1 |
Exploring the Representations of Individual Entities in the Brain Combining EEG and Distributional Semantics
|
|
|
|
In: Front Artif Intell (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Coreference Resolution for the Biomedical Domain: A Survey ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Patterns of Lexical Ambiguity in Contextualised Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Patterns of Polysemy and Homonymy in Contextualised Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Assessing Polyseme Sense Similarity through Co-predication Acceptability and Contextualised Embedding Distance ...
|
|
|
|
Abstract:
Co-predication is one of the most frequently used linguistic tests to tell apart shifts in polysemic sense from changes in homonymic meaning. It is increasingly coming under criticism as evidence is accumulating that it tends to mis-classify specific cases of polysemic sense alteration as homonymy. In this paper, we collect empirical data to investigate these accusations. We asses how co-predication acceptability relates to explicit ratings of polyseme word sense similarity, and how well either measure can be predicted through the distance between target words' contextualised word embeddings. We find that sense similarity appears to be a major contributor in determining co-predication acceptability, but that co-predication judgements tend to rate less similar sense interpretations as being as unacceptable as homonym pairs, effectively mis-classifying these instances. The tested contextualised word embeddings fail to predict word sense similarity consistently, but the similarities between BERT embeddings show ...
|
|
Keyword:
Computer and Information Science; Natural Language Processing; Neural Network
|
|
URL: https://dx.doi.org/10.48448/d4nw-pp53 https://underline.io/lecture/6422-assessing-polyseme-sense-similarity-through-co-predication-acceptability-and-contextualised-embedding-distance
|
|
BASE
|
|
Hide details
|
|
12 |
Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Anaphoric Zero Pronoun Identification: A Multilingual Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Fake Opinion Detection: How Similar are Crowdsourced Datasets to Real Data?
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Crowdsourcing and Aggregating Nested Markable Annotations ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation
|
|
|
|
BASE
|
|
Show details
|
|
|
|