SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.10752 · 2019

TIGS: An Inference Algorithm for Text Infilling with Gradient Search

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

Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios. However, given a well-trained sequential generative model, generating missing symbols conditioned on the context is challenging for existing greedy approximate inference algorithms. In this paper, we propose an iterative inference algorithm based on gradient search, which is the first inference algorithm that can be broadly applied to any neural sequence generative models for text infilling tasks. We compare the proposed method with strong baselines on three text infilling tasks with various mask ratios and different mask strategies. The results show that our proposed method is effective and efficient for fill-in-the-blank tasks, consistently outperforming all baselines.

For agents

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

get_harvested_code_for_paper("1905.10752")
get_code_for_paper("1905.10752")
have("1905.10752")

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

curl https://syntology.ai/api/ran/1905.10752.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.10752.svg)](https://syntology.ai/paper/1905.10752)

Connect an agent — have() is free.