Record Linkage (ReL) is the task of identifying records from a pair of databases referring to the same realworld entity. This has many applications in organisations of all sizes where related data often exist in silos leading to inefficiency in data engineering and analytics applications as well as ineffectiveness of business applications (e.g., unable to personalise marketing campaigns).State-of-the-art (SOTA) machine learning and deep learning based ReL techniques use adaptive similarity measures and learn their relative contributions based on labeled data. However, we report here that they do not work with similar efficacy on industrial data owing to its fundamental differences such as magnitude of schema heterogeneity, need for leveraging structure of the data, lack of training data etc. Through our proposed system `ReLink', we carefully mitigate these challenges and demonstrate that it not only significantly outperforms SOTA baselines on industrial datasets but also on majority of research benchmarks. ReLink introduces the notion of complete-linkage over attributes as well as uses hybrid feature spaces on lexical and semantic similarity measures using pre-trained models such as BERT. Going beyond empirical demonstration, we provide insights and prescriptive guidance on choice of ReL techniques in industrial settings from our observations and lessons learnt from the experience of transferring and deploying for real use-cases in a large financial services organization.

Learning representations such that the source and target distributions appear as similar as possible has benefited transfer learning tasks across several applications. Generally it requires labeled data from the source and only unlabeled data from the target to learn such representations. While these representations act like a bridge to transfer knowledge learned in the source to the target; they may lead to negative transfer when the source specific characteristics detract their ability to represent the target data. We present a novel neural network architecture to simultaneously learn a two-part representation which is based on the principle of segregating source specific representation from the common representation. The first part captures the source specific characteristics while the second part captures the truly common representation. Our architecture optimizes an objective function which acts adversarial for the source specific part if it contributes towards the cross-domain learning. We empirically show that two parts of the representation, in different arrangements, outperforms existing learning algorithms on the source learning as well as cross-domain tasks on multiple datasets.

Duplicate invoice payment is one of the most prominent challenges encountered by accounts payable operations, and whenever it occurs, it costs to the company. Due to large volume and variety of invoices across multiple suppliers, it is not pragmatic to manually examine every invoice to check if it is legitimate and has not been previously financed. This paper presents Digital Auditor (DA), an automated framework for detecting duplicate invoices. It is based on two principles 1) converting invoices into structured templates by extracting relevant information from the invoices and organizing it as key-value pairs and 2) machine learning based duplicate detection algorithm which compares corresponding fields between two invoices and identifies duplicate invoice pairs. Digital Auditor efficiently identifies duplicate pairs, and thus alleviates laborious manual efforts and time in inspecting the invoices against the previously paid invoices. To demonstrate the efficacy of Digital Auditor, this paper presents comprehensive experimental results and key observations from user-trials by business professionals on a large sample of invoices from a non-production environment.

Artificial Intelligence (AI) has come a long way from the stages of being just scientific fiction or academic research curiosity to a point, where it is poised to impact human life significantly. AI driven applications such as autonomous vehicles, medical diagnostics, conversational agents etc. are becoming a reality. In this position paper, we argue that there are certain challenges AI still needs to overcome in its evolution from Research to Real Life. We outline some of these challenges and our suggestions to address them. We provide pointers to similar issues and their resolutions in disciplines such as psychology and medicine from which AI community can leverage the learning. More importantly, this paper is intended to focus the attention of AI research community on translating AI research efforts into real world deployments.

Automatic short answer grading (ASAG) can reduce tedium for instructors, but is complicated by free-form student inputs. An important ASAG task is to assign ordinal scores to student answers, given some “model” or ideal answers. Here we introduce a novel framework for ASAG by cascading three neural building blocks: Siamese bidirectional LSTMs applied to a model and a student answer, a novel pooling layer based on earth-mover distance (EMD) across all hidden states from both LSTMs, and a flexible final regression layer to output scores. On standard ASAG data sets, our system shows substantial reduction in grade estimation error compared to competitive baselines. We demonstrate that EMD pooling results in substantial accuracy gains, and that a support vector ordinal regression (SVOR) output layer helps outperform softmax. Our system also outperforms recent attention mechanisms on LSTM states.

Quality assurance (QA) and customer satisfaction (C-Sat) analysis are two commonly used practices to measure goodness of dialogues between agents and customers in contact centers. The practices however have a few shortcomings. QA puts sole emphasis on agents’ organizational compliance aspect whereas C-Sat attempts to measure customers’ satisfaction only based on post dialogue surveys. As a result, outcome of independent QA and C-Sat analysis may not always be in correspondence. Secondly, both processes are retrospective in nature and hence, evidences of bad past dialogues (and consequently bad customer experiences) can only be found after hours or days or weeks depending on their periodicity. Finally, human intensive nature of these practices lead to time and cost overhead while being able to analyze only a small fraction of dialogues. In this paper, we introduce an automatic real-time quality assurance system for contact centers — QART (pronounced cart). QART performs multi-faceted analysis on dialogue utterances, as they happen, using sophisticated statistical and rule-based natural language processing (NLP) techniques. It covers various aspects inspired by today’s QA and C-Sat practices as well as introduces novel incremental dialogue summarization capability. QART front-end is an interactive dashboard providing views of ongoing dialogues at different granularity enabling agents’ supervisors to monitor and take corrective actions as needed. We demonstrate effectiveness of different back-end modules as well as the overall system by experimental results on a real-life contact center chat dataset.

