Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959149852> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2959149852 abstract "A raw stream of posts from a microblogging platform such as Twitter contains text written in a large variety of languages and writing systems, in registers ranging from formal to internet slang. A significant amount has been expended in recent years to adapt standard NLP processing pipelines to be able to deal with such content. In this paper we suggest a less labor intensive approach to processing multilingual user generated content. We induce low-dimensional distributed representations of text by training a recurrent neural network on the raw bytestream of a microblog feed. Such representations have been recently shown to be effective when used as learned features for sequence labeling tasks such as word, sentence and text segmentation (Chrupala 2013, Evang et al. 2013). In the current work we propose two new scenarios for using such representations. Firstly we employ them in a sequence transduction setting for tweet normalization. Secondly we propose a simple way to build a distributed bag-of-words analog using byte-level text embeddings, and apply it in a hashtag recommendation model. References Kilian Evang, Valerio Basile, Grzegorz Chrupala, Johan Bos. 2013. Elephant: Sequence Labeling for Word and Sentence Segmentation. EMNLP. Grzegorz Chrupala. 2013. Text segmentation with character-level text embeddings. ICML Workshop on Deep Learning for Audio, Speech and Language Processing." @default.
- W2959149852 created "2019-07-23" @default.
- W2959149852 creator A5022698890 @default.
- W2959149852 date "2014-01-01" @default.
- W2959149852 modified "2023-09-23" @default.
- W2959149852 title "Language-agnostic processing of microblog data with text embeddings" @default.
- W2959149852 hasPublicationYear "2014" @default.
- W2959149852 type Work @default.
- W2959149852 sameAs 2959149852 @default.
- W2959149852 citedByCount "0" @default.
- W2959149852 crossrefType "proceedings-article" @default.
- W2959149852 hasAuthorship W2959149852A5022698890 @default.
- W2959149852 hasConcept C136197465 @default.
- W2959149852 hasConcept C136764020 @default.
- W2959149852 hasConcept C143275388 @default.
- W2959149852 hasConcept C147168706 @default.
- W2959149852 hasConcept C154945302 @default.
- W2959149852 hasConcept C204321447 @default.
- W2959149852 hasConcept C2777530160 @default.
- W2959149852 hasConcept C2779500292 @default.
- W2959149852 hasConcept C41008148 @default.
- W2959149852 hasConcept C50644808 @default.
- W2959149852 hasConcept C518677369 @default.
- W2959149852 hasConcept C89600930 @default.
- W2959149852 hasConcept C98501671 @default.
- W2959149852 hasConceptScore W2959149852C136197465 @default.
- W2959149852 hasConceptScore W2959149852C136764020 @default.
- W2959149852 hasConceptScore W2959149852C143275388 @default.
- W2959149852 hasConceptScore W2959149852C147168706 @default.
- W2959149852 hasConceptScore W2959149852C154945302 @default.
- W2959149852 hasConceptScore W2959149852C204321447 @default.
- W2959149852 hasConceptScore W2959149852C2777530160 @default.
- W2959149852 hasConceptScore W2959149852C2779500292 @default.
- W2959149852 hasConceptScore W2959149852C41008148 @default.
- W2959149852 hasConceptScore W2959149852C50644808 @default.
- W2959149852 hasConceptScore W2959149852C518677369 @default.
- W2959149852 hasConceptScore W2959149852C89600930 @default.
- W2959149852 hasConceptScore W2959149852C98501671 @default.
- W2959149852 hasLocation W29591498521 @default.
- W2959149852 hasOpenAccess W2959149852 @default.
- W2959149852 hasPrimaryLocation W29591498521 @default.
- W2959149852 hasRelatedWork W2018268077 @default.
- W2959149852 hasRelatedWork W2158061377 @default.
- W2959149852 hasRelatedWork W2250460709 @default.
- W2959149852 hasRelatedWork W2251237590 @default.
- W2959149852 hasRelatedWork W2277870993 @default.
- W2959149852 hasRelatedWork W2578882746 @default.
- W2959149852 hasRelatedWork W2743665309 @default.
- W2959149852 hasRelatedWork W2807739445 @default.
- W2959149852 hasRelatedWork W2810488830 @default.
- W2959149852 hasRelatedWork W2888777359 @default.
- W2959149852 hasRelatedWork W2902755746 @default.
- W2959149852 hasRelatedWork W2903811917 @default.
- W2959149852 hasRelatedWork W2912277365 @default.
- W2959149852 hasRelatedWork W2927634267 @default.
- W2959149852 hasRelatedWork W2942355933 @default.
- W2959149852 hasRelatedWork W2963801581 @default.
- W2959149852 hasRelatedWork W2963826439 @default.
- W2959149852 hasRelatedWork W3015655072 @default.
- W2959149852 hasRelatedWork W3107576740 @default.
- W2959149852 hasRelatedWork W3201662413 @default.
- W2959149852 isParatext "false" @default.
- W2959149852 isRetracted "false" @default.
- W2959149852 magId "2959149852" @default.
- W2959149852 workType "article" @default.