island99 / READ

own made slides NLP, KG, or others

READ

NLP, KG, or others

Knowledge graph embedding methods

time	meeting	year	author	title	describe
2019/7/21	ACL	2018	Boyang Ding et al.	Improving Knowledge Graph Embedding Using Simple Constraints	investigate a simple way to embed KG into continuous vector space using 1) non-negative constraints on entity representations and 2) approximate entailment constraints on relation representaions.
2019/7/26	ACL	2018	Chandrahas et al.	Towards Under standing the Geometry of Knowledge Graph Embeddings	Initiated a systematic study of analyzing geometry of various Knowledge Graph (KG) embedding methods.
2019/7/29	IJCAI	2018	Wei Qian et al.	Translating Embeddings for Knowledge Graph Completion with Relation Attention Mechanism	propose a translation-based embedding method to achieve attention mechanism, solving the failure of learning attention in previous work.

Knowledge graph application

time	meeting	year	author	title	describe
2019/7/23	ACL	2018	Zhenghao Liu et al.	Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval	EDRM, which introduces knowledge graphs to neural search systems,has more generalization by the semantics of KG.
2019/7/31	IJCAI	2018	Zhouxia Wang et al.	Deep Reasoning with Knowledge Graph for Social Relationship Understanding	utilizing knowledge graph, propose a neural network method with attention mechanism for the task of social relationship recognition.
2019/8/1	SIGIR	2018	Ying Shen et al.	Knowledge-aware Attentive Neural Network for Ranking Question Answer Pairs	propse a neural network KABLSTM for ranking QA pairs, which leverages external knowledge from KG and exploits an attention mechanism for interacting information from input texts and KG.
2019/8/5	IJCAI	2018	Mcuhao Chen et al.	Co-training Embeddings of Knowledge Graphs and Entity Descriptions	introduce a method of cross-lingual entity alignment which performs co-training of KG embedding model and description embedding model,showing that outperforms in experiments of cross-lingual entity alignment, zero-shot alignment and cross-lingual KG completion.
2019/8/8	SIGIR	2019	Xiaolu Lu et. al	Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs	present QUEST, an unsupervised method for QA over dynamically retrieved text corpora based on Group Steiner Trees, which builds a quasi KG before by SPO extraction to computing ranked answers using graph algorithm
2019/8/10	SIGIR	2019	Omar Alonso et al.	Social Knowledge Graph Explorer	Describe a knowledge graph explorer that allows users to query and discover relationships derived automatically from Twitter
2019/8/13	SIGIR	2019	Xiaoli Wang et al.	Effective Medical Archives Processing Using Knowledge Graphs	Present a medical archives processing framework KG-MDMF, using dictionary matching, extraction and expert Q&A system to construct KG, and define semantic measures to calculate similarity score, then do medical archives processing and classification improving.

Entity Linking

time	meeting	year	author	title	describe
2019/9/08	ACL	2018	Phong Le et al	Improving Entity Linking by Modeling Latent Relations between Mentions	treat relations as latent variables in NEL by compute pairwise score
2019/9/10	ACL	2018	Shikhar Murty et al	Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking	using real and complex bilinear mappings for integrating hierarchical information
2019/9/19	ACL	2019	Phong Le et al	Boosting Entity Linking Performance by Leveraging Unlabeled Documents	propose a weakly-supervised model which constructs a high recall list of candidate entities for each mention in unlabeled documents firstly, and use the candidate lists as weak supervision to constrain document-level entity linking model secondly.
2019/9/22	AAAI	2018	Jonathan Raiman et al	DeepType: Multilingual Entity Linking by Neural Type System Evolution	reformulating the design problem into a mixed integer problem: create a type system and subsequently train a neural network with it, and applied to EL and NER task

Other - Security

time	meeting	year	author	title	describe
2019/8/11	Engineering	2018	Yan Jia et al.	A Practical Approach to Constructing a Knowledge Graph for Cybersecurity	Builds an ontology for cybersecurity that is based on vulnerability, and puts forward a method to build a cybersecurity knowledge base.