The paucity of large curated hand-labeled training data forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant supervision signals in the form of labeling functions can be used to obtain labels for given data in near-constant time. In this work, we present Adversarial Data Programming (ADP), which presents an adversarial methodology to generate data as well as a curated aggregated label, given a set of weak labeling functions. More interestingly, such labeling functions are often easily generalizable, thus allowing our framework to be extended to different setups, including self-supervised labeled image generation, zero-shot text to labeled image generation, transfer learning, and multi-task learning.
We compare different models for low resource multi-task sequence tagging that leverage dependencies between label sequences for different tasks. Our analysis is aimed at datasets where each example has labels for multiple tasks. Current approaches use either a separate model for each task or standard multi-task learning to learn shared feature representations. However, these approaches ignore correlations between label sequences, which can provide important information in settings with small training datasets. To analyze which scenarios can profit from modeling dependencies between labels in different tasks, we revisit dynamic conditional random fields (CRFs) and combine them with deep neural networks. We compare single-task, multi-task and dynamic CRF setups for three diverse datasets at both sentence and document levels in English and German low resource scenarios. We show that including silver labels from pretrained part-of-speech taggers as auxiliary tasks can improve performance on downstream tasks. We find that especially in low-resource scenarios, the explicit modeling of inter-dependencies between task predictions outperforms single-task as well as standard multi-task models.
Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we propose AdapterFusion, a new two stage learning algorithm that leverages knowledge from multiple tasks. First, in the knowledge extraction stage we learn task specific parameters called adapters, that encapsulate the task-specific information. We then combine the adapters in a separate knowledge composition step. We show that by separating the two stages, i.e., knowledge extraction and knowledge composition, the classifier can effectively exploit the representations learned from multiple tasks in a non-destructive manner. We empirically evaluate AdapterFusion on 16 diverse NLU tasks, and find that it effectively combines various types of knowledge at different layers of the model. We show that our approach outperforms traditional strategies such as full fine-tuning as well as multi-task learning. Our code and adapters are available at AdapterHub.ml.
The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the task-specific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.
Machine learning has a recognised need for large amounts of annotated data. Due to the high cost of expert annotations, crowdsourcing, where non-experts are asked to label or outline images, has been proposed as an alternative. Although many promising results are reported, the quality of diagnostic crowdsourced labels is still unclear. We propose to address this by instead asking the crowd about visual features of the images, which can be provided more intuitively, and by using these features in a multi-task learning framework through ensemble strategies. We compare our proposed approach to a baseline model with a set of 2000 skin lesions from the ISIC 2017 challenge dataset. The baseline model only predicts a binary label from the skin lesion image, while our multi-task model also predicts one of the following features: asymmetry of the lesion, border irregularity and color. We show that multi-task models with individual crowdsourced features have limited effect on the model, but when combined in an ensembles, leads to improved generalisation. The area under the receiver operating characteristic curve is 0.794 for the baseline model and 0.811 and 0.808 for multi-task ensembles respectively. Finally, we discuss the findings, identify some limitations and recommend directions for further research. The code of the models is available at https://github.com/raumannsr/hints_crowd.
While state of the art image segmentation models typically output segmentations in raster format, applications in geographic information systems often require vector polygons. To help bridge the gap between deep network output and the format used in downstream tasks, we add a frame field output to a deep segmentation model for extracting buildings from remote sensing images. We train a deep neural network that aligns a predicted frame field to ground truth contours. This additional objective improves segmentation quality by leveraging multi-task learning and provides structural information that later facilitates polygonization; we also introduce a polygonization algorithm that utilizes the frame field along with the raster segmentation. Our code is available at https://github.com/Lydorn/Polygonization-by-Frame-Field-Learning.
Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights DO capture accurate word alignments and propose two novel word alignment induction methods Shift-Att and Shift-AET. The main idea is to induce alignments at the step when the to-be-aligned target token is the decoder input rather than the decoder output as in previous work. Shift-Att is an interpretation method that induces alignments from the attention weights of Transformer and does not require parameter update or architecture change. Shift-AET extracts alignments from an additional alignment module which is tightly integrated into Transformer and trained in isolation with supervision from symmetrized Shift-Att alignments. Experiments on three publicly available datasets demonstrate that both methods perform better than their corresponding neural baselines and Shift-AET significantly outperforms GIZA++ by 1.4-4.8 AER points.