Advances in transfer learning have let go the limitations of traditional supervised machine learning algorithms for being dependent on annotated training data for training new models for every new domain.However, several applications encounter scenarios where models need to transfer/adapt across domains when the label sets vary both in terms of count of labels as well as their connotations.This paper presents first-of-its-kind transfer learning algorithm for cross-domain classification with multiple source domains and disparate label sets.It starts with identifying transferable knowledge from across multiple domains that can be useful for learning the target domain task.This knowledge in the form of selective labeled instances from different domains is congregated to form an auxiliary training set which is used for learning the target domain task.Experimental results validate the efficacy of the proposed algorithm against strong baselines on a real world social media and the 20 Newsgroups datasets.

In this paper, we describe an automatic real-time quality assurance system QART (pronounced cart) for contact center chats. QART performs multi-faceted analysis on dialogue utterances, as they happen, using sophisticated statistical and rule-based natural language processing (NLP) techniques. It covers various aspects inspired by today's Quality Assurance and Customer Satisfaction Scoring(C-Sat) practices as well as introduces novel components such as incremental dialogue summarization capability. QART front-end is an interactive dashboard providing views of ongoing dialogues at different granularity, enabling contact center supervisors to monitor and take corrective actions as needed. It is developed on state of the art stream computing platform Apache Spark Streaming with HBase datastore and Python Flask front end.

Automatic short answer grading (ASAG) is the task of automatically grading students answers which are a few words to a few sentences long. While supervised machine learning techniques (classification, regression) have been successfully applied for ASAG, they suffer from the constant need of instructor graded answers as labelled data. In this paper, we propose a transfer learning based technique for ASAG built on an ensemble of text classifier of student answers and a classifier using numeric features derived from various similarity measures with respect to instructor provided model answers. We present preliminary empirical results to demonstrate efficacy of the proposed technique.

The steady growth of graph data from social networks has resulted in wide-spread research in finding solutions to the influence maximization problem. In this paper, we propose a holistic solution to the influence maximization (IM) problem. (1) We introduce an opinion-cum-interaction (OI) model that closely mirrors the real-world scenarios. Under the OI model, we introduce a novel problem of Maximizing the Effective Opinion (MEO) of influenced users. We prove that the MEO problem is NP-hard and cannot be approximated within a constant ratio unless P=NP. (2) We propose a heuristic algorithm OSIM to efficiently solve the MEO problem. To better explain the OSIM heuristic, we first introduce EaSyIM - the opinion-oblivious version of OSIM, a scalable algorithm capable of running within practical compute times on commodity hardware. In addition to serving as a fundamental building block for OSIM, EaSyIM is capable of addressing the scalability aspect - memory consumption and running time, of the IM problem as well. Empirically, our algorithms are capable of maintaining the deviation in the spread always within 5% of the best known methods in the literature. In addition, our experiments show that both OSIM and EaSyIM are effective, efficient, scalable and significantly enhance the ability to analyze real datasets.

Supervised machine learning classification algorithms assume both train and test data are sampled from the same domain or distribution.However, performance of the algorithms degrade for test data from different domain.Such cross domain classification is arduous as features in the test domain may be different and absence of labeled data could further exacerbate the problem.This paper proposes an algorithm to adapt classification model by iteratively learning domain specific features from the unlabeled test data.Moreover, this adaptation transpires in a similarity aware manner by integrating similarity between domains in the adaptation setting.Cross-domain classification experiments on different datasets, including a real world dataset, demonstrate efficacy of the proposed algorithm over state-of-theart.

Text classification tasks suffer from curse of dimensionality due to large feature space.Short text data further exacerbates the problem due to their sparse and noisy nature.Feature selection thus becomes an important step in improving the classification performance.In this paper, we propose a novel feature selection method using Wavelet Packet Transform.Wavelet Packet Transform (WPT) has been used widely in various fields due to its efficiency in encoding transient signals.We demonstrate how short text classification task can be benefited by feature selection using WPT due to their sparse nature.Our technique chooses the most discriminating features by computing inter-class distances in the transformed space.We experimented extensively with several short text datasets.Compared to well known techniques our approach reduces the feature space size and improves the overall classification performance significantly in all the datasets.

This paper describes an ethnographic study of an outsourced business process - the digitization of healthcare forms. The aim of the study was to understand how the work is currently organized, with an eye to uncovering the research challenges which need to be addressed if that work is to be crowdsourced. The findings are organised under four emergent themes: Workplace Ecology, Data Entry Skills and Knowledge, Achieving Targets and Collaborative Working. For each theme a description of how the work is undertaken in the outsourcer's Indian office locations is given, followed by the implications for crowdsourcing that work. This research is a first step in understanding how crowdsourcing might be applied to BPO activities. The paper examines features specific to form digitization - extreme distribution and form decomposition - and lightly touches on the crowdsourcing of BPO work more generally.

