Filters








531 Hits in 3.4 sec

Nugget Proposal Networks for Chinese Event Detection [article]

Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun
2018 arXiv   pre-print
Then based on learned representations, trigger nuggets are proposed and categorized by exploiting character compositional structures of Chinese event triggers.  ...  In this paper, we propose Nugget Proposal Networks (NPNs), which can solve the word-trigger mismatch problem by directly proposing entire trigger nuggets centered at each character regardless of word boundaries  ...  Moreover, we sincerely thank all reviewers for their valuable comments.  ... 
arXiv:1805.00249v1 fatcat:chbgu3ewmvbm5fqugin4r324zm

Nugget Proposal Networks for Chinese Event Detection

Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Then based on learned representations, trigger nuggets are proposed and categorized by exploiting character compositional structures of Chinese event triggers.  ...  In this paper, we propose Nugget Proposal Networks (NPNs), which can solve the word-trigger mismatch problem by directly proposing entire trigger nuggets centered at each character regardless of word boundaries  ...  Moreover, we sincerely thank all reviewers for their valuable comments.  ... 
doi:10.18653/v1/p18-1145 dblp:conf/acl/SunHLL18a fatcat:4hs5i6pw3zf3hoorwjlulz4k5q

CMU-LTI at KBP 2016 Event Nugget Track

Zhengzhong Liu, Jun Araki, Teruko Mitamura, Eduard H. Hovy
2016 Text Analysis Conference  
We also conduct experiments using Neural Network based models for English event nugget detection, which can enable us building models that can be easily transfer to different languages.  ...  This year, we extend our feature based event detection and coreference systems to process also Chinese documents.  ...  Neural Network Models We also employ bidirectional Gated Recurrent Unit (GRU) for event nugget detection. GRU (Cho et al., 2014) is a type of recurrent neural networks (RNNs).  ... 
dblp:conf/tac/LiuAMH16 fatcat:o2jzfyvxk5fkfeekeypfgxewbe

Events Detection, Coreference and Sequencing: What's next? Overview of the TAC KBP 2017 Event Track

Teruko Mitamura, Zhengzhong Liu, Eduard H. Hovy
2017 Text Analysis Conference  
After two successful years of Event Nugget evaluation in the TAC KBP workshop, the third Event Nugget evaluation track for Knowledge Base Population(KBP) still attracts a lot of attention from the field  ...  In addition to the traditional event nugget and coreference tasks, we introduce a new event sequencing task in English.  ...  System Approaches As a general trend, many participants continue to use Neural Network (NN) based methods for event nugget detection.  ... 
dblp:conf/tac/MitamuraLH17 fatcat:pjjwytjm6jdtpkjjep4h727ovm

SRCB Entity Discovery and Linking (EDL) and Event Nugget Systems for TAC 2017

Shanshan Jiang, Yihan Li, Tianyi Qin, Qian Meng, Bin Dong
2017 Text Analysis Conference  
The Event Nugget Detection system identifies event nugget mentions and puts them into co-reference chains. We develop event nugget system based in English and Chinese.  ...  The SRCB team participated in Entity Discovery and Linking task and Event Nugget Detection task in TAC Knowledge Base Population (KBP) 2017.  ...  We participate in event nugget detection and coreference for both English and Chinese task.  ... 
dblp:conf/tac/JiangLQMD17 fatcat:6lp6ouvpuramfibrvkli5nj6oe

ISCAS_Sogou at TAC-KBP 2017

Xianpei Han, Xiliang Song, Hongyu Lin, Qichen Zhu, Yaojie Lu, Le Sun, Jingfang Xu, Mingrong Liu, Ranxu Su, Sheng Shang, Chenwei Ran, Feifei Xue
2017 Text Analysis Conference  
Our system consists of four components: Entity Discovery and Coreference, Relation Extraction, Event Extraction and BeSt Detection. We first briefly describe the architecture of our system.  ...  ISCAS_Sogou participated in the entire Chinese Coldstart task in TAC-KBP 2017. This paper describes our cold start knowledge base population system.  ...  Figure 3 shows the overall architecture of DMCNN used in Event Nugget Detection.  ... 
dblp:conf/tac/HanSLZLSXLSSRX17 fatcat:zcuqlq3jezgthnuznpzug355ay

RPI BLENDER TAC-KBP2016 System Description

Dian Yu, Xiaoman Pan, Boliang Zhang, Lifu Huang, Di Lu, Spencer Whitehead, Heng Ji
2016 Text Analysis Conference  
Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ...  , for multilingual (English, Spanish, Chinese) event nugget detection.  ...  We present the details of Bi-LSTM-CRF for event nugget detection in Figure 5 .  ... 
dblp:conf/tac/YuPZHLWJ16 fatcat:t3n32pldyfab7jvxiofnps24y4

Cost-sensitive Regularization for Label Confusion-aware Event Detection

Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Experiments on TAC-KBP 2017 datasets demonstrate that the proposed method can significantly improve the performances of different models in both English and Chinese event detection.  ...  In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type.  ...  Acknowledgments We sincerely thank the reviewers for their insightful comments and valuable suggestions.  ... 
doi:10.18653/v1/p19-1521 dblp:conf/acl/LinLHS19a fatcat:zxnlfhzrezcejdgq2sssvw6i7q

