RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916419954802688 |
|---|---|
| author | Taktasheva, Ekaterina Bazhukov, Maxim Koncha, Kirill Fenogenova, Alena Artemova, Ekaterina Mikhailov, Vladislav |
| author_facet | Taktasheva, Ekaterina Bazhukov, Maxim Koncha, Kirill Fenogenova, Alena Artemova, Ekaterina Mikhailov, Vladislav |
| contents | Minimal pairs are a well-established approach to evaluating the grammatical knowledge of language models. However, existing resources for minimal pairs address a limited number of languages and lack diversity of language-specific grammatical phenomena. This paper introduces the Russian Benchmark of Linguistic Minimal Pairs (RuBLiMP), which includes 45k pairs of sentences that differ in grammaticality and isolate a morphological, syntactic, or semantic phenomenon. In contrast to existing benchmarks of linguistic minimal pairs, RuBLiMP is created by applying linguistic perturbations to automatically annotated sentences from open text corpora and carefully curating test data. We describe the data collection protocol and present the results of evaluating 25 language models in various scenarios. We find that the widely used language models for Russian are sensitive to morphological and agreement-oriented contrasts but fall behind humans on phenomena requiring understanding of structural relations, negation, transitivity, and tense. RuBLiMP, the codebase, and other materials are publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19232 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs Taktasheva, Ekaterina Bazhukov, Maxim Koncha, Kirill Fenogenova, Alena Artemova, Ekaterina Mikhailov, Vladislav Computation and Language Minimal pairs are a well-established approach to evaluating the grammatical knowledge of language models. However, existing resources for minimal pairs address a limited number of languages and lack diversity of language-specific grammatical phenomena. This paper introduces the Russian Benchmark of Linguistic Minimal Pairs (RuBLiMP), which includes 45k pairs of sentences that differ in grammaticality and isolate a morphological, syntactic, or semantic phenomenon. In contrast to existing benchmarks of linguistic minimal pairs, RuBLiMP is created by applying linguistic perturbations to automatically annotated sentences from open text corpora and carefully curating test data. We describe the data collection protocol and present the results of evaluating 25 language models in various scenarios. We find that the widely used language models for Russian are sensitive to morphological and agreement-oriented contrasts but fall behind humans on phenomena requiring understanding of structural relations, negation, transitivity, and tense. RuBLiMP, the codebase, and other materials are publicly available. |
| title | RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.19232 |