What can Neural Referential Form Selectors Learn?

08/15/2021
by   Guanyi Chen, et al.
0

Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguistic features influencing the RE form are learnt and captured by state-of-the-art RFS models. The results of 8 probing tasks show that all the defined features were learnt to some extent. The probing tasks pertaining to referential status and syntactic position exhibited the highest performance. The lowest performance was achieved by the probing models designed to predict discourse structure properties beyond the sentence level.

READ FULL TEXT
research
09/30/2021

Syntactic Persistence in Language Models: Priming as a Window into Abstract Language Representations

We investigate the extent to which modern, neural language models are su...
research
06/06/2023

Exploring Linguistic Features for Turkish Text Readability

This paper presents the first comprehensive study on automatic readabili...
research
10/25/2022

Discourse Context Predictability Effects in Hindi Word Order

We test the hypothesis that discourse predictability influences Hindi sy...
research
04/17/2020

Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction

Despite the recent progress, little is known about the features captured...
research
05/21/2018

NeuralREG: An end-to-end approach to referring expression generation

Traditionally, Referring Expression Generation (REG) models first decide...
research
04/03/2019

Learning Outside the Box: Discourse-level Features Improve Metaphor Identification

Most current approaches to metaphor identification use restricted lingui...
research
12/08/2022

The Neural Correlates of Linguistic Structure Building: Comments on Kazanina Tavano (2022)

A recent perspective paper by Kazanina Tavano (referred to as the KT...

Please sign up or login with your details

Forgot password? Click here to reset