paper/2206.00100/) (2022)
- [Neural Machine Translation with Phrase-Level Universal Visual Representations](https://mlsanity.com/paper/2203.10299/) (2022)
- [Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling](https://mlsanity.com/paper/2110.02001/) (2021)
- [Retrofitting Structure-aware Transformer Language Model for End Tasks](https://mlsanity.com/paper/2009.07408/) (2020)
- [Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting](https://mlsanity.com/paper/2005.03119/) (2020)

## Built on by (most cited first, 27 of 27)

- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation](https://mlsanity.com/paper/2308.05095/) (2023)
- [Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing](https://mlsanity.com/paper/2412.19806/) (2024)
- [Confabulation: The Surprising Value of Large Language Model Hallucinations](https://mlsanity.com/paper/2406.04175/) (2024)
- [3D-GRES: Generalized 3D Referring Expression Segmentation](https://mlsanity.com/paper/2407.20664/) (2024)
- [An Audit on the Perspectives and Challenges of Hallucinations in NLP](https://mlsanity.com/paper/2404.07461/) (2024)
- [Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling](https://mlsanity.com/paper/2308.05081/) (2023)
- [Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition](https://mlsanity.com/paper/2308.04502/) (2023)
- [PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2408.09481/) (2024)
- [Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation](https://mlsanity.com/paper/2308.02982/) (2023)
- [A Dual-way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking](https://mlsanity.com/paper/2312.11816/) (2023)
- [Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales](https://mlsanity.com/paper/2404.11129/) (2024)
- [A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges](https://mlsanity.com/paper/2405.12669/) (2024)
- [Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene](https://mlsanity.com/paper/2503.15019/) (2025)
- [Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval](https://mlsanity.com/paper/2406.05620/) (2024)
- [NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations](https://mlsanity.com/paper/2501.17261/) (2024)
- [Semi-Supervised Panoptic Narrative Grounding](https://mlsanity.com/paper/2310.18142/) (2023)
- [LightHouse: A Survey of AGI Hallucination](https://mlsanity.com/paper/2401.06792/) (2024)
- [Towards Zero-Shot Multimodal Machine Translation](https://mlsanity.com/paper/2407.13579/) (2024)
- [A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition](https://mlsanity.com/paper/2308.04424/) (2023)
- [Dual-branch Prompting for Multimodal Machine Translation](https://mlsanity.com/paper/2507.17588/) (2025)
- [DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs](https://mlsanity.com/paper/2308.04498/) (2023)
- [JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues](https://mlsanity.com/paper/2310.09503/) (2023)
- [Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing](https://mlsanity.com/paper/2407.04801/) (2024)
- [Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image](https://mlsanity.com/paper/2410.15312/) (2024)
- [Multimodal Machine Translation with Visual Scene Graph Pruning](https://mlsanity.com/paper/2505.19507/) (2025)
- [Dynamic Syntax Mapping: A New Approach to Unsupervised Syntax Parsing](https://mlsanity.com/paper/2312.14966/) (2023)

## Abstract (arXiv)

In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs. First, we represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. To enable pure-text input during inference, we devise a visual scene hallucination mechanism that dynamically generates pseudo visual SG from the given textual SG. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. On the benchmark Multi30K data, our SG-based method outperforms the best-performing baseline by significant BLEU scores on the task and setup, helping yield translations with better completeness, relevance and fluency without relying on paired images. Further in-depth analyses reveal how our model advances in the task setting.