10.1節 はじめに
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition | Jurafsky and Martin | 2000 | amazon | 1 |
| Abstract Meaning Representation for Sembanking | Banarescu et al | 2013 | 2 | |
| Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling | Marcheggiani and Titov | 2017 | arxiv | 3 |
| Question Answering by Reasoning Across Documents with Graph Convolutional Networks | De Cao et al | 2019 | arxiv | 4 |
| BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering | Cao et al | 2019 | arxiv | 5 |
| Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks | Song et al | 2018a | arxiv | 6 |
| Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs | Tu et al | 2019 | arxiv | 7 |
| Graph Convolution over Pruned Dependency Trees Improves Relation Extraction | Zhang et al | 2018c | arxiv | 8 |
| GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction | Fu et al | 2019 | リンク | 9 |
| Attention Guided Graph Convolutional Networks for Relation Extraction | Guo et al | 2019 | arxiv | 10 |
| Graph Neural Networks with Generated Parameters for Relation Extraction | Zhu et al | 2019b | リンク | 11 |
| Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network | Sahu et al | 2019 | arxiv | 12 |
| Joint Type Inference on Entities and Relations via Graph Convolutional Networks | Sun et al | 2019a | リンク | 13 |
| Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks | Zhang et al | 2019d | arxiv | 14 |
| Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks | Marcheggiani et al | 2018 | arxiv | 15 |
| Graph-to-Sequence Learning using Gated Graph Neural Networks | Beck et al | 2018 | arxiv | 16 |
| Structural Neural Encoders for AMR-to-text Generation | Cohen | 2019 | arxiv | 17 |
| A Graph-to-Sequence Model for AMR-to-Text Generation | Song et al | 2018b | arxiv | 18 |
| Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks | Xu et al | 2018b | arxiv | 19 |
| Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach | Hamaguchi et al | 2017 | arxiv | 20 |
| Modeling Relational Data with Graph Convolutional Networks | Schlichtkrull et al | 2018 | arxiv | 21 |
| Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs | Nathani et al | 2019 | arxiv | 22 |
| End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion | Shang et al | 2019a | arxiv | 23 |
| Knowledge Graph Convolutional Networks for Recommender Systems | Wang et al | 2019c | arxiv | 24 |
| Graph Wavelet Neural Network | Xu et al | 2019a | arxiv | 25 |
10.2節 意味役割のラベリング（SRL）
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling | Marcheggiani and Titov | 2017 | arxiv | 1 |
| A Primer on Neural Network Models for Natural Language Processing | Goldberg | 2016 | arxiv | 2 |
10.3節 ニューラル機械翻訳
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Neural Machine Translation by Jointly Learning to Align and Translate | Bahdanau et al | 2014 | arxiv | 1 |
| Attention Is All You Need | Vaswani et al | 2017 | arxiv | 2 |
| BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | Devlin et al | 2018 | arxiv | 3 |
| Improving Language Understanding by Generative Pre-Training | Radford et al | 2018 | リンク | 4 |
| Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks | Marcheggiani et al | 2018 | arxiv | 5 |
| Graph Convolutional Encoders for Syntax-aware Neural Machine Translation | Bastings et al | 2017 | arxiv | 6 |
10.4節 関係抽出
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Graph Convolution over Pruned Dependency Trees Improves Relation Extraction | Zhang et al | 2018c | arxiv | 1 |
| GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction | Fu et al | 2019 | リンク | 2 |
| Attention Guided Graph Convolutional Networks for Relation Extraction | Guo et al | 2019 | arxiv | 3 |
| Graph Neural Networks with Generated Parameters for Relation Extraction | Zhu et al | 2019b | リンク | 4 |
| Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network | Sahu et al | 2019 | arxiv | 5 |
| Joint Type Inference on Entities and Relations via Graph Convolutional Networks | Sun et al | 2019a | リンク | 6 |
| Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks | Zhang et al | 2019d | arxiv | 7 |
| Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling | Marcheggiani and Titov | 2017 | arxiv | 8 |
10.5節 質問応答(QA)
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Question Answering by Reasoning Across Documents with Graph Convolutional Networks | De Cao et al | 2019 | arxiv | 1 |
| BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering | Cao et al | 2019 | arxiv | 2 |
| Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks | Song et al | 2018a | arxiv | 3 |
| Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs | Tu et al | 2019 | arxiv | 4 |
| Constructing Datasets for Multi-hop Reading Comprehension Across Documents | Welbl et al | 2018 | arxiv | 5 |
| End-to-end Neural Coreference Resolution | Lee et al | 2017 | arxiv | 6 |
| Attention Is All You Need | Vaswani et al | 2017 | arxiv | 7 |
| Deep contextualized word representations | Peters et al | 2018 | arxiv | 8 |
10.6節 Graph-to-Sequence学習
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Neural Machine Translation by Jointly Learning to Align and Translate | Bahdanau et al | 2014 | arxiv | 1 |
| AMR-to-text Generation with Synchronous Node Replacement Grammar | Song et al | 2017 | arxiv | 2 |
| Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks | Marcheggiani et al | 2018 | arxiv | 3 |
| Graph-to-Sequence Learning using Gated Graph Neural Networks | Beck et al | 2018 | arxiv | 4 |
| Structural Neural Encoders for AMR-to-text Generation | Cohen | 2019 | arxiv | 5 |
| A Graph-to-Sequence Model for AMR-to-Text Generation | Song et al | 2018b | arxiv | 6 |
| Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling | Marcheggiani and Titov | 2017 | arxiv | 7 |
| Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks | Xu et al | 2018b | arxiv | 8 |
10.7節 知識グラフ上のGNN
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach | Hamaguchi et al | 2017 | arxiv | 1 |
| Modeling Relational Data with Graph Convolutional Networks | Schlichtkrull et al | 2018 | arxiv | 2 |
| Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs | Nathani et al | 2019 | arxiv | 3 |
| End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion | Shang et al | 2019a | arxiv | 4 |
| Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding | Wang et al | 2019f | arxiv | 5 |
| Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks | Park et al | 2019 | arxiv | 6 |
| OAG: Toward Linking Large-scale Heterogeneous Entity Graphs | Zhang et al | 2019b | リンク | 7 |
| Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks | Wang et al | 2018c | リンク | 8 |
| Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network | Xu et al | 2019e | arxiv | 9 |
| Composition-based Multi-Relational Graph Convolutional Networks | Vashishth et al | 2019 | arxiv | 10 |
| Learning Multi-Relational Semantics Using Neural-Embedding Models | Yang et al | 2014 | arxiv | 11 |
10.9節 参考文献
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures | Miwa and Bansal | 2016 | arxiv | 1 |
| N-ary Relation Extraction using Graph State LSTM | Song et al | 2018c | arxiv | 2 |
| Abusive Language Detection with Graph Convolutional Networks | Mishra et al | 2019 | arxiv | 3 |
| Structured Neural Summarization | Fernandes et al | 2018 | arxiv | 4 |
| Attention Is All You Need | Vaswani et al | 2017 | arxiv | 5 |
| BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | Devlin et al | 2018 | arxiv | 6 |