Towards a new possibilistic query translation tool for cross-language information retrieval

Elayeb, Bilel; Romdhane, Wiem Ben; Saoud, Narjès Bellamine Ben

doi:10.1007/s11042-017-4398-2

Cited by 12 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, the simulated results of LSA utilizing semantic space without document unification have established higher efficiency compared to its existing techniques. Elayeb et al 12 proposed a plausible method using probability to possibility translation for dictionary relied on query translation. Lastly, this technique has exceeded the probabilistic one and few innovative CLIR tools.…”

Section: Related Workmentioning

confidence: 99%

Deep learning enabled cross‐lingual search with metaheuristic web based query optimization model for multi‐document summarization

Gangathimmappa¹,

Neelakandan

Sambath

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Due to the exponential increase in the generation of digital documents and in the online search user diversity, multilingual information is highly available on the Internet. However, the huge amount of multilingual data cannot be analyzed manually. Therefore, cross lingual multi-document summarization (CLMDS) model is introduced to generate a summary of several documents in which the summary language is different from the source document language. This paper presents a Deep Learning Enabled Cross-lingual Search with Metaheuristic based Query Optimization (DLCLS-MQO) model for Multi-document summarization. The DLCLS-MQO model allows to offer a query in Tamil, summarize several English documents, and lastly translate the summary into Tamil. The DLCLS-MQO model encompasses four stages of operation such as multilingual search, query optimization, automatic sematic lexicon builder, and document summarization. Firstly, bidirectional long short-term memory (BiLSTM) model is applied to perform multilingual searching process. Followed by, sunflower optimization (SFO) algorithm based query optimization process is carried out. Moreover, global vectors (GloVe) method is used for the construction of domain oriented sentiment lexicons. Finally, extreme gradient boosting (XGBoost) model is applied for the CLMDS. A detailed simulation analysis takes place to highlight the betterment of the DLCLS-MQO model. The resultant experimental values portrayed the superior performance of the DLCLS-MQO model over the compared methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep learning enabled cross‐lingual search with metaheuristic web based query optimization model for multi‐document summarization

Gangathimmappa¹,

Neelakandan

Sambath

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The outcomes of Latent Semantic Analysisby utilizing semantic space and without mergingdocuments together gainexcellent outcomes than the traditional Latent Semantic Analysisapproaches. A new probabilistic methodthat makes use of a probability-topossibility conversionfor dictionary-based query translation was proposed by the researchers in [10]. This method overcomesthe probabilistic success and forfew state-of the-art CLIR instruments.…”

Section: Literature Surveymentioning

confidence: 99%

Cloud Based Multi-Language Indexing Using Cross Lingual Information Retrieval Approaches

al.¹

2021

ITII

View full text Add to dashboard Cite

The exponential growth of data sizes created by digital media (video/audio/images), physicalsimulations, scientific instruments and web authoring joins the new growth of interest in cloud computing. The options for distribution and parallelization of information in clouds make the retrieval and storage processes very complicated, especially when faced with real-time data management. The quantity of Web Users getting access to data over Internet is expanding step by step. An enormous measure of data on Internet is accessible in various languages which could be accessed by anyone whenever. The Information Retrieval (IR) manages finding valuable data from a huge assortment of unorganized, organized and semi-organized information. In the present situation, the variety of data and language boundaries are the difficult challenges for communication and social trade over the world. To tackle such obstructions, CLIR, the cross-language information retrieval frameworks, are these days in solid interest. The Query Expansion (Q.E.) is the way toward adding related and important terms to original inquiry to upgrade its indexing ability to improve the significance of recovered files in CLIR. In this exploration work, Q.E. has been investigated for a Hindi-English and Kannada-English CLIR in that Hindi and Kannada queries are utilized to look through English docs. After the interpretation of query, recovered outcomes are positioned making use of OkapiBM25 to organize the most important doc at the top for expanding the significance of recovered docs using QE. We proposed architecture for Hindi-English and Kannada-English CLIR making use of QE. to improve the importance of recovered reports. In the primary investigation, QE. is performed with and without OkapiBM25 ranking. The outcomes show that the pertinence of recovered archives is higher with OKapiBM25 as contrast with the one without positioning. The work docs plainly demonstrate that the presentation of Hindi-English and Kannada-English CLIR framework can be improved altogether with query development using fitting terms located at suitable place and the recovered Snippets can incredibly fill in as the continuous test collection.

show abstract

“…Several retrieval-based approaches have been proposed in the literature for a variety of NLP tasks, e.g., machine translation [35,36], Q&A [17,18,27], or open-domain dialog systems [37,38,39]. Recently, Q&A systems obtained increased importance due to the fact that digital assistants such as Apple's Siri or Amazon's Alexa have become popular for answering day to day queries.…”

Section: Retrieval-based Approachesmentioning

confidence: 99%

Towards Retrieval-based Conversational Recommendation

Manzoor,

Jannach

2021

Preprint

View full text Add to dashboard Cite

Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are commonly designed to generate responses given the user's utterances in natural language. One main challenge is that these generated responses both have to be appropriate for the given dialog context and must be grammatically and semantically correct. An alternative to such generation-based approaches is to retrieve responses from pre-recorded dialog data and to adapt them if needed. Such retrieval-based approaches were successfully explored in the context of general conversational systems, but have received limited attention in recent years for CRS. In this work, we re-assess the potential of such approaches and design and evaluate a novel technique for response retrieval and ranking. A user study (N=90) revealed that the responses by our system were on average of higher quality than those of two recent generation-based systems. We furthermore found that the quality ranking of the two generation-based approaches is not aligned with the results from the literature, which points to open methodological questions. Overall, our research underlines that retrieval-based approaches should be considered an alternative or complement to language generation approaches. 1

show abstract

Towards a new possibilistic query translation tool for cross-language information retrieval

Cited by 12 publications

References 51 publications

Deep learning enabled cross‐lingual search with metaheuristic web based query optimization model for multi‐document summarization

Deep learning enabled cross‐lingual search with metaheuristic web based query optimization model for multi‐document summarization

Cloud Based Multi-Language Indexing Using Cross Lingual Information Retrieval Approaches

Towards Retrieval-based Conversational Recommendation

Contact Info

Product

Resources

About