Blog(1)

• Towards explainable representations for natural language understanding

  Recent successes in machine learning have led to numerous Artificial Intelligence applications, such as automatic translation and chatbots. However, the effectiveness of these systems is limited by their opaqueness: predictions made by the machine learning models cannot be easily understood by humans, and hence it is hard to discern what the model learns well and what it doesn’t — which is a fundamental step to build more robust AI systems.

Research Areas(0)

Publications(11)

• TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy

  AuthorVibhav Agarwal, Sourav Ghosh, Harichandana BSS, Himanshu Arora, Barath Raj Kandur Raja

  PublishedIEEE/ACM Transactions on Audio, Speech, and Language Processing

  Date2024-01-12

• Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors

  AuthorMarek Kubis, Pawel Skorzewski, Tomasz Zietkiewicz

  PublishedConference on Empirical Methods in Natural Language Processing (EMNLP)

  Date2023-11-12

• Explainable and Accurate Natural Language Understanding for Voice Assistants and Beyond

  AuthorKalpa Gunaratna,Vijay Srinivasan,Hongxia Jin

  PublishedInternational Conference on Information and Knowledge Management (CIKM)

  Date2023-10-21

View More

News(2)

• Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors

  In a spoken dialogue system, an NLU model is preceded by a speech recognition system that can deteriorate the performance of natural language understanding. We propose to investigate the impact of speech recognition errors on the performance of natural language understanding models with a procedure that consists of three stages:

• [Blog] Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors

  In a spoken dialogue system, an NLU model is preceded by a speech recognition system that can deteriorate the performance of natural language understanding. We propose to investigate the impact of speech recognition errors on the performance of natural language understanding models with a procedure that consists of three stages

Others(0)