Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation

• URL: http://arxiv.org/abs/2401.09785v2
• Date: Tue, 30 Jan 2024 07:20:17 GMT
• Title: Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation
• Authors: Besnik Fetahu, Tejas Mehta, Qun Song, Nikhita Vedula, Oleg Rokhlenko, Shervin Malmasi
• Abstract summary: We seek to automate buyer inquiries to sellers using a domain-specific federated Question Answering (QA) system. M2Q reformulates buyer messages into succinct questions by identifying and extracting the most salient information from a message. Live deployment shows that automatic answering saves sellers from manually responding to millions of messages per year.
• Score: 26.593137126739308
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: E-commerce customers frequently seek detailed product information for purchase decisions, commonly contacting sellers directly with extended queries. This manual response requirement imposes additional costs and disrupts buyer's shopping experience with response time fluctuations ranging from hours to days. We seek to automate buyer inquiries to sellers in a leading e-commerce store using a domain-specific federated Question Answering (QA) system. The main challenge is adapting current QA systems, designed for single questions, to address detailed customer queries. We address this with a low-latency, sequence-to-sequence approach, MESSAGE-TO-QUESTION ( M2Q ). It reformulates buyer messages into succinct questions by identifying and extracting the most salient information from a message. Evaluation against baselines shows that M2Q yields relative increases of 757% in question understanding, and 1,746% in answering rate from the federated QA system. Live deployment shows that automatic answering saves sellers from manually responding to millions of messages per year, and also accelerates customer purchase decisions by eliminating the need for buyers to wait for a reply

Related papers

• Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations [0.0]
  In customer contact centers, human agents often struggle with long average handling times (AHT) We propose a decision support system that can look beyond RAG by first identifying customer questions in real time. If the query matches an FAQ, the system retrieves the answer directly from the FAQ database; otherwise, it generates answers via RAG.
  arXiv  Detail & Related papers  (2024-10-14T04:06:22Z)
• Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering [49.68194318431166]
  Product-related question answering (PQA) entails utilizing product-related resources to provide precise responses to users. We propose a novel task of Multilingual Cross-market Product-based Question Answering (MCPQA) We introduce a large-scale dataset comprising over 7 million questions from 17 marketplaces across 11 languages.
  arXiv  Detail & Related papers  (2024-09-24T12:24:34Z)
• CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval [52.134133938779776]
  We present CLARINET, a system that asks informative clarification questions by choosing questions whose answers would maximize certainty in the correct candidate. Our approach works by augmenting a large language model (LLM) to condition on a retrieval distribution, finetuning end-to-end to generate the question that would have maximized the rank of the true candidate at each turn.
  arXiv  Detail & Related papers  (2024-04-28T18:21:31Z)
• Identifying Shopping Intent in Product QA for Proactive Recommendations [25.30972312076997]
  We focus on the domain of e-commerce, namely in identifying Shopping Product Questions (SPQs) We propose features that capture the user's latent shopping behavior from their purchase history, and combine them using a novel Mixture-of-Experts (MoE) model. We identify SPQs in real-time and recommend shopping actions to users to add the queried product into their shopping list.
  arXiv  Detail & Related papers  (2024-04-09T04:55:24Z)
• Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions [95.92276099234344]
  We present a new state-of-the-art for answering ambiguous questions that exploits a database of unambiguous questions generated from Wikipedia. Our method improves performance by 15% on recall measures and 10% on measures which evaluate disambiguating questions from predicted outputs.
  arXiv  Detail & Related papers  (2023-08-16T20:23:16Z)
• Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search [20.216161323866867]
  Frequently Asked Question (FAQ) retrieval aims to retrieve common question-answer pairs for a user query with question intent. Integrating FAQ retrieval in product search can not only empower users to make more informed purchase decisions, but also enhance user retention through efficient post-purchase support. We propose an intent-aware FAQ retrieval system consisting of (1) an intent classifier that predicts when a user's information need can be answered by an FAQ; (2) a reformulation model that rewrites a query into a natural question.
  arXiv  Detail & Related papers  (2023-06-06T05:18:21Z)
• Answering Unanswered Questions through Semantic Reformulations in Spoken QA [20.216161323866867]
  Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. We analyze failed QA requests to identify core challenges: lexical gaps, proposition types, complex syntactic structure, and high specificity. We propose a Semantic Question Reformulation (SURF) model offering three linguistically-grounded operations (repair, syntactic reshaping, generalization) to rewrite questions to facilitate answering.
  arXiv  Detail & Related papers  (2023-05-27T07:19:27Z)
• Product Question Answering in E-Commerce: A Survey [43.12949215659755]
  Product question answering (PQA) aims to automatically provide instant responses to customer's questions in E-Commerce platforms. PQA exhibits unique challenges such as the subjectivity and reliability of user-generated contents. This paper systematically reviews existing research efforts on PQA.
  arXiv  Detail & Related papers  (2023-02-16T05:09:41Z)
• Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision [53.692793122749414]
  We introduce a medical question understanding and answering system with knowledge grounding and semantic self-supervision. Our system is a pipeline that first summarizes a long, medical, user-written question, using a supervised summarization loss. The system first matches the summarized user question with an FAQ from a trusted medical knowledge base, and then retrieves a fixed number of relevant sentences from the corresponding answer document.
  arXiv  Detail & Related papers  (2022-09-30T08:20:32Z)
• E-Commerce Dispute Resolution Prediction [69.84319333335935]
  We take a first step towards automatically assisting human agents in dispute resolution at scale. We construct a large dataset of disputes from the eBay online marketplace, and identify several interesting behavioral and linguistic patterns. We then train classifiers to predict dispute outcomes with high accuracy.
  arXiv  Detail & Related papers  (2021-10-13T09:45:06Z)
• Unsupervised Question Decomposition for Question Answering [102.56966847404287]
  We propose an algorithm for One-to-N Unsupervised Sequence Sequence (ONUS) that learns to map one hard, multi-hop question to many simpler, single-hop sub-questions. We show large QA improvements on HotpotQA over a strong baseline on the original, out-of-domain, and multi-hop dev sets.
  arXiv  Detail & Related papers  (2020-02-22T19:40:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.