paper-with-me

홈 › Papers

Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

2019-03-15 · NAACL 2019 6 · Shauli Ravfogel, Yoav Goldberg, Tal Linzen

How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on subject-verb agreement prediction) are complicated by the fact that any two languages differ in multiple typological properties, as well as by differences in training corpus. We propose a paradigm that addresses these issues: we create synthetic versions of English, which differ from English in one or more typological parameters, and generate corpora for those languages based on a parsed English corpus. We report a series of experiments in which RNNs were trained to predict agreement features for verbs in each of those synthetic languages. Among other findings, (1) performance was higher in subject-verb-object order (as in English) than in subject-object-verb order (as in Japanese), suggesting that RNNs have a recency bias; (2) predicting agreement with both subject and object (polypersonal agreement) improves over predicting each separately, suggesting that underlying syntactic knowledge transfers across the two tasks; and (3) overt morphological case makes agreement prediction significantly easier, regardless of word order.

📄 PDF Abstract BibTeX arXiv:1903.06400

Code (2)

Shaul1321/rnn_typology 공식 구현
573phn/rnn_typology

Tasks

Object

Similar Papers 제목 키워드 기반

Fading memory as inductive bias in residual recurrent networks

2023-07-27 · Igor Dubinin, Felix Effenberger

Residual connections have been proposed as an architecture-based inductive bias to mitigate the problem of exploding and vanishing gradients and increased task performance in both feed-forward and recurrent networks (RNN…

Inductive Bias

Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling

2026-05-18 · Afiq Abdillah Effiezal Aswadi, Oliver Britton, Ross Baker, Matthew Farrugia-Roberts arxiv

Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How …

Language Models Need Inductive Biases to Count Inductively

2024-05-30 · Yingshan Chang, Yonatan Bisk

Counting is a fundamental example of generalization, whether viewed through the mathematical lens of Peano's axioms defining the natural numbers or the cognitive science literature for children learning to count. The arg…

State Space Models

Grounding inductive biases in natural images:invariance stems from variations in data

2021-06-09 · NeurIPS 2021 12 · Diane Bouchacourt, Mark Ibrahim, Ari S. Morcos

To perform well on unseen and potentially out-of-distribution samples, it is desirable for machine learning models to have a predictable response with respect to transformations affecting the factors of variation of the …

Data AugmentationTranslation

Grounding inductive biases in natural images: invariance stems from variations in data

2021-05-21 · NeurIPS 2021 12 · Diane Bouchacourt, Mark Ibrahim, Ari S. Morcos

To perform well on unseen and potentially out-of-distribution samples, it is desirable for machine learning models to have a predictable response with respect to transformations affecting the factors of variation of the …

Data AugmentationTranslation