Global-to-Local Neural Networks for Document-Level Relation Extraction

TL;DR: More recently, with the advances made in the continuous representation of words (word embeddings) and deep neural architectures, many research works are published in the area of relation extraction as discussed by the authors.

TL;DR: Li et al. as mentioned in this paper proposed a three-stage evidenceenhanced DocRE framework consisting of joint relation and evidence extraction, evidence-centered relation extraction (RE), and fusion of extraction results.

TL;DR: This paper proposes a two-stage mention-level framework for document-level relation extraction using an enhanced heterogeneous graph attention network, addressing class imbalance and multilabel prediction with a novel multilabel focal loss function, outperforming existing methods.

TL;DR: This paper designs a Pair-Aware Representation module to predict potential relational entity pairs, which constrains the relation extraction to the predicted entity pairs subset rather than all pairs, and introduces a Entity-Enhanced representation module to assemble directional entity pairs and obtain a holistic understanding of the entire document.

TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.

TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.

TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.