UZH at TAC KBP 2017: Event Nugget Detection via Joint Learning with Softmax-Margin Objective

Peter Makarov, Simon Clematide
2017 Text Analysis Conference  
This paper presents the CLUZH systems for the TAC KBP 2017 Event Nugget Detection Task. We submit three runs in all three languages: English, Spanish, and Chinese.  ...  Each system of the Run 3 ensemble is a jointly learned model that predicts all properties of the Event Nugget: its Span, Subtype, and Realis.  ...  Acknowledgements We would like to thank Luzia Roth and Tilia Ellendorff for their work. Peter Makarov has been supported by European Research Council Grant No. 338875.  ... 
dblp:conf/tac/MakarovC17 fatcat:sxpvgfjosjgzzpbkdvf7wkmwsa

RPI BLENDER TAC-KBP2015 System Description

Yu Hong, Di Lu, Dian Yu, Xiaoman Pan, Xiaobin Wang, Yadong Chen, Lifu Huang, Heng Ji
2015 Text Analysis Conference  
Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ...  We propose to implement a Case-Oriented Real-Time topic-event relation detection system (CORT for short). CORT fulfills a case study S(g,d) for each nugget g in a test document d.  ...  Analysis of New Methods for Event Nugget Detection We By contrast, FTL doesn't rely on rich homogeneous samples.  ... 
dblp:conf/tac/HongLYPHJHWC15 fatcat:x6xbtxnlunf77fikippeiwsbh4

Extracting Rich Semantic Information about Cybersecurity Events

Taneeya Satyapanich, Tim Finin, Francis Ferraro
2019 2019 IEEE International Conference on Big Data (Big Data)  
We argue that the event argument set considered here can support many other cybersecurity events, facilitating the extension to new cybersecurity event types, such as distributed denial of service and  ...  In this paper we describe how cybersecurity events can be described via semantic schemas, examined through an initial set of five event types.  ...  Partial support for this research was provided by a gift from the IBM AI Horizons Network.  ... 
doi:10.1109/bigdata47090.2019.9006444 dblp:conf/bigdataconf/SatyapanichFF19 fatcat:f3p2syu7sncglmopav2enumgri

Mining Sequential Update Summarization with Hierarchical Text Analysis

Chunyun Zhang, Zhongwei Si, Zhanyu Ma, Xiaoming Xi, Yilong Yin
2016 Mobile Information Systems  
Experimental results show that our proposed method has good performance.  ...  Mostly, news of these events shows characteristics that are early sparse and later redundant.  ...  Topic Detection and Tracking. Topic detection and tracking (TDT) refers to the document-level tasks which associated with detecting and tracking news events [23] .  ... 
doi:10.1155/2016/1340973 fatcat:muuovp4zjfarfhber73vjryscm

Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks

Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Specifically, we propose Anchor-Region Networks (ARNs), a sequence-to-nuggets architecture for nested mention detection.  ...  Experiments show that ARNs achieve the state-of-the-art performance on three standard nested entity mention detection benchmarks.  ...  Acknowledgments We sincerely thank the reviewers for their insightful comments and valuable suggestions.  ... 
doi:10.18653/v1/p19-1511 dblp:conf/acl/LinLHS19 fatcat:dyz4kz6bgbeodjj6rhfbxhsx6e

Accelerating Event Detection with DGCNN and FPGAs

Zhe Han, Jingfei Jiang, Linbo Qiao, Yong Dou, Jinwei Xu, Zhigang Kan
2020 Electronics  
We then proposed the first FPGA (Field Programmable Gate Array)-based event detection accelerator based on the proposed model.  ...  We replaced the Sigmoid function to make it more friendly for hardware computation without loss, and we quantized the network weights and activations to compress the network size.  ...  Conclusions In this paper, we analyzed the event detection task and proposed a hardware-friendly Chinese event detection model based on EE-DGCNN.  ... 
doi:10.3390/electronics9101666 fatcat:uoabndnjgfgf7ajwyozs33f47q

Event Detection with Trigger-Aware Lattice Neural Network

Ning Ding, Ziran Li, Zhiyuan Liu, Haitao Zheng, Zibo Lin
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Event detection (ED) aims to locate trigger words in raw text and then classify them into correct event types. In this task, neural network based models became mainstream in recent years.  ...  To address the two issues simultaneously, we propose the Trigger-aware Lattice Neural Network (TLNN). (1) The framework dynamically incorporates word and character information so that the trigger-word  ...  Lin et al. (2018) proposes the nugget proposal networks (NPN) in terms of this issue, which uses a neural network to model character compositional structure of trigger words in a fix-sized window.  ... 
doi:10.18653/v1/d19-1033 dblp:conf/emnlp/DingLLZL19 fatcat:gmc5c4sm5fdppaitxek7ve64jq
« Previous Showing results 1 — 15 out of 531 results