Browsing by Author "Singh, Kuldeep"
Now showing 1 - 4 of 4
Results Per Page
- ItemEncoding Knowledge Graph Entity Aliases in Attentive Neural Network for Wikidata Entity Linking(Berlin ; Heidelberg : Springer, 2020) Mulang’, Isaiah Onando; Singh, Kuldeep; Vyas, Akhilesh; Shekarpour, Saeedeh; Vidal, Maria-Esther; Lehmann, Jens; Auer, Sören; Huang, Zhisheng; Beek, Wouter; Wang, Hua; Zhou, Rui; Zhang, YanchunThe collaborative knowledge graphs such as Wikidata excessively rely on the crowd to author the information. Since the crowd is not bound to a standard protocol for assigning entity titles, the knowledge graph is populated by non-standard, noisy, long or even sometimes awkward titles. The issue of long, implicit, and nonstandard entity representations is a challenge in Entity Linking (EL) approaches for gaining high precision and recall. Underlying KG in general is the source of target entities for EL approaches, however, it often contains other relevant information, such as aliases of entities (e.g., Obama and Barack Hussein Obama are aliases for the entity Barack Obama). EL models usually ignore such readily available entity attributes. In this paper, we examine the role of knowledge graph context on an attentive neural network approach for entity linking on Wikidata. Our approach contributes by exploiting the sufficient context from a KG as a source of background knowledge, which is then fed into the neural network. This approach demonstrates merit to address challenges associated with entity titles (multi-word, long, implicit, case-sensitive). Our experimental study shows ≈8% improvements over the baseline approach, and significantly outperform an end to end approach for Wikidata entity linking.
- ItemFalcon 2.0: An Entity and Relation Linking Tool over Wikidata(New York City, NY : Association for Computing Machinery, 2020) Sakor, Ahmad; Singh, Kuldeep; Patel, Anery; Vidal, Maria-EstherThe Natural Language Processing (NLP) community has significantly contributed to the solutions for entity and relation recognition from a natural language text, and possibly linking them to proper matches in Knowledge Graphs (KGs). Considering Wikidata as the background KG, there are still limited tools to link knowledge within the text to Wikidata. In this paper, we present Falcon 2.0, the first joint entity and relation linking tool over Wikidata. It receives a short natural language text in the English language and outputs a ranked list of entities and relations annotated with the proper candidates in Wikidata. The candidates are represented by their Internationalized Resource Identifier (IRI) in Wikidata. Falcon 2.0 resorts to the English language model for the recognition task (e.g., N-Gram tiling and N-Gram splitting), and then an optimization approach for the linking task. We have empirically studied the performance of Falcon 2.0 on Wikidata and concluded that it outperforms all the existing baselines. Falcon 2.0 is open source and can be reused by the community; all the required instructions of Falcon 2.0 are well-documented at our GitHub repository (https://github.com/SDM-TIB/falcon2.0). We also demonstrate an online API, which can be run without any technical expertise. Falcon 2.0 and its background knowledge bases are available as resources at https://labs.tib.eu/falcon/falcon2/.
- ItemInformation extraction pipelines for knowledge graphs(London : Springer, 2023) Jaradeh, Mohamad Yaser; Singh, Kuldeep; Stocker, Markus; Both, Andreas; Auer, SörenIn the last decade, a large number of knowledge graph (KG) completion approaches were proposed. Albeit effective, these efforts are disjoint, and their collective strengths and weaknesses in effective KG completion have not been studied in the literature. We extend Plumber, a framework that brings together the research community’s disjoint efforts on KG completion. We include more components into the architecture of Plumber to comprise 40 reusable components for various KG completion subtasks, such as coreference resolution, entity linking, and relation extraction. Using these components, Plumber dynamically generates suitable knowledge extraction pipelines and offers overall 432 distinct pipelines. We study the optimization problem of choosing optimal pipelines based on input sentences. To do so, we train a transformer-based classification model that extracts contextual embeddings from the input and finds an appropriate pipeline. We study the efficacy of Plumber for extracting the KG triples using standard datasets over three KGs: DBpedia, Wikidata, and Open Research Knowledge Graph. Our results demonstrate the effectiveness of Plumber in dynamically generating KG completion pipelines, outperforming all baselines agnostic of the underlying KG. Furthermore, we provide an analysis of collective failure cases, study the similarities and synergies among integrated components and discuss their limitations.
- ItemResorting to Context-Aware Background Knowledge for Unveiling Semantically Related Social Media Posts(New York, NY : IEEE, 2022) Sakor, Ahmad; Singh, Kuldeep; Vidal, Maria-EstherSocial media networks have become a prime source for sharing news, opinions, and research accomplishments in various domains, and hundreds of millions of posts are announced daily. Given this wealth of information in social media, finding related announcements has become a relevant task, particularly in trending news (e.g., COVID-19 or lung cancer). To facilitate the search of connected posts, social networks enable users to annotate their posts, e.g., with hashtags in tweets. Albeit effective, an annotation-based search is limited because results will only include the posts that share the same annotations. This paper focuses on retrieving context-related posts based on a specific topic, and presents PINYON, a knowledge-driven framework, that retrieves associated posts effectively. PINYON implements a two-fold pipeline. First, it encodes, in a graph, a CORPUS of posts and an input post; posts are annotated with entities for existing knowledge graphs and connected based on the similarity of their entities. In a decoding phase, the encoded graph is used to discover communities of related posts. We cast this problem into the Vertex Coloring Problem, where communities of similar posts include the posts annotated with entities colored with the same colors. Built on results reported in the graph theory, PINYON implements the decoding phase guided by a heuristic-based method that determines relatedness among posts based on contextual knowledge, and efficiently groups the most similar posts in the same communities. PINYON is empirically evaluated on various datasets and compared with state-of-the-art implementations of the decoding phase. The quality of the generated communities is also analyzed based on multiple metrics. The observed outcomes indicate that PINYON accurately identifies semantically related posts in different contexts. Moreover, the reported results put in perspective the impact of known properties about the optimality of existing heuristics for vertex graph coloring and their implications on PINYON scalability.