We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual Similarity, Natural Language Inference, Named Entity Recognition, Relation Extraction, Dependency Parsing, Machine Reading Comprehension, and Dialogue State Tracking. We build all of the tasks from scratch from diverse source corpora while respecting copyrights, to ensure accessibility for anyone without any restrictions. With ethical considerations in mind, we carefully design annotation protocols. Along with the benchmark tasks and data, we provide suitable evaluation metrics and fine-tuning recipes for pretrained language models for each task. We furthermore release the pretrained language models (PLM), KLUE-BERT and KLUE-RoBERTa, to help reproducing baseline models on KLUE and thereby facilitate future research. We make a few interesting observations from the preliminary experiments using the proposed KLUE benchmark suite, already demonstrating the usefulness of this new benchmark suite. First, we find KLUE-RoBERTa-large outperforms other baselines, including multilingual PLMs and existing open-source Korean PLMs. Second, we see minimal degradation in performance even when we replace personally identifiable information from the pretraining corpus, suggesting that privacy and NLU capability are not at odds with each other. Lastly, we find that using BPE tokenization in combination with morpheme-level pre-tokenization is effective in tasks involving morpheme-level tagging, detection and generation. In addition to accelerating Korean NLP research, our comprehensive documentation on creating KLUE will facilitate creating similar resources for other languages in the future. KLUE is available at <a class="link-external link-https" href="https://klue-benchmark.com/">this URL</a>.
Neural machine translation (NMT) models are conventionally trained with token-level negative log-likelihood (NLL), which does not guarantee that the generated translations will be optimized for a selected sequence-level evaluation metric. Multiple approaches are proposed to train NMT with BLEU as the reward, in order to directly improve the metric. However, it was reported that the gain in BLEU does not translate to real quality improvement, limiting the application in industry. Recently, it became clear to the community that BLEU has a low correlation with human judgment when dealing with state-of-the-art models. This leads to the emerging of model-based evaluation metrics. These new metrics are shown to have a much higher human correlation. In this paper, we investigate whether it is beneficial to optimize NMT models with the state-of-the-art model-based metric, BLEURT. We propose a contrastive-margin loss for fast and stable reward optimization suitable for large NMT models. In experiments, we perform automatic and human evaluations to compare models trained with smoothed BLEU and BLEURT to the baseline models. Results show that the reward optimization with BLEURT is able to increase the metric scores by a large margin, in contrast to limited gain when training with smoothed BLEU. The human evaluation shows that models trained with BLEURT improve adequacy and coverage of translations. Code is available via https://github.com/naver-ai/MetricMT.
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; where tasks shares classes and is more realistic and practical. To address such task, we argue the importance of diversity of samples in an episodic memory. To enhance the sample diversity in the memory, we propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation, named Rainbow Memory (RM). With extensive empirical validations on MNIST, CIFAR10, CIFAR100, and ImageNet datasets, we show that the proposed method significantly improves the accuracy in blurry continual learning setups, outperforming state of the arts by large margins despite its simplicity. Code and data splits will be available in https://github.com/clovaai/rainbow-memory.
In recent years, graph neural networks (GNNs) have been widely adopted in representation learning of graph-structured data and provided state-of-the-art performance in various application such as link prediction and node classification. Simultaneously, self-supervised learning has been studied to some extent to leverage rich unlabeled data in representation learning on graphs. However, employing self-supervision tasks as auxiliary tasks to assist a primary task has been less explored in the literature on graphs. In this paper, we propose a novel self-supervised auxiliary learning framework to effectively learn graph neural networks. Moreover, we design first a meta-path prediction as a self-supervised auxiliary task for heterogeneous graphs. Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance. The proposed method identifies an effective combination of auxiliary tasks and automatically balances them to improve the primary task. Our methods can be applied to any graph neural networks in a plug-in manner without manual labeling or additional data. Also, it can be extended to any other auxiliary tasks. Our experiments demonstrate that the proposed method consistently improves the performance of link prediction and node classification on heterogeneous graphs.
Assessing advertisements, specifically on the basis of user preferences and ad quality, is crucial to the marketing industry. Although recent studies have attempted to use deep neural networks for this purpose, these studies have not utilized image-related auxiliary attributes, which include embedded text frequently found in ad images. We, therefore, investigated the influence of these attributes on ad image preferences. First, we analyzed large-scale real-world ad log data and, based on our findings, proposed a novel multi-step modality fusion network (M2FN) that determines advertising images likely to appeal to user preferences. Our method utilizes auxiliary attributes through multiple steps in the network, which include conditional batch normalization-based low-level fusion and attention-based high-level fusion. We verified M2FN on the AVA dataset, which is widely used for aesthetic image assessment, and then demonstrated that M2FN can achieve state-of-the-art performance in preference prediction using a real-world ad dataset with rich auxiliary attributes.
Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through token-level self-attention. Such token-level encoding hinders the exploration of discourse-level coherence among utterances. This paper presents DialogBERT, a novel conversational response generation model that enhances previous PLM-based dialogue models. DialogBERT employs a hierarchical Transformer architecture. To efficiently capture the discourse-level coherence among utterances, we propose two training objectives, including masked utterance regression and distributed utterance order ranking in analogy to the original BERT training. Experiments on three multi-turn conversation datasets show that our approach remarkably outperforms the baselines, such as BART and DialoGPT, in terms of quantitative evaluation. The human evaluation suggests that DialogBERT generates more coherent, informative, and human-like responses than the baselines with significant margins.
Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text but in a context irrelevant to the given question. This discrepancy becomes especially important as the number of occurrences of the answer text in a passage increases. To resolve this issue, we propose \textbf{BLANC} (\textbf{BL}ock \textbf{A}ttentio\textbf{N} for \textbf{C}ontext prediction) based on two main ideas: context prediction as an auxiliary task in multi-task learning manner, and a block attention method that learns the context prediction task. With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases. We also conduct an experiment of training the models using SQuAD and predicting the supporting facts on HotpotQA and show that BLANC outperforms all baseline models in this zero-shot setting.