• Publications
  • Influence
ClausIE: clause-based open information extraction
TLDR
ClausIE is a novel, clause-based approach to open information extraction, which extracts relations and their arguments from natural language text using a small set of domain-independent lexica, operates sentence by sentence without any post-processing, and requires no training data. Expand
MinIE: Minimizing Facts in Open Information Extraction
TLDR
An experimental study with several real-world datasets found that MinIE achieves competitive or higher precision and recall than most prior systems, while at the same time producing shorter, semantically enriched extractions. Expand
FINET: Context-Aware Fine-Grained Named Entity Typing
TLDR
FINET generates candidate types using a sequence of multiple extractors, ranging from explicitly mentioned types to implicit types, and subsequently selects the most appropriate using ideas from word-sense disambiguation, and supports the most fine-grained type system so far. Expand
Facts That Matter
TLDR
This work introduces fact salience: The task of generating a machine-readable representation of the most prominent information in a text document as a set of facts as well as SalIE, the first fact salient system, which outperforms baselines and text summarizers showing that facts are an effective way to compress information. Expand
A Study of the Importance of External Knowledge in the Named Entity Recognition Task
TLDR
A novel modular framework that divides the knowledge into four categories according to the depth of knowledge they convey, which shows the effects on performance when incrementally adding deeper knowledge and discusses effectiveness/efficiency trade-offs. Expand
Fully Parallel Inference in Markov Logic Networks
TLDR
A parallel grounding algorithm is proposed that partitions the Markov logic network based on its corresponding join graph; each partition is ground independently and in parallel, and is well-suited to other, more efficient parallel inference techniques. Expand
Unsupervised Extraction of Market Moving Events with Neural Attention
TLDR
The authors' experiments suggest that there is an indication that the weights indeed skew the global set of events towards those categories that are more relevant to explain the price change; this effect reflects the performance of the network on stock prediction. Expand
CORE: Context-Aware Open Relation Extraction with Factorization Machines
TLDR
This work argues that integrating contextual information—such as metadata about extraction sources, lexical context, or type information—significantly improves prediction performance and proposes CORE, a novel matrix factorization model that leverages contextual information for open relation extraction. Expand
diaNED: Time-Aware Named Entity Disambiguation for Diachronic Corpora
TLDR
This paper presents the first time-aware method for NED that resolves ambiguities even when mention contexts give only few cues, based on computing temporal signatures for entities and comparing these to the temporal contexts of input mentions. Expand
Werdy: Recognition and Disambiguation of Verbs and Verb Phrases with Syntactic and Semantic Pruning
TLDR
Werdy is presented, a framework for WERD with particular focus on verbs and verbal phrases that identifies multi-word expressions based on the syntactic structure of the sentence and generates a list of candidate senses for each word or phrase using novel syntactic and semantic pruning techniques. Expand
...
1
2
...