Applications
Task-Oriented Dialogue System with Unstructured Knowledge Access
2021
Description: This is a joint work with the CUHK team in participating the Ninth Dialog System Technology Challenge (DSTC9). I worked on ranked retrieval of knowledge snippets that best answer the user's query given the dialogue history. We ranked 12 out of the 24 participating teams. Visit the links below to see how we appproached it!
CV–JD Recommendation System
2019
Description: I wrote a crawler to scrap over 40,000 publicly available CVs and 20,000 job descriptions (JD). Word-level and document-level representations are learnt using the scrapped data using unsupervised methods. A CV–JD matching algorithm based on the learnt representations was developed. A comprehensive evaluation was attempted and the results look coherent!