Referring to what you know and do not know: Making Referring Expression Generation Models Generalize To Unseen Entities

Proceedings of the 28th International Conference on Computational Linguistics, pages 2261–2272 Barcelona, Spain (Online), December 8-13, 2020 2261 Referring to what you know and do not know: Making Referring Expression Generation Models Generalize To Unseen Entities Rossana Cunha, Thiago Castro Ferreira, Adriana Silvina Pagano, and Fabio Alves Arts Faculty, Federal University of Minas Gerais (UFMG), Brazil {rossanacunha,thiagocf05,apagano,fabio-alves}@ufmg.br Abstract Data-to-text Natural Language Generation (NLG) is the computational process of generating natural language in the form of text or voice from non-linguistic data. A core micro-planning task within NLG is referring expression generation (REG), which aims to automatically generate noun phrases to refer to entities mentioned as discourse unfolds. A limitation of novel REG models is not being able to generate referring expressions to entities not encountered during the training process. To solve this problem, we propose two extensions to NeuralREG, a state-of- the-art encoder-decoder REG model. The first is a copy mechanism, whereas the second consists of representing the gender and type of the referent as inputs to the model. Drawing on the results of automatic and human evaluation as well as an ablation study using the WebNLG corpus, we contend that our proposal contributes to the generation of more meaningful referring expressions to unseen entities than the original system and related work. Code and all produced data are publicly available12. 1 Introduction Data-to-text Natural Language Generation (NLG) is the computational process of generating natural lan- guage in the form of text or voice from non-linguistic data. A traditional micro-planning task within the pipeline data-to-text architecture is referring expression generation (REG) (Krahmer and van Deemter, 2019), which aims to automatically generate appropriate noun phrases (e.g., The mathematician Ada Lovelace) to refer to entities (e.g., Ada Lovelace) mentioned as discourse unfolds (e.g., “ was the first to recognise that the machine had applications beyond pure calculation.”). Traditionally, REG systems produce references to discourse entities in two explicit steps. First, they decide on the referential form, i.e., choosing whether a referring expression should be a pronoun (She), a proper name (Ada Lovelace), a description (The mathematician), etc. Once the choice is made, such systems textually realize the referring expression based on the chosen referential form and discourse context. If the first step selects a proper name as the form to refer to Ada Lovelace for instance, the ensuing step is responsible for deciding, among Ada, Ada Lovelace, or another text realization of a proper name, i.e., the one that is the most appropriate referring expression to that entity in a given discourse context. With the advent of large amounts of data, REG systems have undergone a significant change in their architecture. From being rule-based modular, they have become data-driven end-to-end systems that aim to perform the choice of referential form and surface realization jointly. An example of these more integrated approaches is NeuralREG (Castro Ferreira et al., 2018a), an end-to-end neural REG model that produces referring expressions deciding on form and content jointly based on representations of the referent and its surrounding context. …

Content truncated to 500 words