2020
DOI: 10.48550/arxiv.2011.03755
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

NLP-CIC @ DIACR-Ita: POS and Neighbor Based Distributional Models for Lexical Semantic Change in Diachronic Italian Corpora

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

1
0

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 0 publications
0
2
0
Order By: Relevance
“…For example, in the DIACR-Ita challenge [49], there were only 18 words available in the gold standard to detect semantic drift in a diachronic corpus (that is, a corpus from the past and one from the present). In this challenge, Angel et al [50] showed that it is not necessary to obtain a single semantic space to identify semantic drifts but that this can be done using the word embeddings obtained separately for each corpus. To identify if a word has semantic drift, its corresponding sets of k neighboring words in each semantic space are collected and compared with the Jaccard index.…”
Section: Measuring Word Drifts By Word Embeddingsmentioning
confidence: 99%
See 1 more Smart Citation
“…For example, in the DIACR-Ita challenge [49], there were only 18 words available in the gold standard to detect semantic drift in a diachronic corpus (that is, a corpus from the past and one from the present). In this challenge, Angel et al [50] showed that it is not necessary to obtain a single semantic space to identify semantic drifts but that this can be done using the word embeddings obtained separately for each corpus. To identify if a word has semantic drift, its corresponding sets of k neighboring words in each semantic space are collected and compared with the Jaccard index.…”
Section: Measuring Word Drifts By Word Embeddingsmentioning
confidence: 99%
“…To detect words with different meanings between reviews and description corpora for each domain, we followed Angel et al [50] by training word embeddings for each corpus and comparing neighboring words for each target word. We use the implementation of word2vec [27] in Gensim [53] using the CBOW algorithm and a 5-word window (these are the default parameters).…”
Section: Word Embeddings For Word Driftmentioning
confidence: 99%