Sandeep Subramanian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sandeep Subramanian has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Madhavi K. Ganapathiraju
Department of Biomedical Informatics, School of Medicine, University of Pittsburgh
5 shared publications - Adam Roth
Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA
2 shared publications Chris Pal
2 shared publicationsXingdi Yuan
Montreal Institute for Learning Algorithms Université de Montréal
2 shared publicationsAaron Courville
1 shared publicationAdam Trischler
1 shared publication
Latest Publications
- Open Access
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 9308-9319
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
Jonathan Pilault, Raymond Li, Sandeep Subramanian, Chris Pal. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 9308-9319
Open AccessOn Extractive and Abstractive Neural Document Summarization with Transformer Language Models
Jonathan Pilault, Raymond Li, Sandeep Subramanian, Chris Pal. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 32-37
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 32-37
Open AccessDo Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
- Open Access
Antibody Exchange: Information Extraction of Biological Antibody Donation and a Web-Portal to Find Donors and Seekers
Bio-molecular reagents, like antibodies that are required in experimental biology are expensive and their effectiveness, among other things, is critical to the success of the experiment. Although such resources are sometimes donated by one investigator to another through personal communication between the two, there is no previous study to our knowledge on the extent of such donations, nor a central platform that directs resource seekers to donors. In this paper, we describe, to our knowledge, a first attempt at building a web-portal titled Antibody Exchange (or more general ‘Bio-Resource Exchange’) that attempts to bridge this gap between resource seekers and donors in the domain of experimental biology. Users on this portal can request for or donate antibodies, cell-lines, and DNA Constructs. This resource could also serve as a crowd-sourced database of resources for experimental biology. Further, we also studied the extent of antibody donations by mining the acknowledgement sections of scientific articles. Specifically, we extracted the name of the donor, his/her affiliation, and the name of the antibody for every donation by parsing the acknowledgements sections of articles. To extract annotations at this level, we adopted two approaches—a rule based algorithm and a bootstrapped pattern learning algorithm. The algorithms extracted donor names, affiliations, and antibody names with average accuracies of 57% and 62%, respectively. We also created a dataset of 50 expert-annotated acknowledgements sections that will serve as a gold standard dataset to evaluate extraction algorithms in the future.
Open AccessAntibody Exchange: Information Extraction of Biological Antibody Donation and a Web-Portal to Find Donors and Seekers
Bio-molecular reagents, like antibodies that are required in experimental biology are expensive and their effectiveness, among other things, is critical to the success of the experiment. Although such resources are sometimes donated by one investigator to another through personal communication between the two, there is no previous study to our knowledge on the extent of such donations, nor a central platform that directs resource seekers to donors. In this paper, we describe, to our knowledge, a first attempt at building a web-portal titled Antibody Exchange (or more general ‘Bio-Resource Exchange’) that attempts to bridge this gap between resource seekers and donors in the domain of experimental biology. Users on this portal can request for or donate antibodies, cell-lines, and DNA Constructs. This resource could also serve as a crowd-sourced database of resources for experimental biology. Further, we also studied the extent of antibody donations by mining the acknowledgement sections of scientific articles. Specifically, we extracted the name of the donor, his/her affiliation, and the name of the antibody for every donation by parsing the acknowledgements sections of articles. To extract annotations at this level, we adopted two approaches—a rule based algorithm and a bootstrapped pattern learning algorithm. The algorithms extracted donor names, affiliations, and antibody names with average accuracies of 57% and 62%, respectively. We also created a dataset of 50 expert-annotated acknowledgements sections that will serve as a gold standard dataset to evaluate extraction algorithms in the future.
- Open Access
Machine Comprehension by Text-to-Text Neural Question Generation
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.
Open AccessMachine Comprehension by Text-to-Text Neural Question Generation
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.
