Papers by Quynh Do

5 papers
Sharing Encoder Representations across Languages, Domains and Tasks in Large-Scale Spoken Language Understanding (2023.acl-industry)

Copied to clipboard

Challenge: Larger encoders can improve accuracy for spoken language understanding (SLU) but are difficult to use given the inference latency constraints of online systems.
Approach: They propose to use a larger 170M parameter BERT encoder that shares representations across languages, domains and tasks for SLU.
Outcome: The proposed encoders achieve state-of-the-art performance on numerous NLP tasks.
Distributionally Robust Finetuning BERT for Covariate Drift in Spoken Language Understanding (2022.acl-long)

Copied to clipboard

Challenge: Covariate drift can occur when there is a drift between training and testing regarding what users request or how they request it.
Approach: They propose a method that exploits natural variations in data to create a covariate drift in spoken language understanding datasets.
Outcome: The proposed method improves robustness against covariate drift in spoken language understanding (SLU) it shows that a state-of-the-art model suffers performance loss under this drift.
Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned? (2022.emnlp-industry)

Copied to clipboard

Challenge: In productionized machine learning systems, online model performance deteriorates when there is a distributional drift between offline training and online data.
Approach: They propose a need-based retraining strategy guided by an efficient drift detector . they propose overlapping model releases, observation limitation and lack of annotated resources at runtime .
Outcome: The proposed strategy reduces the cost of retraining models at fixed intervals . the proposed strategy can detect drifts when the model is applied on a new data set .
To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding? (2020.coling-main)

Copied to clipboard

Challenge: Existing models for multilingual SLU are mostly DNN-based joint models of intent classification and slot filling.
Approach: They propose a BERT-based adversarial model architecture to learn language-shared and language-specific representations for multilingual SLU.
Outcome: The proposed model narrows the gap to the ideal multilingual performance.
Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding (D19-1)

Copied to clipboard

Challenge: Existing approaches to improve cross-lingual transfer learning on spoken language are pre-train on all available supervised data from another language.
Approach: They propose a language model based source-language data selection method for cross-lingual transfer learning in spoken language understanding.
Outcome: The proposed method reduces training time and improves model performance on spoken language understanding.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations