DeepAI AI Chat
Log In Sign Up

Learning Slice-Aware Representations with Mixture of Attentions

by   Cheng Wang, et al.

Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score. However, model improvement and development often require fine-grained modeling on individual data subsets or slices, for instance, the data slices where the models have unsatisfactory results. In practice, it gives tangible values for developing such models that can pay extra attention to critical or interested slices while retaining the original overall performance. This work extends the recent slice-based learning (SBL) <cit.> with a mixture of attentions (MoA) to learn slice-aware dual attentive representations. We empirically show that the MoA approach outperforms the baseline method as well as the original SBL approach on monitored slices with two natural language understanding (NLU) tasks.


page 1

page 2

page 3

page 4


Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

In real-world machine learning applications, data subsets correspond to ...

Handling Long-Tail Queries with Slice-Aware Conversational Systems

We have been witnessing the usefulness of conversational AI systems such...

Slice-Aware Neural Ranking

Understanding when and why neural ranking models fail for an IR task via...

Domino: Discovering Systematic Errors with Cross-Modal Embeddings

Machine learning models that achieve high overall accuracy often make sy...

Slice Tuner: A Selective Data Collection Framework for Accurate and Fair Machine Learning Models

As machine learning becomes democratized in the era of Software 2.0, one...

Slices of Attention in Asynchronous Video Job Interviews

The impact of non verbal behaviour in a hiring decision remains an open ...

FreaAI: Automated extraction of data slices to test machine learning models

Machine learning (ML) solutions are prevalent. However, many challenges ...