2022-09-25 更新
Vega-MT: The JD Explore Academy Translation System for WMT22
Authors:Changtong Zan, Keqin Peng, Liang Ding, Baopu Qiu, Boan Liu, Shwai He, Qingyu Lu, Zheng Zhang, Chuang Liu, Weifeng Liu, Yibing Zhan, Dacheng Tao
We describe the JD Explore Academy’s submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, including Chinese-English, German-English, Czech-English, Russian-English, and Japanese-English. We push the limit of our previous work — bidirectional training for translation by scaling up two main factors, i.e. language pairs and model sizes, namely the \textbf{Vega-MT} system. As for language pairs, we scale the “bidirectional” up to the “multidirectional” settings, covering all participating languages, to exploit the common knowledge across languages, and transfer them to the downstream bilingual tasks. As for model sizes, we scale the Transformer-Big up to the extremely large model that owns nearly 4.7 Billion parameters, to fully enhance the model capacity for our Vega-MT. Also, we adopt the data augmentation strategies, e.g. cycle translation for monolingual data, and bidirectional self-training for bilingual and monolingual data, to comprehensively exploit the bilingual and monolingual data. To adapt our Vega-MT to the general domain test set, generalization tuning is designed. Based on the official automatic scores of constrained systems, in terms of the sacreBLEU shown in Figure-1, we got the 1st place on {Zh-En (33.5), En-Zh (49.7), De-En (33.7), En-De (37.8), Cs-En (54.9), En-Cs (41.4) and En-Ru (32.7)}, 2nd place on {Ru-En (45.1) and Ja-En (25.6)}, and 3rd place on {En-Ja(41.5)}, respectively; W.R.T the COMET, we got the 1st place on {Zh-En (45.1), En-Zh (61.7), De-En (58.0), En-De (63.2), Cs-En (74.7), Ru-En (64.9), En-Ru (69.6) and En-Ja (65.1)}, 2nd place on {En-Cs (95.3) and Ja-En (40.6)}, respectively. Models will be released to facilitate the MT community through GitHub and OmniForce Platform.
PDF WMT 2022 (Among all constrained systems, Vega-MT won 7 champions, 2 runners-up and 1 third place w.r.t sacreBLEU, and won 8 champions and 2 runners-up w.r.t COMET.)
点此查看论文截图
Investigating and Mitigating Failure Modes in Physics-informed Neural Networks (PINNs)
Authors:Shamsulhaq Basir
In this paper, we demonstrate and investigate several challenges that stand in the way of tackling complex problems using physics-informed neural networks. In particular, we visualize the loss landscapes of trained models and perform sensitivity analysis of backpropagated gradients in the presence of physics. Our findings suggest that existing methods produce highly non-convex loss landscapes that are difficult to navigate. Furthermore, high-order PDEs contaminate the backpropagated gradients that may impede or prevent convergence. We then propose a novel method that bypasses the calculation of high-order PDE operators and mitigates the contamination of backpropagating gradients. In doing so, we reduce the dimension of the search space of our solution and facilitate learning problems with non-smooth solutions. Our formulation also provides a feedback mechanism that helps our model adaptively focus on complex regions of the domain that are difficult to learn. We then formulate an unconstrained dual problem by adapting the Lagrange multiplier method. We apply our method to solve several challenging benchmark problems governed by linear and non-linear PDEs.
PDF
点此查看论文截图
Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia
Authors:Khanh Nguyen, Ali Furkan Biten, Andres Mafla, Lluis Gomez, Dimosthenis Karatzas
Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information, even to the extent of inventing plausible explanations when contextual information and images do not match. In this work, we propose the novel task of captioning Wikipedia images by integrating contextual knowledge. Specifically, we produce models that jointly reason over Wikipedia articles, Wikimedia images and their associated descriptions to produce contextualized captions. Particularly, a similar Wikimedia image can be used to illustrate different articles, and the produced caption needs to be adapted to a specific context, therefore allowing us to explore the limits of a model to adjust captions to different contextual information. A particular challenging task in this domain is dealing with out-of-dictionary words and Named Entities. To address this, we propose a pre-training objective, Masked Named Entity Modeling (MNEM), and show that this pretext task yields an improvement compared to baseline models. Furthermore, we verify that a model pre-trained with the MNEM objective in Wikipedia generalizes well to a News Captioning dataset. Additionally, we define two different test splits according to the difficulty of the captioning task. We offer insights on the role and the importance of each modality and highlight the limitations of our model. The code, models and data splits are publicly available at Upon acceptance.
PDF
点此查看论文截图
Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling
Authors:Thiemo Wambsganss, Vinitra Swamy, Roman Rietsche, Tanja Käser
Natural Language Processing (NLP) has become increasingly utilized to provide adaptivity in educational applications. However, recent research has highlighted a variety of biases in pre-trained language models. While existing studies investigate bias in different domains, they are limited in addressing fine-grained analysis on educational and multilingual corpora. In this work, we analyze bias across text and through multiple architectures on a corpus of 9,165 German peer-reviews collected from university students over five years. Notably, our corpus includes labels such as helpfulness, quality, and critical aspect ratings from the peer-review recipient as well as demographic attributes. We conduct a Word Embedding Association Test (WEAT) analysis on (1) our collected corpus in connection with the clustered labels, (2) the most common pre-trained German language models (T5, BERT, and GPT-2) and GloVe embeddings, and (3) the language models after fine-tuning on our collected data-set. In contrast to our initial expectations, we found that our collected corpus does not reveal many biases in the co-occurrence analysis or in the GloVe embeddings. However, the pre-trained German language models find substantial conceptual, racial, and gender bias and have significant changes in bias across conceptual and racial axes during fine-tuning on the peer-review data. With our research, we aim to contribute to the fourth UN sustainability goal (quality education) with a novel dataset, an understanding of biases in natural language education data, and the potential harms of not counteracting biases in language models for educational tasks.
