• Publications
  • Influence
YAGO2: exploring and querying world knowledge in time, space, context, and many languages
tl;dr
We present YAGO2, an extension of the YAGOA knowledge base with focus on temporal and spatial knowledge. Expand
  • 293
  • 51
  • Open Access
Relation Classification via Multi-Level Attention CNNs
tl;dr
We propose a novel convolutional neural network architecture for relation classification, relying on two levels of attention in order to better discern patterns in heterogeneous contexts. Expand
  • 225
  • 27
  • Open Access
MENTA: inducing multilingual taxonomies from wikipedia
tl;dr
We use linking heuristics to discover potential taxonomic relationships, graph partitioning to form consistent equivalence classes of entities, and a Markov chain-based ranking approach to construct the final taxonomy. Expand
  • 100
  • 10
  • Open Access
Structured Learning for Taxonomy Induction with Belief Propagation
tl;dr
We present a structured learning approach to inducing hypernym taxonomies using a probabilistic graphical model formulation and a directed spanning tree algorithm for the core hypernymy factor. Expand
  • 45
  • 10
  • Open Access
WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation
tl;dr
We present a system based on a series of algorithms to distill fine-grained disambiguated commonsense knowledge from massive amounts of text. Expand
  • 37
  • 10
  • Open Access
LINDA: distributed web-of-data-scale entity matching
tl;dr
In this paper, we formalize the task of automatically creating "sameAs" links across Linked Data sources in a globally consistent manner. Expand
  • 78
  • 9
  • Open Access
PACRR: A Position-Aware Neural IR Model for Relevance Matching
tl;dr
In order to adopt deep learning for information retrieval, models are needed that can capture all relevant information required to assess the relevance of a document to a query. Expand
  • 60
  • 9
  • Open Access
Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
tl;dr
We propose a purely attention based local feature integration framework based on attention clusters, and introduce a shifting operation to capture more diverse signals. Expand
  • 102
  • 8
  • Open Access
WebChild: harvesting and organizing commonsense knowledge from the web
tl;dr
This paper presents a method for automatically constructing a large commonsense knowledge base, called WebChild, from Web contents. Expand
  • 92
  • 8
  • Open Access
Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval
tl;dr
In this work, we highlight three potential shortcomings caused by not considering context information and propose three neural ingredients to address them: a disambiguation component, cascade k-max pooling, and shuffling combination layer. Expand
  • 51
  • 8
  • Open Access