Scalable Micro-planned Generation of Discourse from Structured Data

Abstract

We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically employ end-to-end statistical and neural architectures that learn from a limited amount of task-specific labeled data, and therefore, exhibit limited scalability, domain-adaptability, and interpretability. Unlike these systems, ours is a modular, pipeline-based approach, and does not require task-specific parallel data. It rather relies on monolingual corpora and basic off-the-shelf NLP tools. This makes our system more scalable and easily adaptable to newer domains.Our system employs a 3-staged pipeline that: (i) converts entries in the structured data to canonical form, (ii) generates simple sentences for each atomic entry in the canonicalized representation, and (iii) combines the sentences to produce a coherent, fluent and adequate paragraph description through sentence compounding and co-reference replacement modules. Experiments on a benchmark mixed-domain dataset curated for paragraph description from tables reveals the superiority of our system over existing data-to-text approaches. We also demonstrate the robustness of our system in accepting other popular datasets covering diverse data types such as Knowledge Graphs and Key-Value maps. * The first three authors have equally contributed to the work Submission

Data-to-Text Generation with Content Selection and Planning

“…Although it is generally assumed that taskspecific parallel data is available for model training, Laha et al (2020) do away with this assumption and present a three-stage pipeline model which learns from monolingual corpora. They first convert the input to a form of tuples, which in turn are expressed in simple sentences, followed by the third stage of merging simple sentences to form more complex ones by aggregation and referring expression generation.…”

“…Our work also attempts to alleviate deficiencies in neural data-to-text generation models. In contrast to previous approaches, (Puduppully et al, 2019a;Moryossef et al, 2019;Laha et al, 2020), we place emphasis on macro planning and create plans representing high-level organization of a document including both its content and structure. We share with previous work (e.g., Moryossef et al 2019) the use of a two-stage architecture.…”

Data-to-text Generation with Macro Planning

“…Our work also attempts to alleviate deficiencies in neural data-to-text generation models. In contrast to previous approaches, (Puduppully et al, 2019a;Moryossef et al, 2019;Laha et al, 2020), we place emphasis on macro planning and create plans representing high-level organization of a document including both its content and structure. We share with previous work (e.g., Moryossef et al 2019) the use of a two-stage architecture.…”

Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View

“…Recently, end-to-end learning becomes a trend (Mei, Bansal, and Walter 2016;Chisholm, Radford, and Hachey 2017;Kaffee et al 2018;Jhamtani et al 2018;Bao et al 2018;Liu et al 2019a;Dušek, Novikova, and Rieser 2020) in this field. Among them, some work introduces differentiable planning modules (Sha et al 2018;Laha et al 2018;Puduppully, Dong, and Lapata 2018). Our paper focuses on a two-stage generation which incorporate separate text planner (Ferreira et al 2019;Ma et al 2019).…”