Controlling Topic-Focus Articulation in Meaning-to-Text Generation using Graph Neural Networks
This addresses a specific challenge in natural language generation for applications requiring precise information structuring, though it is incremental in scope.
The paper tackled the problem of controlling topic-focus articulation, specifically active vs. passive voice, in meaning-to-text generation by adding pragmatic information to graph-based meaning representations, resulting in competitive performance with state-of-the-art models and significant improvements in active-passive conversion.
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.