Search Results for author: Adrian Ulges

Found 10 papers, 6 papers with code

Relation Specific Transformations for Open World Knowledge Graph Completion

1 code implementation COLING (TextGraphs) 2020 Haseeb Shah, Johannes Villmow, Adrian Ulges

We propose an open-world knowledge graph completion model that can be combined with common closed-world approaches (such as ComplEx) and enhance them to exploit text-based representations for entities unseen in training.

Knowledge Graph Completion Link Prediction

ConTest: A Unit Test Completion Benchmark featuring Context

no code implementations ACL (NLP4Prog) 2021 Johannes Villmow, Jonas Depoix, Adrian Ulges

We introduce CONTEST, a benchmark for NLP-based unit test completion, the task of predicting a test’s assert statements given its setup and focal method, i. e. the method to be tested.

IRT2: Inductive Linking and Ranking in Knowledge Graphs of Varying Scale

1 code implementation2 Jan 2023 Felix Hamann, Adrian Ulges, Maurice Falk

Our focus is on inductive link prediction models as a basis for practical tools that support knowledge engineers with exploring text collections and discovering and linking new (so-called open-world) entities to the knowledge graph.

Inductive Link Prediction Knowledge Graphs

ManyEnt: A Dataset for Few-shot Entity Typing

1 code implementation COLING 2020 Markus Eberts, Kevin Pech, Adrian Ulges

We introduce ManyEnt, a benchmark for entity typing models in few-shot scenarios.

Entity Typing

Neural Entity Linking on Technical Service Tickets

no code implementations15 May 2020 Nadja Kurz, Felix Hamann, Adrian Ulges

Entity linking, the task of mapping textual mentions to known entities, has recently been tackled using contextualized neural networks.

Entity Linking Transfer Learning

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

2 code implementations17 Sep 2019 Markus Eberts, Adrian Ulges

The model is trained using strong within-sentence negative samples, which are efficiently extracted in a single BERT pass.

 Ranked #1 on Joint Entity and Relation Extraction on SciERC (Cross Sentence metric)

Joint Entity and Relation Extraction Named Entity Recognition (NER) +1

Hamming Sentence Embeddings for Information Retrieval

no code implementations15 Aug 2019 Felix Hamann, Nadja Kurz, Adrian Ulges

In retrieval applications, binary hashes are known to offer significant improvements in terms of both memory and speed.

Information Retrieval Retrieval +3

An Open-World Extension to Knowledge Graph Completion Models

1 code implementation19 Jun 2019 Haseeb Shah, Johannes Villmow, Adrian Ulges, Ulrich Schwanecke, Faisal Shafait

We present a novel extension to embedding-based knowledge graph completion models which enables them to perform open-world link prediction, i. e. to predict facts for entities unseen in training based on their textual description.

Knowledge Graph Completion Link Prediction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.