Improvement of Soundex Algorithm for Indian Language Based on Phonetic Matching

Shah, Rima; Singh, Dheeraj K.

doi:10.5121/ijcsea.2014.4303

Cited by 8 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, it has been adapted for various languages, including the Thai language (Karoonboonyanan et al 1997), the Arabic language (Yahia et al 2006;Shedeed and Abdel 2011;Ousidhoum and Bensaou 2013), the Vietnamese language (Nguyen et al 2008), the Chinese language (Li and Peng 2011), the Indian language (Shah 2014;Gautam et al 2019), the Assamese language (Baruah and Mahanta 2015), the Spanish language (del Pilar Angeles et al 2015), and others.…”

Section: The Original Soundex Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

SoundexGR: An algorithm for phonetic matching for the Greek language

Kavros

Tzitzikas

2022

Nat. Lang. Eng.

View full text Add to dashboard Cite

Text usually suffers from typos which can negatively affect various Information Retrieval and Natural Language Processing tasks. Although there is a wide variety of choices for tackling this issue in the English language, this is not the case for other languages. For the Greek language, most of the existing phonetic algorithms provide rather insufficient support. For this reason, in this paper, we introduce an algorithm for phonetic matching designed for the Greek language: we start from the original Soundex and we redesign and extend it for accommodating the Greek language’s phonetic rules, ending up to a family of algorithms, that we call ${\tt Soundex}_{GR}$ . Then, we report various experimental results showcasing how the algorithm behaves in different scenarios, and we provide comparative results for various parameters of the algorithm for revealing the trade-off between precision and recall in datasets with different kinds of errors. We also provide comparative results with matching using stemming, full phonemic transcription, and edit distance, that demonstrate that ${\tt Soundex}_{GR}$ performs better (indicatively, it achieves F-Score over 95% in collections of similar-sounded words). The simplicity, efficiency, and effectiveness of the proposed algorithm make it applicable and adaptable to a wide range of tasks.

show abstract

Section: The Original Soundex Algorithmmentioning

confidence: 99%

“…2006; Shedeed and Abdel 2011; Ousidhoum and Bensaou 2013), the Vietnamese language (Nguyen et al . 2008), the Chinese language (Li and Peng 2011), the Indian language (Shah 2014; Gautam et al . 2019), the Assamese language (Baruah and Mahanta 2015), the Spanish language (del Pilar Angeles et al .…”

Section: Background and Related Workmentioning

confidence: 99%

SoundexGR: An algorithm for phonetic matching for the Greek language

Kavros

Tzitzikas

2022

Nat. Lang. Eng.

View full text Add to dashboard Cite

show abstract

“…It has also been developed for Indian languages [26], specific examples of which include Devnagri [5], Urdu [9], Odiya [8] and Sindhi [1].…”

Section: The Soundex Algorithmmentioning

confidence: 99%

Unique Health Identifier for India: An algorithm and feasibility analysis on patient data

Soman

Srivastava

Murthy

2015

2015 17th International Conference on E-Health Networking, Application &Amp; Services (HealthCom)

View full text Add to dashboard Cite

We present an algorithm to generate unique identifiers to be used for patient identification in the Electronic Health Record (EHR) system for India. A robust EHR system is essential for ubiquitous provision of technology-enabled health-care services. Conventional EHR systems use identifiers such as Social Security Numbers to identify patients. However, in developing nations, adoption of such systems are in its infancy, leading towards the need of an independent identifier generation mechanism to enable patients without conventional IDs to register and avail health-care services. In this paper, we present an approach to generate Unique Health IDentifiers (UHID) for patients to register with EHR systems in the Indian scenario. The approach uses a combination of patient attributes to generate the identifier, and is non-obvious to a naive user. It is capable of generating upto 46, 656 unique identifiers for similar attributes, and offers the added advantage of efficient duplicate detection by using Soundex codes. The effectiveness of the proposed approach has been benchmarked on an actual patient dataset of 1, 992, 102 records, drawn from C-DAC's Hospital Management Information System (HMIS).

show abstract

“…Chaware and Rao (2012) developed a custom SOUNDEX algorithm for monolingual Hindi and Marathi word pair matching. Shah and Singh (2014) describe an actual multilingual SOUNDEX implementation designed to cover Hindi, Gujarati, and English, which, in addition to the actual algorithm implementation, was aided by a matching threshold declaring two conversions a match even if they differed in up to two characters.…”

Section: Introductionmentioning

confidence: 99%

Using Alternate Representations of Text for Natural Language Understanding

Varada¹,

Peris²,

Park³

et al. 2020

Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

View full text Add to dashboard Cite

One of the core components of voice assistants is the Natural Language Understanding (NLU) model. Its ability to accurately classify the user's request (or "intent") and recognize named entities in an utterance is pivotal to the success of these assistants. NLU models can be challenged in some languages by code-switching or morphological and orthographic variations. This work explores the possibility of improving the accuracy of NLU models for Indic languages via the use of alternate representations of input text for NLU, specifically ISO-15919 and IndicSOUNDEX, a custom SOUNDEX designed to work for Indic languages. We used a deep neural network based model to incorporate the information from alternate representations into the NLU model. We show that using alternate representations significantly improves the overall performance of NLU models when the amount of training data is limited.

show abstract

Improvement of Soundex Algorithm for Indian Language Based on Phonetic Matching

Abstract: In a system with a large database, there always has been a problem that names may not

Cited by 8 publications

References 5 publications

SoundexGR: An algorithm for phonetic matching for the Greek language

SoundexGR: An algorithm for phonetic matching for the Greek language

Unique Health Identifier for India: An algorithm and feasibility analysis on patient data

Using Alternate Representations of Text for Natural Language Understanding

Contact Info

Product

Resources

About