Describing a Knowledge Base

By Qingyun Wang, Xiaoman Pan, Lifu Huang, Boliang Zhang, Heng Ji, Kevin Knight. 2018

59 citations recorded by the source corpus.

We aim to automatically generate natural language descriptions about an input structured knowledge base (KB). We build our generation framework based on a pointer network which can copy facts from the input KB, and add two attention mechanisms: (i) slot-aware attention to capture the association between a slot type and its corresponding slot value; and (ii) a new table position self-attention to capture the inter-dependencies among related slots. For evaluation, besides standard metrics including BLEU, METEOR, and ROUGE, we propose a KB reconstruction based metric by extracting a KB from the generation output and comparing it with the input KB. We also create a new data set which includes 106,216 pairs of structured KBs and their corresponding natural language descriptions for two distinct entity types. Experiments show that our approach significantly outperforms state-of-the-art methods. The reconstructed KB achieves 68.8% - 72.6% F-score.

Subfields: Artificial Intelligence, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Knowledge Graphs & Representation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “, 2018; Perez-Beltrachini and Lapata, 2018), knowledge-base descriptions (OâĂŹDonnell et al., 2000; Banik et al., 2013; Gardent et al., 2017a,b; Novikova et al., 2017b; Wang et al., 2018; Yu et al., 2019), code comment (Iyer et al.”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, methodology): “Apart from delexicalisation, which is most often used in the E2E NLG Challenge, various variants of the copy mechanism are the most prominent approach to address open vocabulary in NLG (Wiseman, Shieber, and Rush 2017; Lebret, Grangier, and Auli 2016; Bao et al. 2018; Kaffee et al. 2018; Wang et al.”
Logic-Consistency Text Generation from Semantic Parses (2021, methodology): “…natural language interfaces (Gatt and Krahmer, 2018; Chen et al., 2020b; Hu et al., 2020; Mishra et al., 2019; Yu et al., 2019; Ngomo et al., 2013; Wang et al., 2018; Gardent et al., 2017; Wang et al., 2020a; *Equal Contribution Figure 1: Our data augmentation procedure for the generator and…”
Relational Memory-Augmented Language Models (2022, background): “, 2021), entity types (Parvez et al., 2018; Wang et al., 2018b) and entity descriptions (Bahdanau et al.”
Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, methodology): “W IKIPERSON (Wang et al. 2018).”
Latent Relation Language Models (2019, methodology): “Compared to other methods that condition LMs on knowledge graphs (KGs; Ahn et al. (2016); Wang et al. (2018)) , the span-based generation from the KGs alleviates problems of malformed or incomplete mentions.”
Variational Template Machine for Data-to-Text Generation (2020, methodology): “Data-to-text has been used to generate different kinds of texts, such as weather reports (Angeli et al., 2010), sports news (Mei et al., 2016; Wiseman et al., 2017) and biographies (Lebret et al., 2016; Wang et al., 2018b; Chisholm et al., 2017).”
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021, methodology): “For end-to-end methods, we select the following methods as baselines: (1) DesKnow (Wang et al., 2018), a seq2seq model with a table position selfattention to capture the inter-dependencies among related attributes; (2) PtGen (Pointer-Generator, See et al.”
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints (2020, methodology): “This drawback prevents them from being applied to larger tables, for example, a table describing a large Knowledge Base (Wang et al., 2018).”
PaperRobot: Incremental Draft Generation of Scientific Ideas (2019, background): “…et al., 2018), biographies based on attributes (Lebret et al., 2016; Chisholm et al., 2017; Liu et al., 2018; Sha et al., 2018; Kaffee et al., 2018; Wang et al., 2018a; Wiseman et al., 2018), and image/video captions based on background entities and events (Krishnamoorthy et al., 2013; Wu et al.,…”
Findings of the Third Workshop on Neural Generation and Translation (2019, background): “The inputs to NLG systems also vary from structured data such as tables (Lebret et al., 2016) or graphs (Wang et al., 2018), to textual data (Nallapati et al., 2016).”