# An Empirical Study on Learning and Improving the Search Objective for Unsupervised Paraphrasing

arXiv: https://arxiv.org/abs/2203.12106 · HTML: https://mlsanity.com/paper/2203.12106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 23 Mar 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Sentence Simplification with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.10931/) (2017)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features](https://mlsanity.com/paper/1703.02507/) (2017)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing](https://mlsanity.com/paper/1906.08104/) (2019)
- [Paraphrase Generation with Deep Reinforcement Learning](https://mlsanity.com/paper/1711.00279/) (2017)
- [Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!](https://mlsanity.com/paper/1809.08731/) (2018)
- [Unsupervised Paraphrasing by Simulated Annealing](https://mlsanity.com/paper/1909.03588/) (2019)
- [Unsupervised Text Generation by Learning from Search](https://mlsanity.com/paper/2007.08557/) (2020)
- [Iterative Edit-Based Unsupervised Sentence Simplification](https://mlsanity.com/paper/2006.09639/) (2020)
- [Integrating Transformer and Paraphrase Rules for Sentence Simplification](https://mlsanity.com/paper/1810.11193/) (2018)
- [Which *BERT? A Survey Organizing Contextualized Encoders](https://mlsanity.com/paper/2010.00854/) (2020)
- [Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction](https://mlsanity.com/paper/2005.01791/) (2020)

## Abstract (arXiv)

Research in unsupervised text generation has been gaining attention over the years. One recent approach is local search towards a heuristically defined objective, which specifies language fluency, semantic meanings, and other task-specific attributes. Search in the sentence space is realized by word-level edit operations including insertion, replacement, and deletion. However, such objective function is manually designed with multiple components. Although previous work has shown maximizing this objective yields good performance in terms of true measure of success (i.e. BLEU and iBLEU), the objective landscape is considered to be non-smooth with significant noises, posing challenges for optimization. In this dissertation, we address the research problem of smoothing the noise in the heuristic search objective by learning to model the search dynamics. Then, the learned model is combined with the original objective function to guide the search in a bootstrapping fashion. Experimental results show that the learned models combined with the original search objective can indeed provide a smoothing effect, improving the search performance by a small margin.