# Select and Attend: Towards Controllable Content Selection in Text Generation

arXiv: https://arxiv.org/abs/1909.04453 · HTML: https://mlsanity.com/paper/1909.04453/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges](https://mlsanity.com/paper/2204.04859/) (2022)
- [Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints](https://mlsanity.com/paper/2109.04546/) (2021)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)
- [WeLM: A Well-Read Pre-trained Language Model for Chinese](https://mlsanity.com/paper/2209.10372/) (2022)
- [The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models](https://mlsanity.com/paper/2410.06554/) (2024)
- [Learning Fine-grained Fact-Article Correspondence in Legal Cases](https://mlsanity.com/paper/2104.10726/) (2021)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation](https://mlsanity.com/paper/2106.00791/) (2021)
- [ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference](https://mlsanity.com/paper/2204.11458/) (2022)
- [There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning](https://mlsanity.com/paper/2210.12459/) (2022)

## Abstract (arXiv)

Many text generation tasks naturally contain two steps: content selection and surface realization. Current neural encoder-decoder models conflate both steps into a black-box architecture. As a result, the content to be described in the text cannot be explicitly controlled. This paper tackles this problem by decoupling content selection from the decoder. The decoupled content selection is human interpretable, whose value can be manually manipulated to control the content of generated text. The model can be trained end-to-end without human annotations by maximizing a lower bound of the marginal likelihood. We further propose an effective way to trade-off between performance and controllability with a single adjustable hyperparameter. In both data-to-text and headline generation tasks, our model achieves promising results, paving the way for controllable content selection in text generation.