SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.16701 · 2023

PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation

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

Syntactically controlled paraphrase generation requires language models to generate paraphrases for sentences according to specific syntactic structures. Existing fine-tuning methods for this task are costly as all the parameters of the model need to be updated during the training process. Inspired by recent studies on parameter-efficient learning, we propose Parse-Instructed Prefix (PIP), a novel adaptation of prefix-tuning to tune large pre-trained language models on syntactically controlled paraphrase generation task in a low-data setting with significantly less training cost. We introduce two methods to instruct a model's encoder prefix to capture syntax-related knowledge: direct initiation (PIP-Direct) and indirect optimization (PIP-Indirect). In contrast to traditional fine-tuning methods for this task, PIP is a compute-efficient alternative with 10 times less learnable parameters. Compared to existing prefix-tuning methods, PIP excels at capturing syntax control information, achieving significantly higher performance at the same level of learnable parameter count.

For agents

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

get_harvested_code_for_paper("2305.16701")
get_code_for_paper("2305.16701")
have("2305.16701")

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

curl https://syntology.ai/api/ran/2305.16701.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.16701.svg)](https://syntology.ai/paper/2305.16701)

Connect an agent — have() is free.