Systematic Homonym Detection and Replacement Based on Contextual Word Embedding

Lee, Younghoon

doi:10.1007/s11063-020-10376-8

Cited by 3 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second half used the pretraining model as the basis for similarity judgment. Reference [42] used contextual word embedding and spherical K-means clustering to detect homophones among neighboring vectors; their method was similar to our method in that they calculated the similarity of the vector angle of a specific sentence; however, their entry point was different.…”

Section: Discussionmentioning

confidence: 99%

Num-Symbolic Homophonic Social Net-Words

Chung

Hsu

Huang³

2022

Information

View full text Add to dashboard Cite

Many excellent studies about social networks and text analyses can be found in the literature, facilitating the rapid development of automated text analysis technology. Due to the lack of natural separators in Chinese, the text numbers and symbols also have their original literal meaning. Thus, combining Chinese characters with numbers and symbols in user-generated content is a challenge for the current analytic approaches and procedures. Therefore, we propose a new hybrid method for detecting blended numeric and symbolic homophony Chinese neologisms (BNShCNs). Interpretation of the words’ actual semantics was performed according to their independence and relative position in context. This study obtained a shortlist using a probability approach from internet-collected user-generated content; subsequently, we evaluated the shortlist by contextualizing word-embedded vectors for BNShCN detection. The experiments show that the proposed method efficiently extracted BNShCNs from user-generated content.

show abstract

Section: Discussionmentioning

confidence: 99%

Num-Symbolic Homophonic Social Net-Words

Chung

Hsu

Huang³

2022

Information

View full text Add to dashboard Cite

show abstract

Deep contextual disambiguation of homonyms and polysemants

Vakulenko

2022

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

A new metric method for word sense disambiguation is put forward, being formulated within a phenomenological analogy to the wave function of an observable quantity in quantum mechanics where the actual meaning of a multivalued word (a homonym or a polysemant) is determined by its context. The choice of the actualized sense is determined by the minimal semantic distance between the semantics of possible word senses and that of the context, where the meanings of the word in question and the context follow from their semantic fields based on lexicographic hyperchains. In contrast to the common models, our method accounts for semantic polarity. The formulated method showed good results in disentangling polysemy, which was not possible to achieve within the contextualized embedding approacdh based on bidirectional encoder representations from transformers (BERT).

show abstract

Exploring the Effect of Conversion on the Distribution of Inflectional Suffixes: A Multivariate Corpus Study

Rauhut

2021

Zeitschrift Für Anglistik Und Amerikanistik

View full text Add to dashboard Cite

Lexical ambiguity in the English language is abundant. Word-class ambiguity is even inherently tied to the productive process of conversion. Most lexemes are rather flexible when it comes to word class, which is facilitated by the minimal morphology that English has preserved. This study takes a multivariate quantitative approach to examine potential patterns that arise in a lexicon where verb-noun and noun-verb conversion are pervasive. The distributions of three inflectional suffixes, verbal -s, nominal -s, and -ed are explored for their interaction with degrees of verb-noun conversion. In order to achieve that, the lexical dispersion, context-dependency, and lexical similarity between the inflected and bare forms were taken into consideration and controlled for in a Generalized Additive Models for Location, Scale and Shape (GAMLSS; Stasinopoulos, M. D., R. A. Rigby, and F. De Bastiani. 2018. “GAMLSS: A Distributional Regression Approach.” Statistical Modelling 18 (3–4): 248–73). The results of a series of zero-one-inflated beta models suggest that there is a clear “uncanny” valley of lexemes that show similar proportions of verbal and nominal uses. Such lexemes have a lower proportion of inflectional uses when textual dispersion and context-dependency are controlled for. Furthermore, as soon as there is some degree of conversion, the probability that a lexeme is always encountered without inflection sharply rises. Disambiguation by means of inflection is unlikely to play a uniform role depending on the inflectional distribution of a lexeme.

show abstract

Systematic Homonym Detection and Replacement Based on Contextual Word Embedding

Cited by 3 publications

References 39 publications

Num-Symbolic Homophonic Social Net-Words

Num-Symbolic Homophonic Social Net-Words

Deep contextual disambiguation of homonyms and polysemants

Exploring the Effect of Conversion on the Distribution of Inflectional Suffixes: A Multivariate Corpus Study

Contact Info

Product

Resources

About