Search Results for author:
Found 8 papers, 7 papers with code
A Fair and In-Depth Evaluation of Existing End-to-End Entity Linking Systems
We provide a more meaningful and fair in-depth evaluation of a variety of existing end-to-end entity linkers.
Efficient and Effective SPARQL Autocompletion on Very Large Knowledge Graphs
For existing SPARQL engines, these queries are impractically slow on large knowledge graphs.
ELEVANT: A Fully Automatic Fine-Grained Entity Linking Evaluation and Analysis Tool
We present Elevant, a tool for the fully automatic fine-grained evaluation of a set of entity linkers on a set of benchmarks.
Efficient SPARQL Autocompletion via SPARQL
We provide an extensive evaluation of a variety of suggestion methods on three large knowledge bases, including Wikidata (6. 9B triples).
Similarity Classification of Public Transit Stations
On all datasets, our learning-based approach achieves an F1 score of over 99%, while even the most elaborate baseline approach (based on TFIDF scores and the geographic distance) achieves an F1 score of at most 94%, and a naive approach of using a geographical distance threshold achieves an F1 score of only 75%.
Tokenization Repair in the Presence of Spelling Errors
We identify three key ingredients of high-quality tokenization repair, all missing from previous work: deep language models with a bidirectional component, training the models on text with spelling errors, and making use of the space information already present.
More Accurate Question Answering on Freebase
Real-world factoid or list questions often have a simple structure, yet are hard to match to facts in a given knowledge base due to high representational and linguistic variability.
Route Planning in Transportation Networks
We survey recent advances in algorithms for route planning in transportation networks.
Data Structures and Algorithms G.2.1; G.2.2; G.2.3; H.2.8; H.3.5; H.4.2
