Haptik introduces HINT3 to benchmark performance of Dialogue Agents

Intent Detection is a vital part of the Natural Language Understanding (NLU) pipeline of  Task-oriented dialogue systems. Recent advances in NLP have enabled systems that perform quite well on existing intent detection benchmarking datasets like HWU64, CLINC150, BANKING77 as shown in Larson et al., 2019, Casanueva et al., 2020. However, most existing datasets for intent detection are generated using crowdsourcing services. This difference in dataset preparation methodology leads to assumptions about training data which are no longer valid in the real world. In the real world, definition of intent often varies across users, tasks and domains.

Read More

Taking Neural Conversation Model To Production

Just about 3 years ago, multiple applications which were primarily backed by conventional machine learning modules got on to the wave of optimism, driven by promising results of Deep Learning techniques.

 

Read More

Paying It Forward: Open Source @ Haptik

Right from early days at Haptik, when it was only Swapan and I writing code, we had this strong urge to ensure that we would contribute to the open source communities in any way we could. We had, after all, benefitted a lot from them.

Read More