SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.02013 · ACL · 2020

Neural Syntactic Preordering for Controlled Paraphrase Generation

Greg Durrett, Tanya Goyal

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

Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization. Past approaches struggle to cover this space of paraphrase possibilities in an interpretable manner. Our work, inspired by pre-ordering literature in machine translation, uses syntactic transformations to softly "reorder" the source sentence and guide our neural paraphrasing model. First, given an input sentence, we derive a set of feasible syntactic rearrangements using an encoder-decoder model. This model operates over a partially lexical, partially syntactic view of the sentence and can reorder big chunks. Next, we use each proposed rearrangement to produce a sequence of position embeddings, which encourages our final encoder-decoder paraphrase model to attend to the source words in a particular order. Our evaluation, both automatic and human, shows that the proposed system retains the quality of the baseline approaches while giving a substantial increase in the diversity of the generated paraphrases. 1

For agents

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

get_harvested_code_for_paper("2005.02013")
get_code_for_paper("2005.02013")
have("2005.02013")

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

curl https://syntology.ai/api/ran/2005.02013.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.02013.svg)](https://syntology.ai/paper/2005.02013)

Connect an agent — have() is free.