Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption. However, all existing caption editing works are implicit models, ie, they directly produce the refined captions without explicit connections to the reference captions. In this paper, we introduce a new task: Explicit Caption Editing (ECE). ECE models explicitly generate a sequence of edit operations, and this edit operation sequence can translate the reference caption into a refined one. Compared to the implicit editing, ECE has multiple advantages: 1) Explainable: it can trace the whole editing path. 2) Editing Efficient: it only needs to modify a few words. 3) Human-like: it resembles the way that humans perform caption editing, and tries to keep original sentence structures. To solve this new task, we propose the first ECE model: TIger. TIger is a non-autoregressive transformer-based model, consisting of three modules: Tagger_del, Tagger_add, and Inserter. Specifically, Tagger_del decides whether each word should be preserved or not, Tagger_add decides where to add new words, and Inserter predicts the specific word for adding. To further facilitate ECE research, we propose two new ECE benchmarks by re-organizing two existing datasets, dubbed COCO-EE and Flickr30K-EE, respectively. Extensive ablations on both two benchmarks have demonstrated the effectiveness of TIger.
We present TacoBot, a task-oriented dialogue system built for the inaugural Alexa Prize TaskBot Challenge, which assists users in completing multi-step cooking and home improvement tasks. TacoBot is designed with a user-centered principle and aspires to deliver a collaborative and accessible dialogue experience. Towards that end, it is equipped with accurate language understanding, flexible dialogue management, and engaging response generation. Furthermore, TacoBot is backed by a strong search engine and an automated end-to-end test suite. In bootstrapping the development of TacoBot, we explore a series of data augmentation strategies to train advanced neural language processing models and continuously improve the dialogue experience with collected real conversations. At the end of the semifinals, TacoBot achieved an average rating of 3.55/5.0.
Classifying the training data correctly without over-fitting is one of the goals in machine learning. In this paper, we propose a generalization-memorization mechanism, including a generalization-memorization decision and a memory modeling principle. Under this mechanism, error-based learning machines improve their memorization abilities of training data without over-fitting. Specifically, the generalization-memorization machines (GMM) are proposed by applying this mechanism. The optimization problems in GMM are quadratic programming problems and could be solved efficiently. It should be noted that the recently proposed generalization-memorization kernel and the corresponding support vector machines are the special cases of our GMM. Experimental results show the effectiveness of the proposed GMM both on memorization and generalization.
Question Answering (QA) is one of the most important natural language processing (NLP) tasks. It aims using NLP technologies to generate a corresponding answer to a given question based on the massive unstructured corpus. With the development of deep learning, more and more challenging QA datasets are being proposed, and lots of new methods for solving them are also emerging. In this paper, we investigate influential QA datasets that have been released in the era of deep learning. Specifically, we begin with introducing two of the most common QA tasks - textual question answer and visual question answering - separately, covering the most representative datasets, and then give some current challenges of QA research.
To investigate the heterogeneity in federated learning in real-world scenarios, we generalize the classic federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants in federated learning in terms of both data distribution and learning tasks. We also present B-FHTL, a federated hetero-task learning benchmark consisting of simulation dataset, FL protocols and a unified evaluation mechanism. B-FHTL dataset contains three well-designed federated learning tasks with increasing heterogeneity. Each task simulates the clients with different non-IID data and learning tasks. To ensure fair comparison among different FL algorithms, B-FHTL builds in a full suite of FL protocols by providing high-level APIs to avoid privacy leakage, and presets most common evaluation metrics spanning across different learning tasks, such as regression, classification, text generation and etc. Furthermore, we compare the FL algorithms in fields of federated multi-task learning, federated personalization and federated meta learning within B-FHTL, and highlight the influence of heterogeneity and difficulties of federated hetero-task learning. Our benchmark, including the federated dataset, protocols, the evaluation mechanism and the preliminary experiment, is open-sourced at https://github.com/alibaba/FederatedScope/tree/master/benchmark/B-FHTL
Hyperparameter optimization (HPO) is crucial for machine learning algorithms to achieve satisfactory performance, whose progress has been boosted by related benchmarks. Nonetheless, existing efforts in benchmarking all focus on HPO for traditional centralized learning while ignoring federated learning (FL), a promising paradigm for collaboratively learning models from dispersed data. In this paper, we first identify some uniqueness of HPO for FL algorithms from various aspects. Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting. To facilitate the research of HPO in the FL setting, we propose and implement a benchmark suite FedHPO-B that incorporates comprehensive FL tasks, enables efficient function evaluations, and eases continuing extensions. We also conduct extensive experiments based on FedHPO-B to benchmark a few HPO methods. We open-source FedHPO-B at https://github.com/alibaba/FederatedScope/tree/master/benchmark/FedHPOB.
