Work

Too much of product information : Don’t worry, let’s look for evidence!

Year: 2023
Type: conference-paper
Abstract: Product question answering (PQA) aims to provide instant response to customer questions posted on shopping message boards, social media, brand websites and retail stores.In this paper, we propose a distantly supervised solution to answer customer questions by using product information.Auto-answering questions using product information poses two main challenges :(i) labelled data is not readily available (ii) lengthy product information requires attending to various parts of the text to answer the question.To this end, we first propose a novel distant supervision based NLI model to prepare training data without any manual efforts.To deal with lengthy context, we factorize answer generation into two sub-problems.First, given product information, model extracts evidence spans relevant to question.Then, model leverages evidence spans to generate answer.Further, we propose two novelties in fine-tuning approach: (i) First, we jointly fine-tune model for both the tasks in end-to-end manner and showcase that it outperforms standard multitask fine-tuning.(ii) Next, we introduce an auxiliary contrastive loss for evidence extraction.We show that combination of these two ideas achieves an absolute improvement of 6% in accuracy (human evaluation) over baselines.
Authors: Aryan Jain, Jitenkumar Rana, Chetan Aggarwal
Language: English
Open Access status: hybrid
OpenAlex ID: W4389524480
FWCI: 0.062
Cites: 15
Cited by: 1
Related to: 10