paper-with-me

Papers

Uncovering Probabilistic Implications in Typological Knowledge Bases

2019-06-18 · ACL 2019 7 · Johannes Bjerva, Yova Kementchedjhieva, Ryan Cotterell, Isabelle Augenstein

The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have post-positions. Uncovering such implications typically amounts to time-consuming manual processing by trained and experienced linguists, which potentially leaves key linguistic universals unexplored. In this paper, we present a computational model which successfully identifies known universals, including Greenberg universals, but also uncovers new ones, worthy of further linguistic investigation. Our approach outperforms baselines previously used for this problem, as well as a strong baseline from knowledge base population.

📄 PDF Abstract BibTeX arXiv:1906.07389

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Base Population

Similar Papers 제목 키워드 기반

Overlooked Data in Typological Databases: What Grambank Teaches Us About Gaps in Grammars

2022-06-01 · LREC 2022 6 · Jakob Lesage, Hannah J. Haynie, Hedvig Skirgård, Tobias Weber 외

Typological databases can contain a wealth of information beyond the collection of linguistic properties across languages. This paper shows how information often overlooked in typological databases can inform the researc…

DescriptiveDiversityNegation

Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing

2018-07-02 · CL 2019 9 · Edoardo Maria Ponti, Helen O'Horan, Yevgeni Berzak, Ivan Vulić 외

Linguistic typology aims to capture structural and semantic variation across the world's languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly…

Cross-Lingual TransferSurvey

The Past, Present, and Future of Typological Databases in NLP

2023-10-20 · Emi Baylor, Esther Ploeger, Johannes Bjerva

Typological information has the potential to be beneficial in the development of NLP models, particularly for low-resource languages. Unfortunately, current large-scale typological databases, notably WALS and Grambank, a…

Language ModelingLanguage Modelling

SIGTYP 2020 Shared Task: Prediction of Typological Features

2020-10-16 · EMNLP (SIGTYP) 2020 11 · Johannes Bjerva, Elizabeth Salesky, Sabrina J. Mielke, Aditi Chaudhary 외

Typological knowledge bases (KBs) such as WALS (Dryer and Haspelmath, 2013) contain information about linguistic properties of the world's languages. They have been shown to be useful for downstream applications, includi…

Cross-Lingual TransferPredictionTransfer Learning

Learning Language Representations for Typology Prediction

2017-07-29 · EMNLP 2017 9 · Chaitanya Malaviya, Graham Neubig, Patrick Littell

One central mystery of neural NLP is what neural models "know" about their subject matter. When a neural machine translation system learns to translate from one language to another, does it learn the syntax or semantics …

Machine TranslationNMTPredictionTranslation