No abstract available.

Text classification has matured as a research discipline over the last decade. Independently, business intelligence over structured databases has long been a source of insights for enterprises. In this work, we bring the two together for Customer Satisfaction(C-Sat) analysis in the services industry. We present ITACS, a solution combining text classification and business intelligence integrated with a novel interactive text labeling interface. ITACS has been deployed in multiple client accounts in contact centers. It can be extended to any services industry setting to analyze unstructured text data and derive operational and business insights. We highlight importance of interactivity in real-life text classification settings. We bring out some unique research challenges about label-sets, measuring accuracy, and interpretability that need serious attention in both academic and industrial research. We recount invaluable experiences and lessons learned as data mining researchers working toward seeing research technology deployed in the services industry.

Text classification has matured well as a research discipline over the years. At the same time, business intelligence over databases has long been a source of insights for enterprises. With the growing importance of the services industry, customer relationship management and contact center operations have become very important. Specifically, the voice of the customer and customer satisfaction (C-Sat) have emerged as invaluable sources of insights about how an enterprise's products and services are percieved by customers.

Contact centers provide dialog based support to organizations to address various customer related issues. We have observed that the calls received at contact centers mostly follow well defined patterns. Such call flows not only specify how an agent should proceed in a call, handle objections, persuade customers, follow compliance issues, etc but also help to structure the operational process of call handling. Automatically identifying such patterns in terms of distinct segments from a collection of transcripts of conversations would improve productivity of agents as well as track compliance to guidelines. Call transcripts from call centers typically tend to be noisy owing to the noise arising from agent/caller distractions, and errors introduced by the speech recognition engine. Such noise makes classical text segmentation algorithms such as TextTiling, which work on each transcript in isolation, very inappropriate. But such noise effects become statistically insignificant over a corpus of similar calls. In this paper, we propose an algorithm to segment conversational transcripts in an unsupervised way utilizing corpus level information of similar call transcripts. We show that our approach outperforms the classical TextTiling algorithm and also describe ways to improve the segmentation using limited supervision. We discuss various ways of evaluating such an algorithm. We apply the proposed algorithm to a corpus of transcripts of calls from a car reservation call center and evaluate it using various evaluation measures. We apply segmentation to the problem of automatically checking the compliance of agents and show that our segmentation algorithm considerably improves the precision.

Noise is a stark reality in real life data. Especially in the domain of text analytics, it has a significant impact as data cleaning forms a very large part of the data processing cycle. Noisy unstructured text is common in informal settings such as on-line chat, SMS, email, newsgroups and blogs, automatically transcribed text from speech, and automatically recognized text from printed or handwritten material. Gigabytes of such data is being generated everyday on the Internet, in contact centers, and on mobile phones. Researchers have looked at various text mining issues such as pre-processing and cleaning noisy text, information extraction, rule learning, and classification for noisy text. This paper focuses on the issues faced by automatic text classifiers in analyzing noisy documents coming from various sources. The goal of this paper is to bring out and study the effect of different kinds of noise on automatic text classification. Does the nature of such text warrant moving beyond traditional text classification techniques? We present detailed experimental results with simulated noise on the Reuters- 21578 and 20-newsgroups benchmark datasets. We present interesting results on real-life noisy datasets from various CRM domains.

Call centers handle customer queries from various domains such as computer sales and support, mobile phones, car rental, etc. Each such domain generally has a domain model which is essential to handle customer complaints. These models contain common problem categories, typical customer issues and their solutions, greeting styles. Currently these models are manually created over time. Towards this, we propose an unsupervised technique to generate domain models automatically from call transcriptions. We use a state of the art Automatic Speech Recognition system to transcribe the calls between agents and customers, which still results in high word error rates (40%) and show that even from these noisy transcriptions of calls we can automatically build a domain model. The domain model is comprised of primarily a topic taxonomy where every node is characterized by topic(s), typical Questions-Answers (Q&As), typical actions and call statistics. We show how such a domain model can be used for topic identification of unseen calls. We also propose applications for aiding agents while handling calls and for agent monitoring based on the domain model.

Organizing Web search results into a hierarchy of topics and sub-topics facilitates browsing the collection and locating results of interest. In this paper, we propose a new hierarchical monothetic clustering algorithm to build a topic hierarchy for a collection of search results retrieved in response to a query. At every level of the hierarchy, the new algorithm progressively identifies topics in a way that maximizes the coverage while maintaining distinctiveness of the topics. We refer the proposed algorithm to as DisCover. Evaluating the quality of a topic hierarchy is a non-trivial task, the ultimate test being user judgment. We use several objective measures such as coverage and reach time for an empirical comparison of the proposed algorithm with two other monothetic clustering algorithms to demonstrate its superiority. Even though our algorithm is slightly more computationally intensive than one of the algorithms, it generates better hierarchies. Our user studies also show that the proposed algorithm is superior to the other algorithms as a summarizing and browsing tool.