JeSemE models for lexical semantic change
收藏资源简介：
Models for diachronic lexical semantics used by the Jena Semantic Explorer (JeSemE) web site described in our COLING 2018 paper "JeSemE: A Website for Exploring Diachronic Changes in Word Meaning and Emotion". Also described and applied in Johannes Hellrich's Ph.D. thesis "Word Embeddings: Reliability & Semantic Change" who was funded by the Deutsche Forschungsgemeinschaft (DFG) within the graduate school "The Romantic Model" (GRK 2041/1). One ZIP file per corpus, each containing several CSV files: CHI.csv with χ<sup>2 </sup>word association values (structure: word-id, word-id, time, value) EMBEDDING.csv with SVD-PPMI word embeddings (aligned; structure: word-id, time, values) EMOTION.csv with VAD word emotion values (structure: word-id, time, values) FREQUENCY.csv with relative word frequency values (structure: word-id, time, value) PPMI.csv with PPMI<sup> </sup>word association values (structure: word-id, word-id, time, value) SIMILARITY.csv with word embedding derived word similarity values (structure: word-id, word-id, time, value) WORDIDS.csv mapping words to their corpus specific IDs Corpora are: coha: Corpus of Historical American English dta: Deutsches Textarchiv 'German Text Archive' google_fiction: Google Books N-Gram corpus, English fiction subcorpus google_german: Google Books N-Gram corpus, German subcorpus rsc: Royal Society Corpus
