• Corpus ID: 3542854

TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution

  title={TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution},
  author={Prafulla Kumar Choubey and Ruihong Huang},
In this paper, we describe TAMU's system submitted to the TAC KBP 2017 event nugget detection and coreference resolution task. Our system builds on the statistical and empirical observations made on training and development data. We found that modifiers of event nuggets tend to have unique syntactic distribution. Their parts-of-speech tags and dependency relations provides them essential characteristics that are useful in identifying their span and also defining their types and realis status… 

NAI-SEA at SemEval-2018 Task 5: An Event Search System

Alibaba’s participating system in the semEval-2018 Task5: Counting Events and Participants in the Long Tail ranks first in all the three subtasks on document level retrieval, and it also ranks first on incident-level evaluation by RSME measure in subtask 3.

Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures

This paper explicitly model correlations between the main event chains of a document with topic transition sentences, inter-coreference chain correlations, event mention distributional characteristics and sub-event structure, and use them with scores obtained from a local coreference relation classifier for jointly resolving multiple event chains in a document.

Event Logic Graph Construction for Event Mining

An architecture for constructing Event Logic Graph is proposed, which includes text corpus collection, event relationship template construction, event extraction and structured representation, event similarity calculation and fusion, event trigger word extraction and argument extraction model construction, and event relationship pair construction, graph database storage.



CMU-LTI at KBP 2016 Event Nugget Track

The CMU LTI team’s participation in TAC KBP 2016 event nugget track is described, and their feature based English Nugget Detection and Coreference systems both rank number 2 among all the participants.

CMUML Micro-Reader System for KBP 2016 Cold Start Slot Filling, Event Nugget Detection, and Event Argument Linking

An overview of the CMUML’s Micro-Reader system for three TAC KBP tasks: Cold Start Slot Filling (SF), Event Nugget Detection and Coreference (EN); and Event Argument Extraction and Linking (EAL).

AIPHES-HD system at TAC KBP 2016: Neural Event Trigger Span Detection and Event Type and Realis Disambiguation with Word Embeddings

A simple but effective system which uses a Bi-Directional LSTM with embeddings short-cuts to the output for Event Trigger detection and simple Logistic Regression Classifiers with event trigger context features based on word embeddINGS for Event Type and Realis detection is implemented.

Event Nugget Detection Task : UMBC systems

This paper describes the Event Nugget Detection system that was submitted to the TAC KBP 2016 Event Track and its performance was low; the F1 measure was low.

Illinois CCG Entity Discovery and Linking, Event Nugget Detection and Co-reference, and Slot Filler Validation Systems for TAC 2016

The University of Illinois CCG team participated in three TAC 2016 tasks: Entity Discovery and Linking (EDL); Event Nugget Detection and Co-reference (ENDC); and Slot Filler Validation (SFV). The EDL

Overview of SYDNEY System for TAC KBP 2015 Event Nugget Detection

Developing experiments indicate that Brown cluster, Nomlex and WordNet features are complementary with more improvement from Word net features, and the contribution of features aimed at improving generalisation is explored.

Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task

The coreference resolution system submitted by Stanford at the CoNLL-2011 shared task was ranked first in both tracks, with a score of 57.8 in the closed track and 58.3 in the open track.

SoochowNLP Team System Description for 2016 KBP Slot Filling and Nugget Detection Tasks

The baseline is a pattern based search engine, which generate a query by using entity name and retrieves pseudo-relevant documents and determines them as reliable candidate fillers when meeting a predefined relation pattern.

Improving DISCERN with Deep Learning

IHMC designed and implemented two variants of an event-detection system that used manually created rules and another one that used rules learned using multiple deep neural networks, both of which were applied to two tasks in the NIST TAC KBP 2016 Event Track.

University of Washington TAC-KBP 2016 System Description

The University of Washington’s event extraction system was composed of three components: Evento, a CRFbased extractor, NomEvent, which makes use a lexicon to build features to identify nominal triggers, and NewsSpike, which uses an unsupervised training process to produce a highprecision extractor.