paper-with-me

Papers

The Rediscovery Hypothesis: Language Models Need to Meet Linguistics

2021-03-02 · Vassilina Nikoulina, Maxat Tezekbayev, Nuradil Kozhakhmet, Madina Babazhanova, Matthias Gallé, Zhenisbek Assylbekov

There is an ongoing debate in the NLP community whether modern language models contain linguistic knowledge, recovered through so-called probes. In this paper, we study whether linguistic knowledge is a necessary condition for the good performance of modern language models, which we call the \textit{rediscovery hypothesis}. In the first place, we show that language models that are significantly compressed but perform well on their pretraining objectives retain good scores when probed for linguistic structures. This result supports the rediscovery hypothesis and leads to the second contribution of our paper: an information-theoretic framework that relates language modeling objectives with linguistic information. This framework also provides a metric to measure the impact of linguistic information on the word prediction task. We reinforce our analytical results with various experiments, both on synthetic and on real NLP tasks in English.

📄 PDF Abstract BibTeX arXiv:2103.01819

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

A State-of-the-Art of Semantic Change Computation

2018-01-30 · Xuri Tang

This paper reviews the state-of-the-art of semantic change computation, one emerging research field in computational linguistics, proposing a framework that summarizes the literature by identifying and expounding five es…

Data Visualization

To the methodology of corpus construction for machine learning:“Taiga” syntax tree corpus and parser

2017-07-01 · “CORPORA” 2017 7 · Tatiana Shavrina, Olga Shapovalova

The “Taiga” project unites the corpus and the syntactic parser, being created in a new field of the corpus linguistics: the material obtained primarily meets the needs of machine learning, rather than linguistic search. …

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing: Tutorial Abstracts

2015-07-01 · IJCNLP 2015 7 ·

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2015-07-01 · IJCNLP 2015 7 ·

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

2015-07-01 · IJCNLP 2015 7 ·