PDF Accepted as a full paper at COLING 2022: The 29th International Conference on Computational Linguistics, 12-17 of October 2022, Gyeongju, Republic of Korea
点此查看论文截图
Frequency Dropout: Feature-Level Regularization via Randomized Filtering
Authors:Mobarakol Islam, Ben Glocker
Deep convolutional neural networks have shown remarkable performance on various computer vision tasks, and yet, they are susceptible to picking up spurious correlations from the training signal. So called `shortcuts’ can occur during learning, for example, when there are specific frequencies present in the image data that correlate with the output predictions. Both high and low frequencies can be characteristic of the underlying noise distribution caused by the image acquisition rather than in relation to the task-relevant information about the image content. Models that learn features related to this characteristic noise will not generalize well to new data. In this work, we propose a simple yet effective training strategy, Frequency Dropout, to prevent convolutional neural networks from learning frequency-specific imaging features. We employ randomized filtering of feature maps during training which acts as a feature-level regularization. In this study, we consider common image processing filters such as Gaussian smoothing, Laplacian of Gaussian, and Gabor filtering. Our training strategy is model-agnostic and can be used for any computer vision task. We demonstrate the effectiveness of Frequency Dropout on a range of popular architectures and multiple tasks including image classification, domain adaptation, and semantic segmentation using both computer vision and medical imaging datasets. Our results suggest that the proposed approach does not only improve predictive accuracy but also improves robustness against domain shift.
PDF 15 pages
点此查看论文截图
Causal Effect Variational Autoencoder with Uniform Treatment
Authors:Daniel Jiwoong Im, Kyunghyun Cho, Narges Razavian
Domain adaptation and covariate shift are big issues in deep learning and they ultimately affect any causal inference algorithms that rely on deep neural networks. Causal effect variational autoencoder (CEVAE) is trained to predict the outcome given observational treatment data and it suffers from the distribution shift at test time. In this paper, we introduce uniform treatment variational autoencoders (UTVAE) that are trained with uniform treatment distribution using importance sampling and show that using uniform treatment over observational treatment distribution leads to better causal inference by mitigating the distribution shift that occurs from training to test time. We also explore the combination of uniform and observational treatment distributions with inference and generative network training objectives to find a better training procedure for inferring treatment effects. Experimentally, we find that the proposed UTVAE yields better absolute average treatment effect error and precision in the estimation of heterogeneous effect error than the CEVAE on synthetic and IHDP datasets.
PDF
点此查看论文截图
Can Shadows Reveal Biometric Information?
Authors:Safa C. Medin, Amir Weiss, Frédo Durand, William T. Freeman, Gregory W. Wornell
We study the problem of extracting biometric information of individuals by looking at shadows of objects cast on diffuse surfaces. We show that the biometric information leakage from shadows can be sufficient for reliable identity inference under representative scenarios via a maximum likelihood analysis. We then develop a learning-based method that demonstrates this phenomenon in real settings, exploiting the subtle cues in the shadows that are the source of the leakage without requiring any labeled real data. In particular, our approach relies on building synthetic scenes composed of 3D face models obtained from a single photograph of each identity. We transfer what we learn from the synthetic data to the real data using domain adaptation in a completely unsupervised way. Our model is able to generalize well to the real domain and is robust to several variations in the scenes. We report high classification accuracies in an identity classification task that takes place in a scene with unknown geometry and occluding objects.
PDF
点此查看论文截图
Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recovery
Authors:Zhenzhen Weng, Kuan-Chieh Wang, Angjoo Kanazawa, Serena Yeung
The ability to perceive 3D human bodies from a single image has a multitude of applications ranging from entertainment and robotics to neuroscience and healthcare. A fundamental challenge in human mesh recovery is in collecting the ground truth 3D mesh targets required for training, which requires burdensome motion capturing systems and is often limited to indoor laboratories. As a result, while progress is made on benchmark datasets collected in these restrictive settings, models fail to generalize to real-world “in-the-wild” scenarios due to distribution shifts. We propose Domain Adaptive 3D Pose Augmentation (DAPA), a data augmentation method that enhances the model’s generalization ability in in-the-wild scenarios. DAPA combines the strength of methods based on synthetic datasets by getting direct supervision from the synthesized meshes, and domain adaptation methods by using ground truth 2D keypoints from the target dataset. We show quantitatively that finetuning with DAPA effectively improves results on benchmarks 3DPW and AGORA. We further demonstrate the utility of DAPA on a challenging dataset curated from videos of real-world parent-child interaction.
PDF
点此查看论文截图
Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks
Authors:Siddhartha Datta
Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work, inspired by adversarial transferability, we propose a new type of black-box NLP adversarial attack that an attacker can choose a similar domain and transfer the adversarial examples to the target domain and cause poor performance in target model. Based on domain adaptation theory, we then propose a defensive strategy, called Learn2Weight, which trains to predict the weight adjustments for a target model in order to defend against an attack of similar-domain adversarial examples. Using Amazon multi-domain sentiment classification datasets, we empirically show that Learn2Weight is effective against the attack compared to standard black-box defense methods such as adversarial training and defensive distillation. This work contributes to the growing literature on machine learning safety.
PDF Accepted in COLING 2022
点此查看论文截图