2 |
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Investigating Failures of Automatic Translation in the Case of Unambiguous Gender ...
|
|
|
|
Abstract:
Transformer based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by transformer based models with regards to translating from a language that doesn't mark gender on nouns into others that do. We find that even when the surrounding context provides unambiguous evidence of the appropriate grammatical gender marking, no transformer based model we tested was able to accurately gender occupation nouns systematically. We release an evaluation scheme and dataset for measuring the ability of transformer based NMT models to translate gender morphology correctly in unambiguous contexts across syntactically diverse sentences. Our dataset translates from an English source into 20 languages from several different language families. With the availability of this dataset, our hope is that the NMT community can iterate on solutions for this class of ... : 10 pages, 2 figures, 4 tables, submitting to EMNLP 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2104.07838 https://dx.doi.org/10.48550/arxiv.2104.07838
|
|
BASE
|
|
Hide details
|
|
4 |
On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
On the Idiosyncrasies of the Mandarin Chinese Classifier System ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
XNLI: Evaluating Cross-lingual Sentence Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Verb Argument Structure Alternations in Word and Sentence Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|