Knowledge Graphs, Information Extraction and Knowledge-aware NLP @ACL20
Here lists papers and quick notes about knowledge graphs, information extraction, and knowledge-aware NLP applications that appear in the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020). Knowledge graph embedding and completion are still hot topics. Named entity recognition is the most extensively studied topic in this year’s ACL conference, with 17 papers accepted. Knowledge-aware or knowledge-guided applications such as sentiment analysis and text generation are also exciting directions.
Knowledge Graph Embedding
Low-Dimensional Hyperbolic Knowledge Graph Embeddings Ines Chami, Adva Wolf, Da-Cheng Juan, Frederic Sala, Sujith Ravi and Christopher Ré [Paper] [Code]
hyperbolic embedding for high-fidelity and parsimonious representations;
simultaneously capture hierarchical and logical patterns;
hyperbolic reflections and rotations with attention to model complex relational patterns
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding. Yun Tang, Jing Huang, Guangtao Wang, Xiaodong He and Bowen Zhou [Paper]
extend the RotatE from 2D complex domain to high dimensional space with orthogonal transforms;
graph context is integrated into distance scoring functions
SEEK: Segmented Embedding of Knowledge Graphs Wentao Xu, Shun Zheng, Liang He, Bin Shao, Jian Yin, Tie-Yan Liu. [Paper] [Code]
lightweight modeling framework
1) facilitating sufficient feature interactions;
2) preserving both symmetry and antisymmetry properties of relations.
ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding Zhiwen Xie, Guangyou Zhou, Jin Liu and Jimmy Xiangji Huang. [Paper]
Inception network to learn query embedding, aiming to increase the interaction between head and relation embeddings;
a relation-aware attention mechanism to enrich the query embedding with the local neighborhood and global entity information
Knowledge Graph Embedding Compression Mrinmaya Sachan. [Paper]
compresses the KG embedding layer by representing each entity in the KG as a vector of discrete codes and then composes the embeddings from these codes
Knowledge Graph Completion
NeuInfer: Knowledge Inference on N-ary Facts Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang and Xueqi Cheng. [Paper]
represent each n-ary fact as a primary triple coupled with a set of its auxiliary descriptive attribute-value pair(s)
Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction Samuel Broscheit, Kiril Gashteovski, Yanjie Wang and Rainer Gemulla. [Paper]
open knowledge graph, a benchmark for open link prediction: OLPBENCH
A Re-evaluation of Knowledge Graph Completion Methods Zhiqing Sun, Shikhar Vashishth, Soumya Sanyal, Partha Talukdar and Yiming Yang. [Paper]
an evaluation protocol for handling bias in the model
Relation Extraction
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian and Yi Chang. [Paper] [Code]
models relations as functions that map subjects to objects in a sentence
Dialogue-Based Relation Extraction Dian Yu, Kai Sun, Claire Cardie and Dong Yu. [Paper] [Code+data]
the first human-annotated dialogue-based relation extraction dataset DialogRE;
a new metric
Exploiting the Syntax-Model Consistency for Neural Relation Extraction Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou and Thien Huu Nguyen. [Paper]
uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization.
Probing Linguistic Features of Sentence-Level Representations in Relation Extraction Christoph Alt, Aleksandra Gabryszak and Leonhard Hennig [Paper]
14 probing tasks specifically focused on linguistic properties relevant to relation extraction four encoder architectures
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction Guoshun Nan, Zhijiang Guo, Ivan Sekulic and Wei Lu [Paper]
empowers the relational reasoning across sentences by automatically inducing the latent document-level graph;
a refinement strategy, which enables the model to incrementally aggregate relevant information for multi-hop reasoning
Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents Daoyuan Chen, Yaliang Li, Kai Lei and Ying Shen [Paper]
consider the problem of shifted label distribution;
jointly extract entity and relation through a group of cooperative multiagents
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task Christoph Alt, Aleksandra Gabryszak and Leonhard Hennig [Paper]
Towards Understanding Gender Bias in Relation Extraction Andrew Gaut, Tony Sun, Shirlyn Tang, Yuxin Huang, Jing Qian, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang and William Yang Wang. [Paper]
Relation Extraction with Explanation Hamed Shahbazi, Xiaoli Fern, Reza Ghaeini and Prasad Tadepalli. [Paper]
Named Entity Recognition
A Unified MRC Framework for Named Entity Recognition Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu and Jiwei Li [Paper] [Code]
formulate NER as a machine reading comprehension task
An Effective Transition-based Model for Discontinuous NER Xiang Dai, Sarvnaz Karimi, Ben Hachey and Cecile Paris. [Paper]
a simple, effective transition-based model with generic neural encoding for discontinuous NER.
