Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios. However, learning multiple training objectives in a single model is challenging due to the unknown relative significance as well as the potential contrariety between them. Empirical studies have shown that the current objective sampling in an ad-hoc manual setting makes the learned language representation barely converge to the desired optimum. Thus, we propose MOMETAS, a novel adaptive sampler based on meta-learning, which learns the latent sampling pattern on arbitrary pre-training objectives. Such a design is lightweight with negligible additional training overhead. To validate our approach, we adopt five objectives and conduct continual pre-training with BERT-base and BERT-large models, where MOMETAS demonstrates universal performance gain over other rule-based sampling strategies on 14 natural language processing tasks.
Although deep neural networks are effective at extracting high-level features, classification methods usually encode an input into a vector representation via simple feature aggregation operations (e.g. pooling). Such operations limit the performance. For instance, a multi-label document may contain several concepts. In this case, one vector can not sufficiently capture its salient and discriminative content. Thus, we propose Hyperbolic Capsule Networks (HyperCaps) for Multi-Label Classification (MLC), which have two merits. First, hyperbolic capsules are designed to capture fine-grained document information for each label, which has the ability to characterize complicated structures among labels and documents. Second, Hyperbolic Dynamic Routing (HDR) is introduced to aggregate hyperbolic capsules in a label-aware manner, so that the label-level discriminative information can be preserved along the depth of neural networks. To efficiently handle large-scale MLC datasets, we additionally present a new routing method to adaptively adjust the capsule number during routing. Extensive experiments are conducted on four benchmark datasets. Compared with the state-of-the-art methods, HyperCaps significantly improves the performance of MLC especially on tail labels.
Multi-label text classification (MLTC) aims to tag most relevant labels for the given document. In this paper, we propose a Label-Specific Attention Network (LSAN) to learn a label-specific document representation. LSAN takes advantage of label semantic information to determine the semantic connection between labels and document for constructing label-specific document representation. Meanwhile, the self-attention mechanism is adopted to identify the label-specific document representation from document content information. In order to seamlessly integrate the above two parts, an adaptive fusion strategy is proposed, which can effectively output the comprehensive label-specific document representation to build multi-label text classifier. Extensive experimental results demonstrate that LSAN consistently outperforms the state-of-the-art methods on four different datasets, especially on the prediction of low-frequency labels. The code and hyper-parameter settings are released to facilitate other researchers.