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 This difference in dataset preparation methodology leads to assumptions about training data which are no longer valid in the real world.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

A Day In The Life Of A Quality Analyst At Haptik

In the early days at Haptik the engineers built, tested, and released software all by themselves. As the company grew and features proliferated, everybody obviously realized that this wasn’t scalable and that developers can’t test their own features. The engineers then started specializing in skill, creating more scale in the development process at Haptik and that is when I made my grand entry.

Read More