Learning Analogy-Preserving Sentence Embeddings for Answer Selection

Diallo, Aïssatou; Zopf, Markus; Fürnkranz, Johannes

doi:10.18653/v1/k19-1085

Cited by 8 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vector cosine similarity in an unsupervised word embedding enabled the prediction of applications for materials years before their publication in the materials science literature ( 49 ). Several supervised analogy learning methods based on word embeddings have been successfully applied in a variety of natural language processing tasks ( 22 , 50 , 51 ). Our algorithm uses this approach to leverage information about cancer and kinases latent in the published literature.…”

Section: Discussionmentioning

confidence: 99%

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Ravanmehr

Blau

Cappelletti

et al. 2021

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.

show abstract

Section: Discussionmentioning

confidence: 99%

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Ravanmehr

Blau

Cappelletti

et al. 2021

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Vector cosine similarity was taken recently to enable prediction of materials for applications years before their publication in the materials science literature by unsupervised word embedding (39). Several supervised analogy learning methods based on word embeddings have been successfully applied in a variety of natural language processing tasks (13,40,41). Our algorithm uses this approach to leverage information about cancer and kinases latent in the published literature.…”

Section: Discussionmentioning

confidence: 99%

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Ravanmehr

Blau

Cappelletti

et al. 2021

Preprint

View full text Add to dashboard Cite

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of more than 530 PKs have been targeted by FDA-approved medications and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on co-occurrence patterns in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. In historical data, associations between PKs and specific cancers could be predicted years in advance with good accuracy. Our model may be a tool to predict the relevance of inhibiting PKs with specific cancers.

show abstract

“…In a more recent line of work, analogical embedding is used for the problem of answer selection in query-answering systems, namely finding the correct answer for a given question from a set of candidate (potentially correct) answers [9]. Analogy quadruples are defined in the form of q p : a p :: q i : a ij , where q p and a p denote a question and its correct answer (so-called "prototypes"), and q i , a ij are the ith question and its jth candidate answer.…”

Section: Related Workmentioning

confidence: 99%

Analogical Embedding for Analogy-Based Learning to Rank

Fahandar¹,

Hüllermeier²

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning to rank based on principles of analogical reasoning has recently been proposed as a novel approach to preference learning. The approach essentially builds on a regularity assumption of the following kind: Given objects A B, C, D, if A relates to B as C relates to D, and A is preferred to B, then C is presumably preferred to D. This assumption is formalized in terms of so-called analogical proportions, which operate on a feature representation of the objects. A suitable representation is therefore essential for the success of analogy-based learning to rank. Therefore, we propose a method for analogical embedding, i.e., for embedding the data in a target space such that, in this space, the aforementioned analogy assumption is as valid and strongly pronounced as possible. This is accomplished by means of a neural network with a quadruple Siamese structure, which is trained on a suitably designed set of examples in the form of quadruples of objects. By conducting experiments on several real-world data sets, we provide evidence for the usefulness of analogical embedding and its potential to improve the performance of analogy-based learning to rank.

show abstract

Learning Analogy-Preserving Sentence Embeddings for Answer Selection

Cited by 8 publications

References 23 publications

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Analogical Embedding for Analogy-Based Learning to Rank

Contact Info

Product

Resources

About