Latent space embedding for retrieval in question-answer archives

Show simple item record

dc.contributor.author Padmanabhan, Deepak
dc.contributor.author Garg, Dinesh
dc.contributor.author Shevade, Shirish Krishnaj
dc.contributor.other Conference on Empirical Methods in Natural Language Processing
dc.coverage.spatial Copenhagen, DK
dc.date.accessioned 2017-09-19T17:08:25Z
dc.date.available 2017-09-19T17:08:25Z
dc.date.issued 2017-09-07
dc.identifier.citation Padmanabhan, Deepak; Garg, Dinesh and Shevade, Shirish, "Latent space embedding for retrieval in question-answer archives", in the Conference on Empirical Methods in Natural Language Processing, Copenhagen, DK, Sep. 7-11, 2017. en_US
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/3147
dc.description.abstract Community-driven Question Answering (CQA) systems such as Yahoo! Answers have become valuable sources of reusable information. CQA retrieval enables usage of historical CQA archives to solve new questions posed by users. This task has received much recent attention, with methods building upon literature from translation models, topic models, and deep learning. In this paper, we devise a CQA retrieval technique, LASER-QA, that embeds question-answer pairs within a unified latent space preserving the local neighborhood structure of question and answer spaces. The idea is that such a space mirrors semantic similarity among questions as well as answers, thereby enabling high quality retrieval. Through an empirical analysis on various real-world QA datasets, we illustrate the improved effectiveness of LASER-QA over state-of-the-art methods.
dc.description.statementofresponsibility by Deepak Padmanabhan, Dinesh Garg and Shirish Shevade
dc.language.iso en en_US
dc.title Latent space embedding for retrieval in question-answer archives en_US
dc.type Article en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account