Scalable Micro-planned Generation of Discourse from Structured Data
Bibliographic Data
| ID | 12155694 |
|---|---|
| Authors | Anirban Laha (Mila, Université de Montréal., corresponding author), Parag Jain (0000-0002-2114-2740, University of Edinburgh), Abhijit Mishra (0009-0008-8976-4387, IBM Research.), Karthik Sankaranarayanan (0000-0001-7306-6746, IBM Research.) |
| Year | 2019 |
| Volume | 45 |
| Issue | 4 |
| Pages | 737-763 |
| Publication date | 2019-10-08 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Computational Linguistics (JOURNAL) |
| Journal identifiers | ISSN: 0891-2017 • E-ISSN: 1530-9312 |
| Publisher | Association for Computational Linguistics (PUBLISHER • US) |
| DOI | 10.1162/coli_a_00363 |
| OpenAlex | W2895279374 |
| Language | EN |
| Citations received | 2 |
| References cited | 21 |
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 use 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. Rather, it 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 utilizes a three-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 data set 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 data sets covering diverse data types such as knowledge graphs and key-value maps
Database · Fluency · Interpretability · Natural language · Natural Language Generation · Natural language processing · Natural language understanding · Paragraph · Pipeline (software · Programming language · Robustness (evolution · Scalability · Sentence · Text simplification · Computer Science · Multimodal Machine Learning Applications · Natural Language Processing Techniques · Topic Modeling · Artificial Intelligence
| Citations per year | 1 |
|---|---|
| Citation span | 2024 - 2026 (3) |
| Highly cited | No |