Stanislav Peshterliev


Decoupled Transformer for Scalable Inference in Open-domain Question Answering
Haytham Elfdaeel | Stanislav Peshterliev
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)

Large transformer models, such as BERT, achieve state-of-the-art results in machine reading comprehension (MRC) for open-domain question answering (QA). However, transformers have a high computational cost for inference which makes them hard to apply to online QA systems for applications like voice assistants. To reduce computational cost and latency, we propose decoupling the transformer MRC model into input-component and cross-component. The decoupling allows for part of the representation computation to be performed offline and cached for online use. To retain the decoupled transformer accuracy, we devised a knowledge distillation objective from a standard transformer model. Moreover, we introduce learned representation compression layers which help reduce by four times the storage requirement for the cache. In experiments on the SQUAD 2.0 dataset, a decoupled transformer reduces the computational cost and latency of open-domain MRC by 30-40% with only 1.2 points worse F1-score compared to a standard transformer.


Active Learning for New Domains in Natural Language Understanding
Stanislav Peshterliev | John Kearney | Abhyuday Jagannatha | Imre Kiss | Spyros Matsoukas
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)

We explore active learning (AL) for improving the accuracy of new domains in a natural language understanding (NLU) system. We propose an algorithm called Majority-CRF that uses an ensemble of classification models to guide the selection of relevant utterances, as well as a sequence labeling model to help prioritize informative examples. Experiments with three domains show that Majority-CRF achieves 6.6%-9% relative error rate reduction compared to random sampling with the same annotation budget, and statistically significant improvements compared to other AL approaches. Additionally, case studies with human-in-the-loop AL on six new domains show 4.6%-9% improvement on an existing NLU system.