Arpit Sharma


pdf bib
Improving Intent Classification in an E-commerce Voice Assistant by Using Inter-Utterance Context
Arpit Sharma
Proceedings of The 3rd Workshop on e-Commerce and NLP

In this work, we improve the intent classification in an English based e-commerce voice assistant by using inter-utterance context. For increased user adaptation and hence being more profitable, an e-commerce voice assistant is desired to understand the context of a conversation and not have the users repeat it in every utterance. For example, let a user’s first utterance be ‘find apples’. Then, the user may say ‘i want organic only’ to filter out the results generated by an assistant with respect to the first query. So, it is important for the assistant to take into account the context from the user’s first utterance to understand her intention in the second one. In this paper, we present our approach for contextual intent classification in Walmart’s e-commerce voice assistant. It uses the intent of the previous user utterance to predict the intent of her current utterance. With the help of experiments performed on real user queries we show that our approach improves the intent classification in the assistant.


pdf bib
Combining Knowledge Hunting and Neural Language Models to Solve the Winograd Schema Challenge
Ashok Prakash | Arpit Sharma | Arindam Mitra | Chitta Baral
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Winograd Schema Challenge (WSC) is a pronoun resolution task which seems to require reasoning with commonsense knowledge. The needed knowledge is not present in the given text. Automatic extraction of the needed knowledge is a bottleneck in solving the challenge. The existing state-of-the-art approach uses the knowledge embedded in their pre-trained language model. However, the language models only embed part of the knowledge, the ones related to frequently co-existing concepts. This limits the performance of such models on the WSC problems. In this work, we build-up on the language model based methods and augment them with a commonsense knowledge hunting (using automatic extraction from text) module and an explicit reasoning module. Our end-to-end system built in such a manner improves on the accuracy of two of the available language model based approaches by 5.53% and 7.7% respectively. Overall our system achieves the state-of-the-art accuracy of 71.06% on the WSC dataset, an improvement of 7.36% over the previous best.


pdf bib
Identifying Various Kinds of Event Mentions in K-Parser Output
Arpit Sharma | Nguyen Vo | Somak Aditya | Chitta Baral
Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation