Controlling Topic-Focus Articulation in Meaning-to-Text Generation using Graph Neural Networks

TL;DR

This paper explores controlling topic-focus articulation in meaning-to-text generation using graph neural networks, introducing a novel node encoding strategy that improves active-passive voice conversion.

Contribution

It proposes a new depth-first search based node aggregation method for graph neural models, enhancing control over topic-focus articulation in text generation.

Findings

The new encoding strategy achieves competitive performance on general text generation.

Significant improvements are observed in active-passive voice conversion tasks.

Different TFA types greatly influence graph model performance.

Abstract

A bare meaning representation can be expressed in various ways using natural language, depending on how the information is structured on the surface level. We are interested in finding ways to control topic-focus articulation when generating text from meaning. We focus on distinguishing active and passive voice for sentences with transitive verbs. The idea is to add pragmatic information such as topic to the meaning representation, thereby forcing either active or passive voice when given to a natural language generation system. We use graph neural models because there is no explicit information about word order in a meaning represented by a graph. We try three different methods for topic-focus articulation (TFA) employing graph neural models for a meaning-to-text generation task. We propose a novel encoding strategy about node aggregation in graph neural models, which instead of traditional encoding by aggregating adjacent node information, learns node representations by using depth-first search. The results show our approach can get competitive performance with state-of-art graph models on general text generation, and lead to significant improvements on the task of active-passive conversion compared to traditional adjacency-based aggregation strategies. Different types of TFA can have a huge impact on the performance of the graph models.