Predicting Customer Satisfaction with Soft Labels for Ordinal Classification

Manderscheid, Etienne; Lee, Matthias

doi:10.18653/v1/2023.acl-industry.62

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, providing valuable guidance for similar industrial applications. Considering various factors, we employ LLaMA-2-7B in a real-world setting to generate summaries from Automatic Speech Recognition (ASR)-generated transcripts Khasanova et al, 2022;Laskar et al, 2022aLaskar et al, ,b, 2023bManderscheid and Lee, 2023) of organizational meetings. Below, we summarize our major contributions in this paper:…”

Section: Introductionmentioning

confidence: 99%

Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective

Laskar,

Fu,

Chen

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

View full text Add to dashboard Cite

This paper studies how to effectively build meeting summarization systems for real-world usage using large language models (LLMs). For this purpose, we conduct an extensive evaluation and comparison of various closed-source and open-source LLMs, namely, GPT-4, GPT-3.5, PaLM-2, and LLaMA-2. Our findings reveal that most closed-source LLMs are generally better in terms of performance. However, much smaller open-source models like LLaMA-2 (7B and 13B) could still achieve performance comparable to the large closed-source models even in zero-shot scenarios. Considering the privacy concerns of closed-source models for only being accessible via API, alongside the high cost associated with using fine-tuned versions of the closed-source models, the opensource models that can achieve competitive performance are more advantageous for industrial use. Balancing performance with associated costs and privacy concerns, the LLaMA-2-7B model looks more promising for industrial usage. In sum, this paper offers practical insights on using LLMs for real-world business meeting summarization, shedding light on the trade-offs between performance and cost.

show abstract

Section: Introductionmentioning

confidence: 99%

Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective

Laskar,

Fu,

Chen

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

View full text Add to dashboard Cite

show abstract

Towards the Genome-scale Discovery of Bivariate Monotonic Classifiers

Fourquet

Krejca

Doerr

et al. 2023

Preprint

View full text Add to dashboard Cite

Motivation Monotonic bivariate classifiers can describe simple patterns in high-dimensional data that may not be discernible using only elementary linear decision boundaries. Such classifiers are relatively simple, easy to interpret, and do not require large amounts of data to be effective. A challenge is that finding optimal pairs of features from a vast number of possible pairs tends to be computationally intensive, limiting the applicability of these classifiers. Results We prove a simple mathematical inequality and show how it can be exploited for the faster identification of optimal feature combinations. Our empirical results suggest speedups of 10x--20x, relative to the previous, naive, approach in applications. This result thus greatly extends the range of possible applications for bivariate monotonic classifiers. In addition, we provide the first open-source code to identify optimal monotonic bivariate classifiers. Availability: https://gitlab.pasteur.fr/ofourque/mem_python

show abstract