# Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches

arXiv: https://arxiv.org/abs/2108.10197 · HTML: https://mlsanity.com/paper/2108.10197/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 23 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Distilling Task-Specific Knowledge from BERT into Simple Neural Networks](https://mlsanity.com/paper/1903.12136/) (2019)
- [The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation](https://mlsanity.com/paper/1804.09849/) (2018)
- [Understanding and Improving Knowledge Distillation](https://mlsanity.com/paper/2002.03532/) (2020)
- [Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition](https://mlsanity.com/paper/1811.04531/) (2018)

## Built on by (most cited first, 2 of 2)

- [LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay](https://mlsanity.com/paper/2508.03628/) (2025)
- [Progressive Refinement of E-commerce Search Ranking Based on Short-Term Activities of the Buyer](https://mlsanity.com/paper/2512.13037/) (2025)

## Abstract (arXiv)

The Bidirectional Encoder Representations from Transformers (BERT) model has been radically improving the performance of many Natural Language Processing (NLP) tasks such as Text Classification and Named Entity Recognition (NER) applications. However, it is challenging to scale BERT for low-latency and high-throughput industrial use cases due to its enormous size. We successfully optimize a Query-Title Relevance (QTR) classifier for deployment via a compact model, which we name BERT Bidirectional Long Short-Term Memory (BertBiLSTM). The model is capable of inferring an input in at most 0.2ms on CPU. BertBiLSTM exceeds the off-the-shelf BERT model's performance in terms of accuracy and efficiency for the aforementioned real-world production task. We achieve this result in two phases. First, we create a pre-trained model, called eBERT, which is the original BERT architecture trained with our unique item title corpus. We then fine-tune eBERT for the QTR task. Second, we train the BertBiLSTM model to mimic the eBERT model's performance through a process called Knowledge Distillation (KD) and show the effect of data augmentation to achieve the resembling goal. Experimental results show that the proposed model outperforms other compact and production-ready models.