Detection and correction of non word spelling errors in Hindi language

Jain, Amita; Jain, Minni

doi:10.1109/icdmic.2014.6954235

Cited by 12 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For suggestive List, we have utilized data available in literature. Jain and Jain (2014) analysed the erroneous data and identified the most frequently occurred spelling errors by users. It is observed that user performs maximum errors in case of phonetically similar characters.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…For Hindi spelling error correction in literature, very limited work has been done. In Hindi, a method for spelling error correction and detection for non‐word error has been proposed by Jain and Jain (2014). A system which detects and corrects document‐specific error in Indic OCR using N‐gram model has been proposed (Saluja, Adiga, Ramakrishnan, et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…A deep learning‐based model is also proposed by Etoori et al (2018). UTTAM (Jain & Jain, 2014) proposed a system for spelling error detection and correction using supervised approach in Hindi language. They have proposed to generate a candidate list followed by applying the Viterbi algorithm to find the most suitable sequence of words.…”

Section: Related Workmentioning

confidence: 99%

“…In the literature, spelling correction in Social Media Communication (SMC) text has been related to only non‐word errors or Out‐of‐vocabulary (OOV) words (Jain & Jain, 2014). However, real‐word spelling errors also should be addressed.…”

Section: Introductionmentioning

confidence: 99%

“…They showed good accuracy for standard language and text but in case of SMC where other hindrances are present like code‐mixing, informal text, and so forth, these systems crash drastically. A latest work is “Uttam” by Jain and Jain (2014), they used supervised approach to handled non‐word and real‐word errors in text, but they cannot deal with SMC text efficiently. Till now there is no work available that handles spelling errors in roman Hindi text.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Code‐mixed Hindi‐English text correction using fuzzy graph and word embedding

2023

Self Cite

View full text Add to dashboard Cite

Interaction via social media involves frequent code‐mixed text, spelling errors and noisy elements, which creates a bottleneck in the performance of natural language processing applications. This proposed work is the first approach for code‐mixed Hindi‐English social media text that comprises language identification, detection and correction of non‐word (Out of Vocabulary) errors as well as real‐word errors occurring simultaneously. Each identified language (Devanagari Hindi, Roman Hindi, and English) has its own complexities and challenges. Errors are detected individually for each language and a suggestive list of the erroneous words is created. After this, a fuzzy graph between different words of the suggestive lists is generated using various semantic relations in Hindi WordNet. Word embeddings and Fuzzy graph‐based centrality measures are used to find the correct word. Several experiments are performed on different social media datasets taken from Instagram, Twitter, YouTube comments, Blogs, and WhatsApp. The experimental results demonstrate that the proposed system corrects out‐of‐vocabulary words as well as real‐word errors with a maximum recall of 0.90 and 0.67, respectively for Dev_Hindi and 0.87 and 0.66, respectively for Rom_Hindi. The proposed method is also applied for state‐of‐art sentiment analysis approaches where the F1‐score has been visibly improved.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%