Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks

Severyn, Aliaksei; Moschitti, Alessandro

doi:10.1145/2766462.2767738

Cited by 623 publications

(538 citation statements)

References 23 publications

Supporting

Mentioning

525

Contrasting

Unclassified

Order By: Relevance

“…on the swing-up pendulum) as it scales up quadratically with the number of ranking constraints. Other ranking approaches with linear learning complexity will be considered (e.g., based on neural nets [30] or ranking forests [8]) to address this limitation. A third and most important limitation concerns the non-reversible MDP case, where the transition from s to s might take much longer than from s to s. Further work is on-going to address the non reversible case.…”

Section: Discussion and Perspectivesmentioning

confidence: 99%

Anti Imitation-Based Policy Learning

Sebag¹,

Akrour²,

Mayeur³

et al. 2016

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Section: Discussion and Perspectivesmentioning

confidence: 99%

Anti Imitation-Based Policy Learning

Sebag¹,

Akrour²,

Mayeur³

et al. 2016

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

“…We compared the performance of our deep learning model against: BM25; the Unigram Query Likelihood Model (UQLM) with Dirichlet Smoothing (Zhai and Lafferty, 2004); Word Mover's Distance (WMD) that leverages pretrained word-vectors; and a couple of neural network models based on the architecture described in (Severyn and Moschitti, 2015).…”

Section: Methods Comparedmentioning

confidence: 99%

Deep Learning for Biomedical Information Retrieval: Learning Textual Relevance from Click Logs

Mohan¹,

Fiorini²,

Kim³

et al. 2017

BioNLP 2017

View full text Add to dashboard Cite

We describe a Deep Learning approach to modeling the relevance of a document's text to a query, applied to biomedical literature. Instead of mapping each document and query to a common semantic space, we compute a variable-length difference vector between the query and document which is then passed through a deep convolution stage followed by a deep regression network to produce the estimated probability of the document's relevance to the query. Despite the small amount of training data, this approach produces a more robust predictor than computing similarities between semantic vector representations of the query and document, and also results in significant improvements over traditional IR text factors. In the future, we plan to explore its application in improving PubMed search.

show abstract

“…More formally the similarity between query q and snippet s is computed as: sim(q,s)=q T W s (1) For our CNN model, we use the short text ranking system proposed by Severyn (Severyn and Moschitti, 2015). The convolution filter width is set to 5, the feature map size to 150, and the batch size to 50.…”

Section: Snippet Rankingmentioning

confidence: 99%

Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data

Maheshwari¹,

Kumar²,

Ramakrishnan³

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: De

View full text Add to dashboard Cite

We present a system for resolving entities and disambiguating locations based on publicly available web data in the domain of ancient Hindu Temples. Scarce, unstructured information poses a challenge to Entity Resolution(ER) and snippet ranking. Additionally, because the same set of entities may be associated with multiple locations, Location Disambiguation(LD) is a problem. The mentions and descriptions of temples 1 exist in the order of hundreds of thousands, with such data generated by various users in various forms such as text (Wikipedia pages), videos (YouTube videos), blogs, etc. We demonstrate an integrated approach using a combination of grammar rules for parsing and unsupervised (clustering) algorithms to resolve entity and locations with high confidence. A demo of our system is accessible at tinyurl.com/templedemos 2 .Our system is open source and available on GitHub 3 .

show abstract

Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks

Cited by 623 publications

References 23 publications

Anti Imitation-Based Policy Learning

Anti Imitation-Based Policy Learning

Deep Learning for Biomedical Information Retrieval: Learning Textual Relevance from Click Logs

Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data

Contact Info

Product

Resources

About