This paper describes Humor-BERT, a set of BERT Large based models that we used in the SemEval-2021 Task 7: Detecting and Rating Humor and Offense. It presents pre and post processing techniques, variable threshold learning, meta learning and Ensemble approach to solve various sub-tasks that were part of the challenge. We also present a comparative analysis of various models we tried. Our method was ranked 4th in Humor Controversy Detection, 8th in Humor Detection, 19th in Average Offense Score prediction and 40th in Average Humor Score prediction globally. F1 score obtained for Humor classification was 0.9655 and for Controversy detection it was 0.6261. Our user name on the leader board is ThisIstheEnd and team name is EndTimes.

Semantic slot prediction is one of the important task for natural language understanding (NLU). They depend on the quality and quantity of the human crafted training data, which affects model generalization. With the advent of voice assistants exposing AI platforms to third party developers, training data quality and quantity matters for any machine learning algorithm to learn and generalize properly.AI platforms provides provision to add custom external plist defined by the developers for the training data. Hence we are exploring dataset, called LowCorpusSlotData, containing low corpus training data with larger number of slots and significant test data. We also use external plist for the above dataset to aid in slot identification. We experimented using state of the art architectures like Bi-directional Encoder Representations from Transformers (BERT) with variants and Bi-directional Encoder with Custom Decoder. To address the low corpus problem, we propose a pipeline approach where we extract candidate slot information using the external plist extractor module and feed as input along with utterance.