Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce
This addresses the problem of dynamic and transferable title compression for voice commerce, offering a novel meta-learning approach that is incremental over existing supervised methods.
The paper tackles product title compression for voice/mobile commerce by modeling it as a meta-learning problem where the goal is to learn compression models from just one example per task, using an unsupervised meta-training approach with automatic task generation; their best model achieves an F1 score of 0.8412, beating the baseline by 25 F1 points.
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.