Results 31 to 40 of about 1,557,530 (322)
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them.
Biao Zhang +3 more
semanticscholar +1 more source
Zero-shot cross-lingual transfer language selection using linguistic similarity
Information Processing & Management, 2023 We study the selection of transfer languages for different Natural Language Processing tasks, specifically sentiment analysis, named entity recognition and dependency parsing. In order to select an optimal transfer language, we propose to utilize different linguistic similarity metrics to measure the distance between languages and make the choice of ...
Juuso Eronen +2 more
openaire +2 more sources
Phonetic correlations of the Russian and Slovak languages: Vocalism
Ученые записки Казанского университета: Серия Гуманитарные науки, 2020 The correlation analysis of vocal systems of the Russian and Slovak languages, in which phonological spaces are determined by the number and set of phoneme-forming differential characteristics of vowels, was performed.
T.I. Magomedova
doaj +1 more source
Better Zero-Shot Reasoning with Self-Adaptive Prompting [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans.
Xingchen Wan +4 more
semanticscholar +1 more source
Kommunikation ÜBER / PER / VIA Internet, Chat, SMS und E-Mail. Wie lassen sich diese digitalen Wege ausdrücken? [PDF]
Linguistische Treffen in Wrocław, 2023 The article focuses on prepositional word phrases that are considered usualised and lexicalised word compounds. Lexicalisation is marked by the zero article between the preposition and the noun.
Monika Hornáček Banášová +1 more
doaj +1 more source
Acquisition of referentiality in elicited narratives of Estonian-speaking children
Open Linguistics, 2022 This study addresses the acquisition of referential expressions in pre-schoolers’ narratives in Estonian. A total of sixteen 6- to 7-year-old typically developing monolingual Estonian children were tested using the story “Baby Goat” from the Multilingual
Argus Reili, Kütt Andra
doaj +1 more source
ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image
Sanjay Subramanian +5 more
semanticscholar +1 more source
Few-Shot and Zero-Shot Learning for Historical Text Normalization [PDF]
, 2019 Historical text normalization often relies on small training datasets. Recent work has shown that multi-task learning can lead to significant improvements by exploiting synergies with related datasets, but there has been no systematic study of different ...
Bollmann, Marcel +2 more
core +3 more sources
Lexicological Influence through Language Contacts
Revista de Lenguas Modernas, 2019 Language contacts can be studied in three directions: a) language acquisition; b) language borrowing; c) translation. In this project all of the three directions are investigated. The process of language borrowing is analysed on four levels: phonological,
Aleksandra Banjević
doaj +1 more source
ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity? [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Recent research on dialog state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on aggressive data augmentation and fine-tuning of ever larger language model ...
Michael Heck +8 more
semanticscholar +1 more source