Effective Slot Filling Based on Shallow Distant Supervision Methods

Spoken Language Systems at Saarland University (LSV) participated this year with 5 runs at the TAC KBP English slot filling track. Effective algorithms for all parts of the pipeline, from document retrieval to relation prediction and response post-processing, are bundled in a modular end-to-end relation extraction system called RelationFactory. The main run solely focuses on shallow techniques and achieved significant improvements over LSV's last year's system, while using the same training data and patterns. Improvements mainly have been obtained by a feature representation focusing on surface skip n-grams and improved scoring for extracted distant supervision patterns. Important factors for effective extraction are the training and tuning scheme for distant supervision classifiers, and the query expansion by a translation model based on Wikipedia links. In the TAC KBP 2013 English Slotfilling evaluation, the submitted main run of the LSV RelationFactory system achieved the top-ranked F1-score of 37.3%.

• Publication year

  2014

• Venue

  Text Analysis Conference

• Publication date

  2014-01-06

• Fields of study

  Computer Science

• Identifiers
  arXiv 1401.1158
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A survey of noise reduction methods for distant supervision

  2013influential reference
• Combining Generative and Discriminative Model Scores for Distant Supervision

  2013cited by this paper
• New York University 2012 System for KBP Slot Filling

  2012cited by this paper
• PRIS at TAC2012 KBP Track

  2012cited by this paper
• Exploiting Syntactico-Semantic Structures for Relation Extraction

  2011cited by this paper
• A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters

  2010cited by this paper
• Cross-language retrieval using link-based language models

  2010cited by this paper
• Characterizing the Errors of Data-Driven Dependency Parsing Models

  2007cited by this paper
• Learning to Extract Relations from the Web using Minimal Supervision

  2007cited by this paper
• Supervised versus multiple instance learning: an empirical comparison

  2005cited by this paper
• Making large scale SVM learning practical

  1998cited by this paper

• FabricQA-Extractor: A Question Answering System to Extract Information from Documents using Natural Language Questions

  2024cites this paper
• Learning to Reason with a Scalable Probabilistic Logic

  2022cites this paper
• Building Knowledge Graphs and Recommender Systems for Suggesting Reskilling and Upskilling Options from the Web

  2022influential citation
• Incorporating Semantic Dependencies Extracted from Knowledge Graphs into Joint Inference Template-Based Information Extraction

  2020cites this paper
• Optimierung von Unternehmensbewertungen durch automatisierte Wissensidentifikation, -extraktion und -integration

  2020cites this paper
• Unsupervised and Supervised Learning of Complex Relation Instances Extraction in Natural Language

  2020cites this paper
• NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction

  2020cites this paper
• Name Variants for Improving Entity Discovery and Linking

  2019cites this paper
• Visual Segmentation for Information Extraction from Heterogeneous Visually Rich Documents

  2019cites this paper
• Neural Rule Grounding for Low-Resource Relation Extraction

  2019influential citation
• Type-aware Convolutional Neural Networks for Slot Filling

  2019cites this paper
• Neural Rule Grounding for Low-Resource Relation Extraction

  2019cites this paper
• Extracting and Representing Entities, Types, and Relations

  2019cites this paper
• Knowledge Base Population based on Entity Graph Analysis. (Peuplement d'une base de connaissance fondé sur l'exploitation d'un graphe d'entités)

  2018cites this paper
• Mining and Leveraging Background Knowledge for Improving Named Entity Linking

  2018cites this paper
• A Machine Learning Filter for the Slot Filling Task

  2018cites this paper
• Deep learning methods for knowledge base population

  2018cites this paper
• FrameIt: Ontology Discovery for Noisy User-Generated Text

  2018cites this paper
• Explainable Improved Ensembling for Natural Language and Vision

  2018cites this paper
• CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling

  2018cites this paper
• Unsupervised Slot Filler Refinement via Entity Community Construction

  2017cites this paper
• Constructing a Knowledge Base for Entertainment by Interlinking Multiple Data Sources

  2017cites this paper
• Unsupervised graph-based relation extraction and validation for knowledge base population

  2017influential citation
• A New Classification Framework to Evaluate the Entity Profiling on the Web

  2017influential citation
• Impact of Coreference Resolution on Slot Filling

  2017influential citation
• Low-rank regularization for high-dimensional sparse conjunctive feature spaces in information extraction

  2017cites this paper
• Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures

  2017cites this paper
• A Machine learning Filter for Relation Extraction

  2016cites this paper
• Stacking With Auxiliary Features: Improved Ensembling for Natural Language and Vision

  2016cites this paper
• NAIST Participation in the TAC KBP 2016 Cold Start Slot Filling Task: Combining CNN-based and Bootstrapping-based Methods

  2016cites this paper
• RPI BLENDER TAC-KBP2016 System Description

  2016cites this paper
• Towards Accurate Relation Extraction from Wikipedia

  2016cites this paper
• Unsupervised Person Slot Filling based on Graph Mining

  2016influential citation
• Comparing Convolutional Neural Networks to Traditional Models for Slot Filling

  2016influential citation
• The Semantic Web – ISWC 2016

  2016cites this paper
• Answer Extraction for Question Answering Game Application

  2016cites this paper
• Building and Exploring an Enterprise Knowledge Graph for Investment Analysis

  2016cites this paper
• Data mining for building knowledge bases: techniques, architectures and applications

  2016cites this paper
• Understanding Questions and Extracting Answers: Interactive Quiz Game Application Design

  2015cites this paper
• Biography-Dependent Collaborative Entity Archiving for Slot Filling

  2015cites this paper
• Joint Information Extraction and Reasoning: A Scalable Statistical Relational Learning Approach

  2015cites this paper
• Mining activation force defined dependency patterns for relation extraction

  2015cites this paper
• Detecting conditional healthiness of food items from natural language text

  2015cites this paper
• Building Knowledge Bases with Universal Schema: Cold Start and Slot-Filling Approaches

  2015cites this paper
• Knowledge base population using stacked ensembles of information extractors

  2015cites this paper
• Relation Extraction from Wikipedia Leveraging Intrinsic Patterns

  2015cites this paper
• Why Read if You Can Scan? Trigger Scoping Strategy for Biographical Fact Extraction

  2015cites this paper
• Bootstrapped Self Training for Knowledge Base Population

  2015influential citation
• Ghent University - IBCN Participation in the TAC KBP 2015 Cold Start Slot Filling task

  2015cites this paper
• Stacked Ensembles of Information Extractors for Knowledge-Base Population

  2015cites this paper
• Stacked Ensembles of Information Extractors for Knowledge-Base Population by Combining Supervised and Unsupervised Approaches

  2015cites this paper
• Effective distant supervision for end-to-end knowledge base population systems

  2014cites this paper
• Relation Extraction using Distant Supervision, SVMs, and Probabilistic First Order Logic

  2014cites this paper
• Researching persons & organizations: AWAKE: From text to an entity-centric knowledge base

  2014cites this paper
• Ghent University-IBCN participation in TAC-KBP 2014 slot filling and cold start tasks

  2014cites this paper
• RelationFactory: A Fast, Modular and Effective System for Knowledge Base Population

  2014cites this paper
• Analysing recall loss in named entity slot filling

  2014influential citation
• A Multi-strategy Learning Approach to Competitor Identification

  2014cites this paper
• Understanding questions and finding answers : semantic relation annotation to compute the Expected Answer Type

  2014influential citation
• University of Texas at Austin KBP 2013 Slot Filling System: Bayesian Logic Programs for Textual Inference

  2013influential citation