Document Summarization in Malayalam with sentence framing

Kishore, Kavya; Gopal, Greeshma N.; Neethu, P H

doi:10.1109/infosci.2016.7845326

Cited by 7 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, other researchers presented various machine translation systems employing kārakas (Manning and Rao, 2010;H S and Idicula, 2017;Goyal and Sinha, 2009). Kārakas were also utilized in word sense disambiguation (Singh and Siddiqui, 2015), text summarization for Malayalam (Kishore et al, 2016), and processing natural language queries for database extraction (Gupta et al, 2012;Gorthi et al, 2014;Jindal et al, 2014;Kataria and Nath, 2015). Additionally, researchers proposed natural language generation (Madhavan and Reghuraj, 2012), semantic role labeling (Anwar and Sharma, 2016), language encoders for vision-and-language tasks (Gorthi and Mamidi, 2022) and argument classification in Hindi-English code-mixed tweets (Pal and Sharma, 2019), all utilizing kārakas.…”

Section: Literature Surveymentioning

confidence: 99%

Kāraka-Based Answer Retrieval for Question Answering in Indic Languages

Verma,

Joshi,

Shivani

et al. 2023

Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language Proce

View full text Add to dashboard Cite

Kārakas from ancient Paninian grammar form a concise set of semantic roles that capture crucial aspect of sentence meaning pivoted on the action verb. In this paper, we propose employing a kāraka-based approach for retrieving answers in Indic question-answering systems. To study and evaluate this novel approach, empirical experiments are conducted over large benchmark corpora in Hindi and Marathi. The results obtained demonstrate the effectiveness of the proposed method. Additionally, we explore the varying impact of two approaches for extracting kārakas. The literature surveyed and experiments conducted encourage hope that kāraka annotation can improve communication with machines using natural languages, particularly in low-resource languages.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Kāraka-Based Answer Retrieval for Question Answering in Indic Languages

Verma,

Joshi,

Shivani

et al. 2023

Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language Proce

View full text Add to dashboard Cite

show abstract

“…After that, the graph inputs into an algorithm to form the summary. The paper [15] constructs a weighted graph to recognise the top terms within an Indian text. The graph facilitates generating the abstracive summarization.…”

Section: Medlinementioning

confidence: 99%

Bilingual Summarization of English and Arabic Genetic Diseases Texts

Almugbel

2021

Int J Innov Educ Res

View full text Add to dashboard Cite

Health Literacy aims at empowering patients to take better decisions about their health. The quality of Health Literacy for patients with genetic diseases can be enriched via facilitating the bilingual retrieval of summaries about the genetic diseases texts from the net. This paper proposes helps translator to achieve this task by utilizing NLP and Recurrent Neural Network (RNN) techniques for two tasks: generating abstractive summarizations and making Arabic-English translation. Both summarization and translation tasks require training sets that can be built from English summaries corpus and Arabic-English parallel corpora. The English summaries corpus is built from Orphadata while the parallel corpora is built from Wiki articles. The corpus is utilized for generating the English summaries from the Wiki articles, and the corpora is utilized for translating these summaries into Arabic. This paper defines the research problem. Then, it investigates a set of objectives to solve the problem. After that, it presents a literature review of the tasks in the objectives. Finally, it discusses the proposed solution for the problem from the following aspects: the required corpora, the system architecture, the RNN memory cell components architectures, the proposed software for the implementation, and the system evaluation.

show abstract

“…Kavya Kishore et al [11] in their paper used a suitable semantic representation called Karaka tree for representing the sentences in the document. Karaka tree that is based on Panini's grammar framework is a suitable representation for representing Malayalam sentences as it has resemblance to the Malayalam grammar specification.…”

Section: Related Workmentioning

confidence: 99%

Automatic summarization of Malayalam documents using clause identification method

Sunitha¹,

Jaya²,

Ganesh³

2019

IJECE

View full text Add to dashboard Cite

<span>Text summarization is an active research area in the field of natural language processing. Huge amount of information in the internet necessitates the development of automatic summarization systems. There are two types of summarization techniques: Extractive and Abstractive. Extractive summarization selects important sentences from the text and produces summary as it is present in the original document. Abstractive summarization systems will provide a summary of the input text as is generated by human beings. Abstractive summary requires semantic analysis of text. Limited works have been carried out in the area of abstractive summarization in Indian languages especially in Malayalam. Only extractive summarization methods are proposed in Malayalam. In this paper, an abstractive summarization system for Malayalam documents using clause identification method is proposed. As part of this research work, a POS tagger and a morphological analyzer for Malayalam words in cricket domain are also developed. The clauses from input sentences are identified using a modified clause identification algorithm. The clauses are then semantically analyzed using an algorithm to identify semantic triples - subject, object and predicate. The score of each clause is then calculated by using feature extraction and the important clauses which are to be included in the summary are selected based on this score. Finally an algorithm is used to generate the sentences from the semantic triples of the selected clauses which is the abstractive summary of input documents.</span>

show abstract

Document Summarization in Malayalam with sentence framing

Cited by 7 publications

References 11 publications

Kāraka-Based Answer Retrieval for Question Answering in Indic Languages

Kāraka-Based Answer Retrieval for Question Answering in Indic Languages

Bilingual Summarization of English and Arabic Genetic Diseases Texts

Automatic summarization of Malayalam documents using clause identification method

Contact Info

Product

Resources

About