To investigate the heterogeneity of federated learning in real-world scenarios, we generalize the classical federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants in federated learning in terms of both data distribution and learning tasks. We also present B-FHTL, a federated hetero-task learning benchmark consisted of simulation dataset, FL protocols and a unified evaluation mechanism. B-FHTL dataset contains three well-designed federated learning tasks with increasing heterogeneity. Each task simulates the clients with different data distributions and learning tasks. To ensure fair comparison among different FL algorithms, B-FHTL builds in a full suite of FL protocols by providing high-level APIs to avoid privacy leakage, and presets most common evaluation metrics spanning across different learning tasks, such as regression, classification, text generation and etc. Furthermore, we compare the FL algorithms in fields of federated multi-task learning, federated personalization and federated meta learning within B-FHTL, and highlight the influence of heterogeneity and difficulties of federated hetero-task learning. Our benchmark, including the federated dataset, protocols, the evaluation mechanism and the preliminary experiment, is open-sourced at https://github.com/alibaba/FederatedScope/tree/contest/v1.0.
Graph Neural Networks (GNNs) have received extensive research attention for their promising performance in graph machine learning. Despite their extraordinary predictive accuracy, existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs, rendering these models vulnerable to graph structural attacks and with limited capacity in generalizing to graphs of varied homophily levels. Although many methods have been proposed to improve the robustness of GNN models, most of these techniques are restricted to the spatial domain and employ complicated defense mechanisms, such as learning new graph structures or calculating edge attentions. In this paper, we study the problem of designing simple and robust GNN models in the spectral domain. We propose EvenNet, a spectral GNN corresponding to an even-polynomial graph filter. Based on our theoretical analysis in both spatial and spectral domains, we demonstrate that EvenNet outperforms full-order models in generalizing across homophilic and heterophilic graphs, implying that ignoring odd-hop neighbors improves the robustness of GNNs. We conduct experiments on both synthetic and real-world datasets to demonstrate the effectiveness of EvenNet. Notably, EvenNet outperforms existing defense models against structural attacks without introducing additional computational costs and maintains competitiveness in traditional node classification tasks on homophilic and heterophilic graphs.
In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria. Such a dialog is a combination of task-oriented and chitchat, different from traditional single-purpose human-machine dialog systems. However, due to the social stigma associated with mental illness, the dialogue data related to depression consultation and diagnosis are rarely disclosed. Though automatic dialogue-based diagnosis foresees great application potential, data sparsity has become one of the major bottlenecks restricting research on such task-oriented chat dialogues. Based on clinical depression diagnostic criteria ICD-11 and DSM-5, we construct the D$^4$: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat which simulates the dialogue between doctors and patients during the diagnosis of depression, including diagnosis results and symptom summary given by professional psychiatrists for each dialogue.Finally, we finetune on state-of-the-art pre-training models and respectively present our dataset baselines on four tasks including response generation, topic prediction, dialog summary, and severity classification of depressive episode and suicide risk. Multi-scale evaluation results demonstrate that a more empathy-driven and diagnostic-accurate consultation dialogue system trained on our dataset can be achieved compared to rule-based bots.