SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03989 · ACL · 2022

AdaptOr: Objective-Centric Adaptation Framework for Language Models

Vít Novotný, Michal Štefánik, Petr Sojka, Nikola Groverová

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

Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces the AdaptOr library 1 that transposes the traditional model-centric approach composed of pre-training + fine-tuning steps to objective-centric approach, composing the training process by applications of selected objectives. We survey research directions that can benefit from enhanced objective-centric experimentation in multi-task training, custom objectives development, dynamic training curricula, or domain adaptation. AdaptOr aims to ease the reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of AdaptOr in selected unsupervised domain adaptation scenarios.

For agents

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

get_harvested_code_for_paper("2203.03989")
get_code_for_paper("2203.03989")
have("2203.03989")

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

curl https://syntology.ai/api/ran/2203.03989.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03989.svg)](https://syntology.ai/paper/2203.03989)

Connect an agent — have() is free.