---
title: "Partial-Tree Linearization: Generalized Word Ordering for Text Synthesis"
authors:
  - "Yue Zhang"
doi: ""
url: "https://ijcai.org/proceedings/2013/329"
pdf: "https://ijcai.org/proceedings/2013/0329.pdf"
venue: "Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence"
year: 2013
pages: "2232-2237"
track: ""
keywords:
---

# Partial-Tree Linearization: Generalized Word Ordering for Text Synthesis

Yue Zhang

*Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence*, pages 2232-2237.

## Abstract

We present partial-tree linearization, a generalized word ordering (i.e. ordering a set of input words into a grammatical and fluent sentence) task for text-to-text applications. Recent studies of word ordering can be categorized into either abstract word ordering (no input syntax except for POS) or tree linearization (input words are associated with a full unordered syntax tree). Partial-tree linearization covers the whole spectrum of input between these two extremes. By allowing POS and dependency relations to be associated with any subset of input words, partial-tree linearization is more practical for a dependency-based NLG pipeline, such as transfer-based MT and abstractive text summarization. In addition, a partial-tree linearizer can also perform abstract word ordering and full-tree linearization. Our system achieves the best published results on standard PTB evaluations of these tasks.