# Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce

arXiv: https://arxiv.org/abs/2102.10760 · HTML: https://mlsanity.com/paper/2102.10760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Meta-Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1808.08437/) (2018)
- [Unsupervised Learning via Meta-Learning](https://mlsanity.com/paper/1810.02334/) (2018)
- [Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks](https://mlsanity.com/paper/1911.03863/) (2019)
- [Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks](https://mlsanity.com/paper/1908.10423/) (2019)
- [Meta-learning for Few-shot Natural Language Processing: A Survey](https://mlsanity.com/paper/2007.09604/) (2020)
- [Dynamic Memory Induction Networks for Few-Shot Text Classification](https://mlsanity.com/paper/2005.05727/) (2020)
- [When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification](https://mlsanity.com/paper/1908.08788/) (2019)
- [Multi-Source Pointer Network for Product Title Summarization](https://mlsanity.com/paper/1808.06885/) (2018)
- [Automatic Generation of Chinese Short Product Titles for Mobile Display](https://mlsanity.com/paper/1803.11359/) (2018)
- [A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data](https://mlsanity.com/paper/1801.01725/) (2018)
- [On the Importance of Attention in Meta-Learning for Few-Shot Text Classification](https://mlsanity.com/paper/1806.00852/) (2018)
- [Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery](https://mlsanity.com/paper/2012.06943/) (2020)
- [Product Title Refinement via Multi-Modal Generative Adversarial Learning](https://mlsanity.com/paper/1811.04498/) (2018)

## Abstract (arXiv)

Product title compression for voice and mobile commerce is a well studied problem with several supervised models proposed so far. However these models have 2 major limitations; they are not designed to generate compressions dynamically based on cues at inference time, and they do not transfer well to different categories at test time. To address these shortcomings we model title compression as a meta learning problem where we ask can we learn a title compression model given only 1 example compression? We adopt an unsupervised approach to meta training by proposing an automatic task generation algorithm that models the observed label generation process as the outcome of 4 unobserved processes. We create parameterized approximations to each of these 4 latent processes to get a principled way of generating random compression rules, which are treated as different tasks. For our main meta learner, we use 2 models; M1 and M2. M1 is a task agnostic embedding generator whose output feeds into M2 which is a task specific label generator. We pre-train M1 on a novel unsupervised segment rank prediction task that allows us to treat M1 as a segment generator that also learns to rank segments during the meta-training process. Our experiments on 16000 crowd generated meta-test examples show that our unsupervised meta training regime is able to acquire a learning algorithm for different tasks after seeing only 1 example for each task. Further, we show that our model trained end to end as a black box meta learner, outperforms non parametric approaches. Our best model obtains an F1 score of 0.8412, beating the baseline by a large margin of 25 F1 points.