Bipartite Flat-Graph Network for Nested Named Entity Recognition Ying Luo and Hai Zhao [Paper]
BiLSTM + GCN to learn flat entities and their inner dependencies
Code and Named Entity Recognition in StackOverflow Jeniya Tabassum, Mounica Maddela, Wei Xu and Alan Ritter [Paper]
Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer Jianfei Yu, Jing Jiang, Li Yang and Rui Xia. [Paper]
Multi-Cell Compositional LSTM for NER Domain Adaptation Chen Jia and Yue Zhang. [Paper]
Named Entity Recognition without Labelled Data: A Weak Supervision Approach Pierre Lison, Jeremy Barnes, Aliaksandr Hubin and Samia Touileb [Paper]
a broad spectrum of labelling functions to automatically annotate texts from the target domain;
a hidden Markov model which captures the varying accuracies and confusions of the labelling functions
Simplify the Usage of Lexicon in Chinese NER Ruotian Ma, Minlong Peng, Qi Zhang, Zhongyu Wei and Xuanjing Huang [Paper]
Use Lexicon for Chinese NER as simply as possible
Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language Qianhui Wu, Zijia Lin, Börje Karlsson, Jian-Guang Lou and Biqing Huang [Paper]
Sources of Transfer in Multilingual Named Entity Recognition David Mueller, Nicholas Andrews and Mark Dredze [Paper]
Temporally-Informed Analysis of Named Entity Recognition Shruti Rijhwani and Daniel Preotiuc-Pietro. [Paper]
FLAT: Chinese NER Using Flat-Lattice Transformer Xiaonan Li, Hang Yan, Xipeng Qiu and Xuanjing Huang [Paper]
Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling Canasai Kruengkrai, Thien Hai Nguyen, Sharifah Mahani Aljunied and Lidong Bing. [Paper]
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno and Kentaro Inui [Paper]
Named Entity Recognition as Dependency Parsing Juntao Yu, Bernd Bohnet and Massimo Poesio. [Paper]
Soft Gazetteers for Low-Resource Named Entity Recognition Shruti Rijhwani, Shuyan Zhou, Graham Neubig and Jaime Carbonell. [Paper]
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition Bill Yuchen Lin, Dong-Ho Lee, Ming Shen, Ryan Moreno, Xiao Huang, Prashant Shiralkar and Xiang Ren. [Paper]
Entity Typing
Hierarchical Entity Typing via Multi-level Learning to Rank ACL 2020. Chen et al. [Paper]
hierarchical entity classification; training: multi-level learning-to-rank loss; prediction: coarse-to-fine decoder
Connecting Embeddings for Knowledge Graph Entity Typing Yu Zhao, Anxiang zhang, Ruobing Xie, Kang Liu and Xiaojie WANG. [Paper]
Entity Linking
From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains Jan-Christoph Klie, Richard Eckart de Castilho and Iryna Gurevych. [Paper]
Improving Entity Linking through Semantic Reinforced Entity Embeddings Feng Hou, Ruili Wang, Jun He and Yi Zhou. [Paper]
Entity Alignment
Neighborhood Matching Network for Entity Alignment Yuting Wu, Xiao Liu, Yansong Feng, Zheng Wang and Dongyan Zhao [Paper]
Information Extraction
A Joint Neural Model for Information Extraction with Global Features Ying Lin, Heng Ji, Fei Huang and Lingfei Wu [Paper]
extract the globally optimal IE result as a graph from an input sentence.
IMoJIE: Iterative Memory-Based Joint Open Information Extraction Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam and Soumen Chakrabarti [Paper]
an extension to CopyAttention; produces the next extraction conditioned on all previously extracted tuples
TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories Giannis Karamanolakis, Jun Ma and Xin Luna Dong. [Paper]
Improving Event Detection via Open-domain Trigger Knowledge Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li and Jun Xie. [Paper]
Knowledge-aware Applications
Question Answering
Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings. Apoorv Saxena, Aditay Tripathi and Partha Talukdar [Paper] [Code]
Sentiment Analysis
KinGDOM: Knowledge-Guided DOMain adaptation for sentiment analysis Deepanway Ghosal, Devamanyu Hazarika, Abhinaba Roy, Navonil Majumder, Rada Mihalcea and Soujanya Poria. [Paper]
Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion Knowledge Bowen Zhang, Min Yang, Xutao Li, Yunming Ye, Xiaofei Xu and Kuai Dai. [Paper]
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis Hao Tian, Can Gao, Xinyan Xiao, Hao Liu, Bolei He, Hua Wu, Haifeng Wang and Feng Wu. [Paper]
Generation
Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy Xiexiong Lin, Weiyu Jian, Jianshan He, Taifeng Wang and Wei Chu. [Paper]
Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs Houyu Zhang, Zhenghao Liu, Chenyan Xiong and Zhiyuan Liu. [Paper] [Code]
Semantic Graphs for Generating Deep Questions Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua and Min-Yen Kan [Paper] [Code]
Incorporating External Knowledge through Pre-training for Natural Language to Code Generation Frank F. Xu, Zhengbao Jiang, Pengcheng Yin, Bogdan Vasilescu and Graham Neubig. [Paper] [Code]
Dataset
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang and Xiaoyan Zhu [Paper] [Code+Data]
SciREX: A Challenge Dataset for Document-Level Information Extraction Sarthak Jain, Madeleine van Zuylen, Hannaneh Hajishirzi and Iz Beltagy [Paper] [Data+Code]
Please check out our recent survey for more literature about knowledge graphs.
A Survey on Knowledge Graphs: Representation, Acquisition and Applications. Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and Philip S Yu. arXiv preprint arXiv:2002.00388, 2020.