Revisiting Absence withSymptoms that *T* Show up Decades Later to Recover Empty Categories

TL;DR

This paper investigates null elements in multiple languages, proposing a rule-based method for Chinese and neural models for English, Chinese, and Korean to improve their detection and recovery in parse trees.

Contribution

It introduces a multilingual comparison of null element processing and extends rule-based and neural approaches to handle null elements across three languages.

Findings

Rule-based approach achieved 80.00 F1 in Chinese.

Neural models achieved up to 90.94 F1 in English.

First cross-linguistic comparison of null elements in parsing.

Abstract

This paper explores null elements in English, Chinese, and Korean Penn treebanks. Null elements contain important syntactic and semantic information, yet they have typically been treated as entities to be removed during language processing tasks, particularly in constituency parsing. Thus, we work towards the removal and, in particular, the restoration of null elements in parse trees. We focus on expanding a rule-based approach utilizing linguistic context information to Chinese, as rule based approaches have historically only been applied to English. We also worked to conduct neural experiments with a language agnostic sequence-to-sequence model to recover null elements for English (PTB), Chinese (CTB) and Korean (KTB). To the best of the authors' knowledge, null elements in three different languages have been explored and compared for the first time. In expanding a rule based approach to Chinese, we achieved an overall F1 score of 80.00, which is comparable to past results in the CTB. In our neural experiments we achieved F1 scores up to 90.94, 85.38 and 88.79 for English, Chinese, and Korean respectively with functional labels.