36 citations · 86 across the 22 of their papers we have counts for
19 papers · 1 filter
DBLPLink: An Entity Linker for the DBLP Scholarly Knowledge Graph
Debayan Banerjee, Arefa, Ricardo Usbeck +1
In this work, we present a web application named DBLPLink, which performs entity linking over the DBLP scholarly knowledge graph. DBLPLink uses text-to-text pre-trained language mo…
Biomedical Entity Linking with Triple-aware Pre-Training
Xi Yan, Cedric Möller, Ricardo Usbeck
Linking biomedical entities is an essential aspect in biomedical natural language processing tasks, such as text mining and question answering. However, a difficulty of linking the…
The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck +1
In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing. We perform experiments within the the context of knowle…
GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck +1
In this work, we present an end-to-end Knowledge Graph Question Answering (KGQA) system named GETT-QA. GETT-QA uses T5, a popular text-to-text pre-trained language model. The model…
AmQA: Amharic Question Answering Dataset
Tilahun Abedissa, Ricardo Usbeck, Yaregal Assabie
Question Answering (QA) returns concise answers or answer lists from natural language text given a context document. Many resources go into curating QA datasets to advance robust m…
The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs
Angelie Kraft, Ricardo Usbeck
Knowledge graphs are increasingly used in a plethora of downstream tasks or in the augmentation of statistical models to improve factuality. However, social biases are engraved in…
Transformer with Tree-order Encoding for Neural Program Generation
Klaudia-Doris Thellmann, Bernhard Stadler, Ricardo Usbeck +1
While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicabi…
Knowledge Graph Question Answering Datasets and Their Generalizability: Are They Enough for Future Research?
Longquan Jiang, Ricardo Usbeck
Existing approaches on Question Answering over Knowledge Graphs (KGQA) have weak generalizability. That is often due to the standard i.i.d. assumption on the underlying dataset. Re…
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation
Md Rashad Al Hasan Rony, Ricardo Usbeck, Jens Lehmann
Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is pa…
RoMe: A Robust Metric for Evaluating Natural Language Generation
Md Rashad Al Hasan Rony, Liubov Kovriguina, Debanjan Chaudhuri +2
Evaluating Natural Language Generation (NLG) systems is a challenging task. Firstly, the metric should ensure that the generated hypothesis reflects the reference's semantics. Seco…
QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers
Aleksandr Perevalov, Dennis Diefenbach, Ricardo Usbeck +1
The ability to have the same experience for different user groups (i.e., accessibility) is one of the most important characteristics of Web-based systems. The same is true for Know…
Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisis
Aleksandr Perevalov, Xi Yan, Liubov Kovriguina +3
Data-driven systems need to be evaluated to establish trust in the scientific approach and its applicability. In particular, this is true for Knowledge Graph (KG) Question Answerin…
Semantic Answer Type and Relation Prediction Task (SMART 2021)
Nandana Mihindukulasooriya, Mohnish Dubey, Alfio Gliozzo +5
Each year the International Semantic Web Conference organizes a set of Semantic Web Challenges to establish competitions that will advance state-of-the-art solutions in some proble…
Survey on English Entity Linking on Wikidata
Cedric Möller, Jens Lehmann, Ricardo Usbeck
Wikidata is a frequently updated, community-driven, and multilingual knowledge graph. Hence, Wikidata is an attractive basis for Entity Linking, which is evident by the recent incr…
Towards an Interoperable Ecosystem of AI and LT Platforms: A Roadmap for the Implementation of Different Levels of Interoperability
Georg Rehm, Dimitrios Galanis, Penny Labropoulou +21
With regard to the wider area of AI/LT platform interoperability, we concentrate on two core aspects: (1) cross-platform search and discovery of resources and services; (2) composi…
Template-based Question Answering using Recursive Neural Networks
Ram G Athreya, Srividya Bansal, Axel-Cyrille Ngonga Ngomo +1
We propose a neural network-based approach to automatically learn and classify natural language questions into its corresponding template using recursive neural networks. An obviou…
Entity Linking in 40 Languages using MAG
Diego Moussallem, Ricardo Usbeck, Michael Röder +1
A plethora of Entity Linking (EL) approaches has recently been developed. While many claim to be multilingual, the MAG (Multilingual AGDISTIS) approach has been shown recently to o…
BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking
Axel-Cyrille Ngonga Ngomo, Michael Röder, Diego Moussallem +2
The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain…
MAG: A Multilingual, Knowledge-base Agnostic and Deterministic Entity Linking Approach
Diego Moussallem, Ricardo Usbeck, Michael Röder +1
Entity linking has recently been the subject of a significant body of research. Currently, the best performing approaches rely on trained mono-lingual models. Porting these approac…