Results 31 to 40 of about 833 (102)
Embedded Topic Models Enhanced by Wikification
Proceedings of the First Workshop on Advancing Natural Language Processing for WikipediaTopic modeling analyzes a collection of documents to learn meaningful patterns of words. However, previous topic models consider only the spelling of words and do not take into consideration the homography of words. In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities. We evaluate our method
Shibuya, Takashi, Utsuro, Takehito
openaire +2 more sources
WikifyMe: Creating Testbed for Wikifiers
Труды Института системного программирования РАН, 2018 Finding relationships between words in text and articles from Wikipedia is an extremely popular task known as wikification. However there is still no gold standard corpus for wikifiers comparison.
Sergey Bartunov +2 more
doaj
Automatic Accuracy Prediction for AMR Parsing
, 2019 Meaning Representation (AMR) represents sentences as directed, acyclic and rooted graphs, aiming at capturing their meaning in a machine readable format. AMR parsing converts natural language sentences into such graphs.
Frank, Anette, Opitz, Juri
core +1 more source
Evaluating Scoped Meaning Representations [PDF]
, 2018 Semantic parsing offers many opportunities to improve natural language understanding. We present a semantically annotated parallel corpus for English, German, Italian, and Dutch where sentences are aligned with scoped meaning representations in order to ...
Abzianidze, Lasha +3 more
core +2 more sources
Wikification of learning objects using metadata as an alternative context for disambiguation [PDF]
, 2014 We present a methodology to wikify learning objects. Our proposal is focused on two processes: word sense disambiguation and relevant phrase selection. The disambiguation process involves the use of the learning objects metadata as either additional or ...
GELBUKH, ALEXANDER +11 more
core
TripleSent: a triple store of events associated with their prototypical sentiment [PDF]
, 2016 The current generation of sentiment analysis systems is limited in their real-world applicability because they cannot detect utterances that implicitly carry positive or negative sentiment.
Desmet, Bart +3 more
core +1 more source
Zero-shot Neural Transfer for Cross-lingual Entity Linking
, 2018 Cross-lingual entity linking maps an entity mention in a source language to its corresponding entry in a structured knowledge base that is in a different (target) language.
Carbonell, Jaime +3 more
core +1 more source
Crowdsourcing Question-Answer Meaning Representations
, 2017 We introduce Question-Answer Meaning Representations (QAMRs), which represent the predicate-argument structure of a sentence as a set of question-answer pairs.
Dagan, Ido +4 more
core +1 more source
A Survey of Volunteered Open Geo-Knowledge Bases in the Semantic Web
, 2013 Over the past decade, rapid advances in web technologies, coupled with innovative models of spatial data collection and consumption, have generated a robust growth in geo-referenced information, resulting in spatial information overload.
A. Ballatore +70 more
core +1 more source
Named Entity Disambiguation for Noisy Text
, 2017 We address the task of Named Entity Disambiguation (NED) for noisy text. We present WikilinksNED, a large-scale NED dataset of text fragments from the web, which is significantly noisier and more challenging than existing news-based datasets.
Cohen, Noam +5 more
core +1 more source