Position-aware Attention and Supervised Data Improve Slot Filling

Abstract

Organized relational knowledge in the form of "knowledge graphs" is important for many applications. However, the ability to populate knowledge bases with facts automatically extracted from documents has improved frustratingly slowly. This paper simultaneously addresses two issues that have held back prior work. We first propose an effective new model, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction. Then we build TACRED, a large (119,474 examples) supervised relation extraction dataset, obtained via crowdsourcing and targeted towards TAC KBP relations. The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance. When the model trained on this new dataset replaces the previous relation extraction component of the best TAC KBP 2015 slot filling system, its F 1 score increases markedly from 22.2% to 26.7%.

Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework

“…We first conduct experiments on the widely used benchmark data set Riedel (Riedel et al, 2010), and then on the TARCED (Zhang et al, 2017) data set. The latter allows us to control the noise level in the labels to observe the behavior and working mechanism of our proposed method.…”

Type-aware Convolutional Neural Networks for Slot Filling

“…In contrast to their work, we extend the convolutional neural network in this paper to not only doing relation classification but jointly learning to classify entities and relations. Recently, Zhang et al (2017) propose position-aware attention which calculates attention weights based on the current hidden state of their LSTM, the output state of the LSTM and the position embeddings which encode the distance of the current word to the two relation arguments. Moreover, they publish a supervised relation extraction dataset, obtained by crowdsourcing, for training slot filling relation classification models.…”

On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning

“…Note that there are many other variants of such models for RE in the literature Zhang et al, 2017;Verga et al, 2018). However, as our goal in this paper is to evaluate different pooling mechanisms for RE, we focus on these standard representation learning methods to avoid the confounding effect of the complicated models, thus better revealing the effectiveness of the pooling methods.…”

“…Due to its important applications on many areas of natural language processing (e.g., question answering, knowledge base construction), RE has been actively studied in the last decade, featuring a variety of feature-based or kernel-based models for this problem (Zelenko et al, 2002;Zhou et al, 2005;Bunescu and Mooney, 2005;Sun et al, 2011;Chan and Roth, 2010;Nguyen et al, 2009). Recently, the introduction of deep learning has produced a new generation of models for RE with the state-of-the-art performance on many different benchmark datasets (Zeng et al, 2014;dos Santos et al, 2015;Xu et al, 2015;Liu et al, 2015;Zhou et al, 2016;Wang et al, 2016;Zhang et al, 2017Zhang et al, , 2018b. The advantage of deep learning over the previous approaches for RE is the ability to automatically learn effective features for the sentences from data via various network architectures.…”