Improving hmm-based extractive summarization for multi-domain contact center dialogues

Higashinaka, Ryuichiro; Minami, Yasuhiro; Nishikawa, Hitoshi; Dohsaka, Kohji; Meguro, Takeshi; Kobashikawa, Satoshi; Masataki, Hirokazu; Yoshioka, Osamu; Takahashi, Satoshi; Kikui, Genichiro

doi:10.1109/slt.2010.5700823

Cited by 4 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is quite interesting to note that while a lot of work has been in the area of financial text processing, only a few of them ( [11] and [4]) tried to understand the intent behind inbound calls specific to the financial domain. Moreover, none of them performed abstracting summarization followed by hierarchical clustering and classification of customer calls related to the financial domain to analyse the reasons and motivators behind these calls.…”

Section: Problem Statementmentioning

confidence: 99%

Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain

Patil,

Chopra,

Ghosh

et al. 2021

Preprint

View full text Add to dashboard Cite

In this era of abundant digital information, customer satisfaction has become one of the prominent factors in the success of any business. Customers want a one-click solution for almost everything. They tend to get unsatisfied if they have to call about something which they could have done online. Moreover, incoming calls are a high-cost component for any business. Thus, it is essential to develop a framework capable of mining the reasons and motivators behind customer calls. This paper proposes two models. Firstly, an attention-based stacked bidirectional Long Short Term Memory Network followed by Hierarchical Clustering for extracting these reasons from transcripts of inbound calls. Secondly, a set of ensemble models based on probabilities from Support Vector Machines and Logistic Regression. It is capable of detecting factors that led to these calls. Extensive evaluation proves the effectiveness of these models.

show abstract

Section: Problem Statementmentioning

confidence: 99%

Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain

Patil,

Chopra,

Ghosh

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Many text summarization studies in recent years formulate text summarization as the maximum coverage problem (Filatova and Hatzivassiloglou, 2004;Yih et al, 2007;Takamura and Okumura, 2009;Gillick and Favre, 2009;Nishikawa et al, 2010;Higashinaka et al, 2010). The maximum coverage model, based on the maximum coverage problem, generates a summary by selecting sentences to cover as many information units (such as unigrams and bigrams) as possible.…”

Section: Introductionmentioning

confidence: 99%

Multi-Document Summarization Model Based on Redundancy-Constrained Knapsack Problem

Nishikawa¹,

Hirao²,

Makino³

et al. 2013

Journal of Natural Language Processing

Self Cite

View full text Add to dashboard Cite

In this study, we regard multi-document summarization as a redundancy-constrained knapsack problem. The summarization model based on this formulation is obtained by adding a constraint that curbs redundancy in the summary to a summarization model based on the Knapsack problem. As the redundancy-constrained knapsack problem is an NP-hard problem and its computational cost is high, we propose a fast decoding method based on the Lagrange heuristic to quickly locate an approximate solution. Experiments based on ROUGE evaluation show that our proposed model outperforms the state-of-the-art text summarization model, the maximum coverage model, in finding the optimal solution. We also show that our decoding method finds a good approximate solution, which is comparable to the optimal solution of the maximum coverage model, more than 100 times faster than an integer linear programming solver.

show abstract

Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain

Patil¹,

Chopra²,

Ghosh³

et al. 2022

Computational Methods and Data Engineering

View full text Add to dashboard Cite

Improving hmm-based extractive summarization for multi-domain contact center dialogues

Cited by 4 publications

References 8 publications

Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain

Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain

Multi-Document Summarization Model Based on Redundancy-Constrained Knapsack Problem

Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain

Contact Info

Product

Resources

About