Skip to content

This work presents four directions to address the current limitations of Anwesha (prototype for Semantic Search in Bangla).

Notifications You must be signed in to change notification settings

ArupDas15/Revisiting_Anwesha

Repository files navigation

Revisiting Anwesha: Enhancing Personalised and Natural Search in Bangla

Paper | Dataset

About Anwesha

Anwesha is a semantic search tool over Bangla documents.

To know more about Anwesha, in its current form kindly visit here.

In this work, we have addressed the existing limitations of Anwesha. To know more about our work kindly refer to the paper below.

Citing

If you are using any of the resources, please cite the following paper:

@inproceedings{das-etal-2022-revisiting,
    title = "Revisiting Anwesha:Enhancing Personalised and Natural Search in {B}angla",
    author = "Das, Arup  and
      Acharya, Joyojyoti  and
      Kundu, Bibekananda  and
      Chakraborti, Sutanu",
    booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON)",
    month = dec,
    year = "2022",
    address = "New Delhi, India",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.icon-main.24",
    pages = "183--193",
    abstract = "Bangla is a low-resource, highly agglutinative language. Thus it is challenging to facilitate an effective search of Bangla documents. We have created a gold standard dataset containing query document relevance pairs for evaluation purposes. We utilise Named Entities to improve the retrieval effectiveness of traditional Bangla search algorithms. We suggest a reasonable starting model for leveraging implicit preference feedback based on the user search behaviour to enhance the results retrieved by the Explicit Semantic Analysis (ESA) approach. We use contextual sentence embeddings obtained via Language-agnostic BERT Sentence Embedding (LaBSE) to rerank the candidate documents retrieved by the traditional search algorithms (tf-idf) based on the top sentences that are most relevant to the query. This paper presents our empirical findings across these directions and critically analyses the results.",
}

Research Team

Name Contact LinkedIn/ Website
1 Arup Das, (AIDB, IITM) cs20s016@smail.iitm.ac.in https://www.linkedin.com/in/arup-das-90033a153/
2 Joyojyoti Acharya, (AIDB, IITM) cs21m024@smail.iitm.ac.in https://www.linkedin.com/in/joy-iitm/
3 Bibekananda Kundu, (CDAC) bibekananda.kundu@gmail.com https://www.linkedin.com/in/bibekananda-kundu-51205434/
4 Sutanu Chakraborti, (AIDB, IITM) sutanuc@cse.iitm.ac.in http://www.cse.iitm.ac.in/~sutanuc/

Acknowledgement

We acknowledge the below Alumni's of AIDB Laboratory, IIT Madras for their invaluable contributions in the initial development stages of Anwesha.

Name Contact LinkedIn/ Website
1 Lokasis Ghorai, (AIDB, IITM) cs20m033@smail.iitm.ac.in https://www.linkedin.com/in/lokasis-ghorai-6b073a146/
2 Arjun Kumar Gupta, (AIDB, IITM) cs20m015@smail.iitm.ac.in https://www.linkedin.com/in/arjun-kumar-gupta-10898117a/

About

This work presents four directions to address the current limitations of Anwesha (prototype for Semantic Search in Bangla).

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published