Deep Contextual Embeddings for Address Classification in E-commerce

TL;DR

This paper introduces a novel NLP-based approach using pre-trained language models, especially RoBERTa, to classify and understand unstructured e-commerce addresses in India, improving routing accuracy.

Contribution

It presents the first application of pre-trained language models like RoBERTa for address understanding in e-commerce, with effective fine-tuning for various downstream tasks.

Findings

RoBERTa achieves around 90% accuracy in sub-region classification.

Pre-trained models generalize well for downstream supply chain tasks.

Proposed approach outperforms traditional methods in address classification.

Abstract

E-commerce customers in developing nations like India tend to follow no fixed format while entering shipping addresses. Parsing such addresses is challenging because of a lack of inherent structure or hierarchy. It is imperative to understand the language of addresses, so that shipments can be routed without delays. In this paper, we propose a novel approach towards understanding customer addresses by deriving motivation from recent advances in Natural Language Processing (NLP). We also formulate different pre-processing steps for addresses using a combination of edit distance and phonetic algorithms. Then we approach the task of creating vector representations for addresses using Word2Vec with TF-IDF, Bi-LSTM and BERT based approaches. We compare these approaches with respect to sub-region classification task for North and South Indian cities. Through experiments, we demonstrate the effectiveness of generalized RoBERTa model, pre-trained over a large address corpus for language modelling task. Our proposed RoBERTa model achieves a classification accuracy of around 90% with minimal text preprocessing for sub-region classification task outperforming all other approaches. Once pre-trained, the RoBERTa model can be fine-tuned for various downstream tasks in supply chain like pincode suggestion and geo-coding. The model generalizes well for such tasks even with limited labelled data. To the best of our knowledge, this is the first of its kind research proposing a novel approach of understanding customer addresses in e-commerce domain by pre-training language models and fine-tuning them for different purposes.