# Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model

arXiv: https://arxiv.org/abs/2204.07014 · HTML: https://mlsanity.com/paper/2204.07014/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [PyTorch-BigGraph: A Large-scale Graph Embedding System](https://mlsanity.com/paper/1903.12287/) (2019)
- [TABBIE: Pretrained Representations of Tabular Data](https://mlsanity.com/paper/2105.02584/) (2021)
- [Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries](https://mlsanity.com/paper/2008.09036/) (2020)
- [Generative Adversarial Active Learning for Unsupervised Outlier Detection](https://mlsanity.com/paper/1809.10816/) (2018)
- [XGBOD: Improving Supervised Outlier Detection with Unsupervised Representation Learning](https://mlsanity.com/paper/1912.00290/) (2019)
- [Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval](https://mlsanity.com/paper/1906.00041/) (2019)
- [LSCP: Locally Selective Combination in Parallel Outlier Ensembles](https://mlsanity.com/paper/1812.01528/) (2018)
- [SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemble](https://mlsanity.com/paper/1910.08192/) (2019)
- [Empower Entity Set Expansion via Language Model Probing](https://mlsanity.com/paper/2004.13897/) (2020)
- [Web Table Extraction, Retrieval and Augmentation: A Survey](https://mlsanity.com/paper/2002.00207/) (2020)
- [TURL: Table Understanding through Representation Learning](https://mlsanity.com/paper/2006.14806/) (2020)
- [EntiTables: Smart Assistance for Entity-Focused Tables](https://mlsanity.com/paper/1708.08721/) (2017)
- [Novel Entity Discovery from Web Tables](https://mlsanity.com/paper/2002.00206/) (2020)
- [Auto-completion for Data Cells in Relational Tables](https://mlsanity.com/paper/1909.03443/) (2019)
- [A Two-Stage Masked LM Method for Term Set Expansion](https://mlsanity.com/paper/2005.01063/) (2020)
- [Generating Categories for Sets of Entities](https://mlsanity.com/paper/2008.08428/) (2020)

## Built on by (most cited first, 1 of 1)

- [Explaining ELH Concept Descriptions through Counterfactual Reasoning](https://mlsanity.com/paper/2301.05109/) (2023)

## Abstract (arXiv)

Row completion is the task of augmenting a given table of text and numbers with additional, relevant rows. The task divides into two steps: subject suggestion, the task of populating the main column; and gap filling, the task of populating the remaining columns. We present state-of-the-art results for subject suggestion and gap filling measured on a standard benchmark (WikiTables). Our idea is to solve this task by harmoniously combining knowledge base table interpretation and free text generation. We interpret the table using the knowledge base to suggest new rows and generate metadata like headers through property linking. To improve candidate diversity, we synthesize additional rows using free text generation via GPT-3, and crucially, we exploit the metadata we interpret to produce better prompts for text generation. Finally, we verify that the additional synthesized content can be linked to the knowledge base or a trusted web source such as Wikipedia.