Extracting structured knowledge from product profiles is crucial for various applications in e-Commerce. State-of-the-art approaches for knowledge extraction were each designed for a single category of product, and thus do not apply to real-life e-Commerce scenarios, which often contain thousands of diverse categories. This paper proposes TXtract, a taxonomy-aware knowledge extraction model that applies to thousands of product categories organized in a hierarchical taxonomy. Through category conditional self-attention and multi-task learning, our approach is both scalable, as it trains a single model for thousands of categories, and effective, as it extracts category-specific attribute values. Experiments on products from a taxonomy with 4,000 categories show that TXtract outperforms state-of-the-art approaches by up to 10% in F1 and 15% in coverage across all categories.
The emergence of a variety of graph-based meaning representations (MRs) has sparked an important conversation about how to adequately represent semantic structure. These MRs exhibit structural differences that reflect different theoretical and design considerations, presenting challenges to uniform linguistic analysis and cross-framework semantic parsing. Here, we ask the question of which design differences between MRs are meaningful and semantically-rooted, and which are superficial. We present a methodology for normalizing discrepancies between MRs at the compositional level (Lindemann et al., 2019), finding that we can normalize the majority of divergent phenomena using linguistically-grounded rules. Our work significantly increases the match in compositional structure between MRs and improves multi-task learning (MTL) in a low-resource setting, demonstrating the usefulness of careful MR design analysis and comparison.
Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation. By enabling the model to learn a better representation of the long dialogue context, our approaches attempt to solve the problem that the performance of the baseline significantly drops when the input dialogue context sequence is long. In our experiments, our proposed model achieves a 7.03% relative improvement over the baseline, establishing a new state-of-the-art joint goal accuracy of 52.04% on the MultiWOZ 2.0 dataset.
Multi-task learning (mtl) provides state-of-the-art results in many applications of computer vision and natural language processing. In contrast to single-task learning (stl), mtl allows for leveraging knowledge between related tasks improving prediction results on the main task (in contrast to an auxiliary task) or all tasks. However, there is a limited number of comparative studies on applying mtl architectures for regression and time series problems taking recent advances of mtl into account. An interesting, non-linear problem is the forecast of the expected power generation for renewable power plants. Therefore, this article provides a comparative study of the following recent and important mtl architectures: Hard parameter sharing, cross-stitch network, sluice network (sn). They are compared to a multi-layer perceptron model of similar size in an stl setting. Additionally, we provide a simple, yet effective approach to model task specific information through an embedding layer in an multi-layer perceptron, referred to as task embedding. Further, we introduce a new mtl architecture named emerging relation network (ern), which can be considered as an extension of the sluice network. For a solar power dataset, the task embedding achieves the best mean improvement with 14.9%. The mean improvement of the ern and the sn on the solar dataset is of similar magnitude with 14.7% and 14.8%. On a wind power dataset, only the ern achieves a significant improvement of up to 7.7%. Results suggest that the ern is beneficial when tasks are only loosely related and the prediction problem is more non-linear. Contrary, the proposed task embedding is advantageous when tasks are strongly correlated. Further, the task embedding provides an effective approach with reduced computational effort compared to other mtl architectures.
As an effective learning paradigm against insufficient training samples, Multi-Task Learning (MTL) encourages knowledge sharing across multiple related tasks so as to improve the overall performance. In MTL, a major challenge springs from the phenomenon that sharing the knowledge with dissimilar and hard tasks, known as negative transfer, often results in a worsened performance. Though a substantial amount of studies have been carried out against the negative transfer, most of the existing methods only model the transfer relationship as task correlations, with the transfer across features and tasks left unconsidered. Different from the existing methods, our goal is to alleviate negative transfer collaboratively across features and tasks. To this end, we propose a novel multi-task learning method called Task-Feature Collaborative Learning (TFCL). Specifically, we first propose a base model with a heterogeneous block-diagonal structure regularizer to leverage the collaborative grouping of features and tasks and suppressing inter-group knowledge sharing. We then propose an optimization method for the model. Extensive theoretical analysis shows that our proposed method has the following benefits: (a) it enjoys the global convergence property and (b) it provides a block-diagonal structure recovery guarantee. As a practical extension, we extend the base model by allowing overlapping features and differentiating the hard tasks. We further apply it to the personalized attribute prediction problem with fine-grained modeling of user behaviors. Finally, experimental results on both simulated dataset and real-world datasets demonstrate the effectiveness of our proposed method
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task. In this paper, we build an offensive language detection system, which combines multi-task learning with BERT-based models. Using a pre-trained language model such as BERT, we can effectively learn the representations for noisy text in social media. Besides, to boost the performance of offensive language detection, we leverage the supervision signals from other related tasks. In the OffensEval-2020 competition, our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place (92.23%F1). An empirical analysis is provided to explain the effectiveness of our approaches.
