Factor-based Compositional Embedding Models

By Mo Yu. 2014

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Bowen Zhou
2. Bing Xiang
3. Jie Zhou
4. C. D. Santos
5. Bruno Martins
6. Mohit Bansal
7. Wei Xu
8. Caiming Xiong

In Representation & Self-Supervised Learning

1. Bing Xiang
2. Bruno Martins
3. Bowen Zhou
4. Wei Xu
5. Mário J. Silva
6. Ralph Grishman
7. C. D. Santos
8. Thien Huu Nguyen

Citations in the corpus

• End-to-end learning of semantic role labeling using recurrent neural networks (2015, background): “There are various ways of obtaining good word representations (Mikolov et al., 2013; Col-lobert and Weston, 2008; Mnih and Kavukcuoglu, 2013; Yu et al., 2014).”
• Relation Classification via Multi-Level Attention CNNs (2016, unknown): “…and Harabagiu, 2010) 82.2 Dependency Methods RNN (Socher et al., 2012) 77.6 MVRNN (Socher et al., 2012) 82.4 FCM (Yu et al., 2014) 83.0 Hybrid FCM (Yu et al., 2014) 83.4 SDP-LSTM (Xu et al., 2015b) 83.7 DRNNs (Xu et al., 2016) 85.8 SPTree (Miwa and Bansal, 2016) 84.5 End-To-End Methods CNN+…”
• Bidirectional Long Short-Term Memory Networks for Relation Classification (2015, background): “FCM (Yu et al., 2014): They decompose the sentence into substructures, and extract features for each substructure.”
• Enriching Pre-trained Language Model with Entity Information for Relation Classification (2019, methodology): “There has been some work with deep learning methods for relation classification, such as (Socher et al., 2012; Zeng et al., 2014; Yu et al., 2014; dos Santos et al., 2015)”
• Relation Extraction: Perspective from Convolutional Neural Networks (2015, background): “For instance, the supervised features (dependency parse and name tagging) are crucial to FCM (Yu et al., 2014) to sig-nificantly improve its performance.”
• Classifying Relations by Ranking with Convolutional Neural Networks (2015, methodology): “Some recent work on relation classification has focused on the use of deep neural networks with the aim of reducing the number of handcrafted features (Socher et al., 2012; Zeng et al., 2014; Yu et al., 2014).”
• Semi-Supervised Bootstrapping of Relationship Extractors with Distributional Semantics (2015, background): “Finally, we could explore richer compositional functions, combining word embeddings with syntactic dependencies (SD) (Yu et al., 2014).”
• Relation Classification via Recurrent Neural Network (2015, methodology): “And there are other valuable models such as MV-RNN(Socher et al., 2012), CNN(Nguyen and Grishman, 2015), FCM(Yu et al., 2014).”