Improving efficiency and accuracy in multilingual entity extraction

By Joachim Daiber, Max Jakob, Chris Hokamp, Pablo N. Mendes. 2013

590 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

Citations in the corpus

Knowledge Enhanced Contextual Word Representations (2019, methodology): “, 2011) and DBpedia Spotlight (Daiber et al., 2013).”
TGIF: A New Dataset and Benchmark on Animated GIF Description (2016, background): “We do the following checks: The sentence (1) contains at least 8, but no more than 25 words (white space separated); (2) contains only ASCII characters; (3) does not contain profanity (checked by keyword matching); (4) should be typed, not copy/pasted (checked by disabling copy/paste on the task pag”
Learning from Noisy Labels with Distillation (2017, methodology): “DBpedia Spotlight takes many text-related factors into consideration, such as synonyms and text morphological transformations.”
Semantic Web in data mining and knowledge discovery: A comprehensive survey (2016, methodology): “For unstructured data, i.e., textual contents, the interlinking is typically done by linking named entities in the text to LOD sources with tools such as DBpedia Spotlight.”
Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “A large number of KGs, such as Freebase [1], DBpedia [2], YAGO [3], and NELL [4], have been created and successfully applied to many real-world applications, from semantic parsing [5], [6] and named entity disambiguation [7], [8], to information extraction [9], [10] and question answering [11], [12]”
Entity Linking meets Word Sense Disambiguation: a Unified Approach (2014, background): “This problem becomes even more accentuated in the latest version of this system (Daiber et al., 2013).”
emrQA: A Large Corpus for Question Answering on Electronic Medical Records (2018, methodology): “The text span of country=France from the Wikipedia passage is then used as the answer (Daiber et al., 2013).”
Broad-Coverage Semantic Parsing as Transduction (2019, methodology): “Our transducer at each decoding time step looks for the source node from the preceding nodes, which ensures that the output of a greedy search is already a valid arborescence ˆ Y : Therefore, a MST algorithm such as the Chu-Liu-Edmonds algorithm at O ( EV ) used in Zhang et al. (2019) 5 Data Pre-and”
Towards Knowledge-Based Recommender Dialog System (2019, unknown): “2 We then perform entity linking (Daiber et al., 2013) on dialog contents and thus informative non-item entities appearing in dialog contents are matched to E .”
GERBIL - Benchmarking Named Entity Recognition and Linking consistently (2017, methodology): “DBpedia Spotlight: One of the first semantic approaches [15] was published in 2011, combining NER and NED approaches based on DBpedia.”
Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples (2017, methodology): “In this setup, all the entities that have been annotated in the text with DBpedia Spotlight are replaced with their respective URIs.”
Edina: Building an Open Domain Socialbot with Self-dialogues (2017, methodology): “The second NER is performed using DBpedia Spotlight API [Daiber et al., 2013] which extracts more information on the named entities from Wikipedia.”
Core techniques of question answering systems over knowledge bases: a survey (2017, unknown): “These are DBpedia Spotlight [21] and AIDA [91].”
Video Question Answering with Spatio-Temporal Reasoning (2019, methodology): “We detect proper nouns (e.g., person names, body parts, animal names, etc.) in the collected answers using the DBpedia Spotlight (Daiber et al. 2013) and replace them with the corresponding common noun.”
End-to-End Neural Entity Linking (2018, background): “Until recently, the common approach of popular systems (Ceccarelli et al., 2013; van Erp et al., 2013; Piccinno and Ferragina, 2014; Daiber et al., 2013; Hoffart et al., 2011; Steinmetz and Sack, 2013) was to solve these two sub-problems independently.”
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph (2019, methodology): “Thus, we adopt entity linking algorithm [6] to find the related entities of an item from its title, brand, and description in the shopping website.”