1 |
Is "my favorite new movie" my favorite movie? Probing the Understanding of Recursive Noun Phrases ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Scalar Adjective Identification and Multilingual Ranking ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Scalar Adjective Identification and Multilingual Ranking ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses ...
|
|
|
|
Abstract:
Pre-trained language models (LMs) encode rich information about linguistic structure but their knowledge about lexical polysemy remains unclear. We propose a novel experimental setup for analysing this knowledge in LMs specifically trained for different languages (English, French, Spanish and Greek) and in multilingual BERT. We perform our analysis on datasets carefully designed to reflect different sense distributions, and control for parameters that are highly correlated with polysemy such as frequency and grammatical category. We demonstrate that BERT-derived representations reflect words' polysemy level and their partitionability into senses. Polysemy-related information is more clearly present in English BERT embeddings, but models in other languages also manage to establish relevant distinctions between words at different polysemy levels. Our results contribute to a better understanding of the knowledge encoded in contextualised representations and open up new avenues for multilingual lexical semantics ... : Accepted to TACL. Pre-MIT Press publication version ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2104.14694 https://dx.doi.org/10.48550/arxiv.2104.14694
|
|
BASE
|
|
Hide details
|
|
5 |
Let's Play mono-poly: BERT Can Reveal Words' Degree of Polysemy ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
MULTISEM at SemEval-2020 Task 3: Fine-tuning BERT for Lexical Meaning ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Common sense or world knowledge? Investigating adapter-based knowledge injection into pretrained transformers
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Simplification Using Paraphrases and Context-Based Lexical Substitution
|
|
|
|
In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; https://hal.archives-ouvertes.fr/hal-01838519 ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Jun 2018, Nouvelle Orléans, United States (2018)
|
|
BASE
|
|
Show details
|
|
15 |
Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation
|
|
|
|
In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; https://hal.archives-ouvertes.fr/hal-01838521 ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics Jun 2018, Nouvelle Orléans, United States (2018)
|
|
BASE
|
|
Show details
|
|
16 |
Comparing Constraints for Taxonomic Organization
|
|
|
|
In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; https://hal.archives-ouvertes.fr/hal-01838520 ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics Jun 2018, Nouvelle Orléans, United States (2018)
|
|
BASE
|
|
Show details
|
|
17 |
UniMa at SemEval-2018 Task 7 : semantic relation extraction and classification from scientific publications
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Mapping the Paraphrase Database to WordNet
|
|
|
|
In: Conference on Lexical and Computational Semantics ; https://hal.archives-ouvertes.fr/hal-01838527 ; Conference on Lexical and Computational Semantics, Aug 2017, Vancouver, Canada (2017)
|
|
BASE
|
|
Show details
|
|
19 |
Learning Antonyms with Paraphrases and a Morphology-aware Neural Network
|
|
|
|
In: Conference on Lexical and Computational Semantics ; https://hal.archives-ouvertes.fr/hal-01838526 ; Conference on Lexical and Computational Semantics, Aug 2017, Vancouver, Canada (2017)
|
|
BASE
|
|
Show details
|
|
20 |
Word Sense Filtering Improves Embedding-Based Lexical Substitution
|
|
|
|
In: Conference of the European Chapter of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-01838524 ; Conference of the European Chapter of the Association for Computational Linguistics , Apr 2017, Valencia, Spain (2017)
|
|
BASE
|
|
Show details
|
|
|
|