Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities
Due to the emergence of natural language processing (NLP) interfaces, there has been growing intent to use conversational channels for commerce. Beyond customer service, NLP-enabled AI agents are being integrated into various steps of the order-to-cash (OTC) process. Social media and messaging platf...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Published: |
Archīum Ateneo
2024
|
Subjects: | |
Online Access: | https://archium.ateneo.edu/qmit-faculty-pubs/27 https://doi.org/10.1007/978-3-031-60615-1_4 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Ateneo De Manila University |
id |
ph-ateneo-arc.qmit-faculty-pubs-1026 |
---|---|
record_format |
eprints |
spelling |
ph-ateneo-arc.qmit-faculty-pubs-10262024-09-30T07:31:48Z Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities Ilagan, Joseph Benjamin R Ilagan, Jose Ramon Zulueta, Pia Ysabel Rodrigo, Ma. Mercedes T. Due to the emergence of natural language processing (NLP) interfaces, there has been growing intent to use conversational channels for commerce. Beyond customer service, NLP-enabled AI agents are being integrated into various steps of the order-to-cash (OTC) process. Social media and messaging platforms such as Facebook Messenger have become pivotal for businesses, especially during and after the COVID-19 pandemic, but adoption has been limited. In addition, attitudes towards fully-automated conversational agents (CA) have been mixed, and there is room for human involvement in transactional conversations. A distinguishing contribution of this research is leveraging the inherent capabilities of Large Language Models (LLMs) in handling multilingual conversations and extracting transactional details through named entity recognition (NER). The study describes a hybrid human-AI setup augmenting agents with an auto-agent leveraging LLMs’ natural language understanding (NLU) capabilities, designed using the OTC process pattern applied to conversational UX frameworks. A prototype of the setup aims to streamline operations and reduce errors by enhancing the user experience during key OTC steps through improved conversational design. Recognizing the irreplaceable essence of human interaction, the hybrid human-in-the-loop approach was chosen, mitigating the impersonal nature of full automation. A prototype handling customers and humans augmented by LLMs for NER handling of transaction, customer, and product information was built. Sample synthetic bilingual conversations between customers and sales agents were generated using ChatGPT and fed into the system for evaluation. 2024-01-01T08:00:00Z text https://archium.ateneo.edu/qmit-faculty-pubs/27 https://doi.org/10.1007/978-3-031-60615-1_4 Quantitative Methods and Information Technology Faculty Publications Archīum Ateneo Co-pilots conversational commerce Conversational user experience Generative AI Large language models Named entity recognition Natural language understanding Artificial Intelligence and Robotics Computer Sciences Databases and Information Systems Physical Sciences and Mathematics |
institution |
Ateneo De Manila University |
building |
Ateneo De Manila University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
Ateneo De Manila University Library |
collection |
archium.Ateneo Institutional Repository |
topic |
Co-pilots conversational commerce Conversational user experience Generative AI Large language models Named entity recognition Natural language understanding Artificial Intelligence and Robotics Computer Sciences Databases and Information Systems Physical Sciences and Mathematics |
spellingShingle |
Co-pilots conversational commerce Conversational user experience Generative AI Large language models Named entity recognition Natural language understanding Artificial Intelligence and Robotics Computer Sciences Databases and Information Systems Physical Sciences and Mathematics Ilagan, Joseph Benjamin R Ilagan, Jose Ramon Zulueta, Pia Ysabel Rodrigo, Ma. Mercedes T. Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities |
description |
Due to the emergence of natural language processing (NLP) interfaces, there has been growing intent to use conversational channels for commerce. Beyond customer service, NLP-enabled AI agents are being integrated into various steps of the order-to-cash (OTC) process. Social media and messaging platforms such as Facebook Messenger have become pivotal for businesses, especially during and after the COVID-19 pandemic, but adoption has been limited. In addition, attitudes towards fully-automated conversational agents (CA) have been mixed, and there is room for human involvement in transactional conversations. A distinguishing contribution of this research is leveraging the inherent capabilities of Large Language Models (LLMs) in handling multilingual conversations and extracting transactional details through named entity recognition (NER). The study describes a hybrid human-AI setup augmenting agents with an auto-agent leveraging LLMs’ natural language understanding (NLU) capabilities, designed using the OTC process pattern applied to conversational UX frameworks. A prototype of the setup aims to streamline operations and reduce errors by enhancing the user experience during key OTC steps through improved conversational design. Recognizing the irreplaceable essence of human interaction, the hybrid human-in-the-loop approach was chosen, mitigating the impersonal nature of full automation. A prototype handling customers and humans augmented by LLMs for NER handling of transaction, customer, and product information was built. Sample synthetic bilingual conversations between customers and sales agents were generated using ChatGPT and fed into the system for evaluation. |
format |
text |
author |
Ilagan, Joseph Benjamin R Ilagan, Jose Ramon Zulueta, Pia Ysabel Rodrigo, Ma. Mercedes T. |
author_facet |
Ilagan, Joseph Benjamin R Ilagan, Jose Ramon Zulueta, Pia Ysabel Rodrigo, Ma. Mercedes T. |
author_sort |
Ilagan, Joseph Benjamin R |
title |
Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities |
title_short |
Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities |
title_full |
Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities |
title_fullStr |
Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities |
title_full_unstemmed |
Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models’ Natural Language Understanding Abilities |
title_sort |
optimizing conversational commerce involving multilingual consumers through large language models’ natural language understanding abilities |
publisher |
Archīum Ateneo |
publishDate |
2024 |
url |
https://archium.ateneo.edu/qmit-faculty-pubs/27 https://doi.org/10.1007/978-3-031-60615-1_4 |
_version_ |
1811611647968542720 |