SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.04523 · 2022

Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The long-distance agreement, evidence for syntactic structure, is increasingly used to assess the syntactic generalization of Neural Language Models. Much work has shown that transformers are capable of high accuracy in varied agreement tasks, but the mechanisms by which the models accomplish this behavior are still not well understood. To better understand transformers' internal working, this work contrasts how they handle two superficially similar but theoretically distinct agreement phenomena: subject-verb and object-past participle agreement in French. Using probing and counterfactual analysis methods, our experiments show that i) the agreement task suffers from several confounders which partially question the conclusions drawn so far and ii) transformers handle subject-verb and object-past participle agreements in a way that is consistent with their modeling in theoretical linguistics.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2212.04523")
get_code_for_paper("2212.04523")
have("2212.04523")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2212.04523.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2212.04523.svg)](https://syntology.ai/paper/2212.04523)

Connect an agent — have() is free.