With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate neural network is trained for each individual task. Yet, recent multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint, by jointly tackling multiple tasks through a learned shared representation. In this survey, we provide a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision, explicitly emphasizing on dense prediction tasks. Our contributions concern the following. First, we consider MTL from a network architecture point-of-view. We include an extensive overview and discuss the advantages/disadvantages of recent popular MTL models. Second, we examine various optimization methods to tackle the joint learning of multiple tasks. We summarize the qualitative elements of these works and explore their commonalities and differences. Finally, we provide an extensive experimental evaluation across a variety of dense prediction benchmarks to examine the pros and cons of the different methods, including both architectural and optimization based strategies.
The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Representation Learning (HRL) termed in this paper. This brief survey covers the topic of HRL, centered around several major learning settings and real-world applications. First of all, from the mathematical perspective, we present a unified learning framework which is able to model most existing learning settings with the heterogeneous inputs. After that, we conduct a comprehensive discussion on the HRL framework by reviewing some selected learning problems along with the mathematics perspectives, including multi-view learning, heterogeneous transfer learning, Learning using privileged information and heterogeneous multi-task learning. For each learning task, we also discuss some applications under these learning problems and instantiates the terms in the mathematical framework. Finally, we highlight the challenges that are less-touched in HRL and present future research directions. To the best of our knowledge, there is no such framework to unify these heterogeneous problems, and this survey would benefit the community.
Deep learning based methods have achieved impressive results in many applications for image-based diet assessment such as food classification and food portion size estimation. However, existing methods only focus on one task at a time, making it difficult to apply in real life when multiple tasks need to be processed together. In this work, we propose an end-to-end multi-task framework that can achieve both food classification and food portion size estimation. We introduce a food image dataset collected from a nutrition study where the groundtruth food portion is provided by registered dietitians. The multi-task learning uses L2-norm based soft parameter sharing to train the classification and regression tasks simultaneously. We also propose the use of cross-domain feature adaptation together with normalization to further improve the performance of food portion size estimation. Our results outperforms the baseline methods for both classification accuracy and mean absolute error for portion estimation, which shows great potential for advancing the field of image-based dietary assessment.
Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing. However, there is currently no cross-task dataset in NLP, which hinders the development of multi-task learning. We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization. MATINF contains 1.07 million question-answer pairs with human-labeled categories and user-generated question descriptions. Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question answering, and summarization. We benchmark existing methods and a novel multi-task baseline over MATINF to inspire further research. Our comprehensive comparison and experiments over MATINF and other datasets demonstrate the merits held by MATINF.
Morphological information is important for many sequence labeling tasks in Natural Language Processing (NLP). Yet, existing approaches rely heavily on manual annotations or external software to capture this information. In this study, we propose using subword contextual embeddings to capture the morphological information for languages with rich morphology. In addition, we incorporate these embeddings in a hierarchical multi-task setting which is not employed before, to the best of our knowledge. Evaluated on Dependency Parsing (DEP) and Named Entity Recognition (NER) tasks, which are shown to benefit greatly from morphological information, our final model outperforms previous state-of-the-art models on both tasks for the Turkish language. Besides, we show a net improvement of 18.86% and 4.61% F-1 over the previously proposed multi-task learner in the same setting for the DEP and the NER tasks, respectively. Empirical results for five different MTL settings show that incorporating subword contextual embeddings brings significant improvements for both tasks. In addition, we observed that multi-task learning consistently improves the performance of the DEP component.
We propose a meta-learning approach that learns from multiple tasks in a transductive setting, by leveraging the unlabeled query set in addition to the support set to generate a more powerful model for each task. To develop our framework, we revisit the empirical Bayes formulation for multi-task learning. The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task. We derive a novel amortized variational inference that couples all the variational posteriors via a meta-model, which consists of a synthetic gradient network and an initialization network. Each variational posterior is derived from synthetic gradient descent to approximate the true posterior on the query set, although where we do not have access to the true gradient. Our results on the Mini-ImageNet and CIFAR-FS benchmarks for episodic few-shot classification outperform previous state-of-the-art methods. Besides, we conduct two zero-shot learning experiments to further explore the potential of the synthetic gradient.
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal performance. To fine-tune with less forgetting, we propose a recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks. Specifically, we propose a Pretraining Simulation mechanism to recall the knowledge from pretraining tasks without data, and an Objective Shifting mechanism to focus the learning on downstream tasks gradually. Experiments show that our method achieves state-of-the-art performance on the GLUE benchmark. Our method also enables BERT-base to achieve better performance than directly fine-tuning of BERT-large. Further, we provide the open-source RecAdam optimizer, which integrates the proposed mechanisms into Adam optimizer, to facility the NLP community.