- Open Access
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Machine Comprehension by Text-to-Text Neural Question Generation
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Open AccessMachine Comprehension by Text-to-Text Neural Question Generation
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Adversarial Generation of Natural Language
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Adversarial Generation of Natural Language
- Open Access
- 5 December 2016
- Published by Springer Nature in BMC Medical Genomics
- Vol. 9 (S3) , 73
A pilot study on the prevalence of DNA palindromes in breast cancer genomes
DNA palindromes are a unique pattern of repeat sequences that are present in the human genome. It consists of a sequence of nucleotides in which the second half is the complement of the first half but appearing in reverse order. These palindromic sequences may have a significant role in DNA replication, transcription and gene regulation processes. They occur frequently in human cancers by clustering at specific locations of the genome that undergo gene amplification and tumorigenesis. Moreover, some studies showed that palindromes are clustered in amplified regions of breast cancer genomes especially in chromosomes (chr) 8 and 11. With the large number of personal genomes and cancer genomes becoming available, it is now possible to study their association to diseases using computational methods. Here, we conducted a pilot study on chromosomes 8 and 11 of cancer genomes to identify computationally the differentially occurring palindromes. We processed 69 breast cancer genomes from The Cancer Genome Atlas including serum-normal and tumor genomes, and 1000 Genomes to serve as control group. The Biological Language Modelling Toolkit (BLMT) computes palindromes in whole genomes. We developed a computational pipeline integrating BLMT to compute and compare prevalence of palindromes in personal genomes. We carried out a pilot study on chr 8 and chr 11 taking into account single nucleotide polymorphisms, insertions and deletions. Of all the palindromes that showed any variation in cancer genomes, 38% of what were near breast cancer genes happened to be the most differentiated palindromes in tumor (i.e. they ranked among the top 25% by our heuristic measure). These results will shed light on the prevalence of palindromes in oncogenes and the mutations that are present in the palindromic regions that could contribute to genomic rearrangements, and breast cancer progression.
- 5 December 2016
- Published by Springer Nature in BMC Medical Genomics
- Vol. 9 (S3) , 73
Open AccessA pilot study on the prevalence of DNA palindromes in breast cancer genomes
DNA palindromes are a unique pattern of repeat sequences that are present in the human genome. It consists of a sequence of nucleotides in which the second half is the complement of the first half but appearing in reverse order. These palindromic sequences may have a significant role in DNA replication, transcription and gene regulation processes. They occur frequently in human cancers by clustering at specific locations of the genome that undergo gene amplification and tumorigenesis. Moreover, some studies showed that palindromes are clustered in amplified regions of breast cancer genomes especially in chromosomes (chr) 8 and 11. With the large number of personal genomes and cancer genomes becoming available, it is now possible to study their association to diseases using computational methods. Here, we conducted a pilot study on chromosomes 8 and 11 of cancer genomes to identify computationally the differentially occurring palindromes. We processed 69 breast cancer genomes from The Cancer Genome Atlas including serum-normal and tumor genomes, and 1000 Genomes to serve as control group. The Biological Language Modelling Toolkit (BLMT) computes palindromes in whole genomes. We developed a computational pipeline integrating BLMT to compute and compare prevalence of palindromes in personal genomes. We carried out a pilot study on chr 8 and chr 11 taking into account single nucleotide polymorphisms, insertions and deletions. Of all the palindromes that showed any variation in cancer genomes, 38% of what were near breast cancer genes happened to be the most differentiated palindromes in tumor (i.e. they ranked among the top 25% by our heuristic measure). These results will shed light on the prevalence of palindromes in oncogenes and the mutations that are present in the palindromic regions that could contribute to genomic rearrangements, and breast cancer progression.
- Open Access
- 5 October 2016
- Published by MDPI AG in Preprints.org
Bio-Resource Exchange: Study of Prevalence of Antibody Donation and Development of a Web Portal to Facilitate it
Bio-molecular reagents like antibodies required in experimental biology are expensive and their effectiveness, among other things, is critical to the success of the experiment. Although such resources are sometimes donated by one investigator to another through personal communication between the two, there is no previous study to our knowledge on the extent of such donations, nor a central platform that directs resource seekers to donors. In this paper, we describe, to our knowledge, a first attempt at building a web-portal titled Bio-Resource Exchange that attempts to bridge this gap between resource seekers and donors in the domain of experimental biology. Users on this portal can request for or donate antibodies, cell-lines and DNA Constructs. This resource could also serve as a crowd-sourced database of resources for experimental biology. Further, in order to index donations outside of our portal, we mined scientific articles to find instances of donations of antibodies and attempted to extract information about these donations at the finest granularity. Specifically, we extracted the name of the donor, his/her affiliation and the name of the antibody for every donation by parsing the acknowledgements sections of articles. To extract annotations at this level, we propose two approaches – a rule based algorithm and a bootstrapped relation learning algorithm. The algorithms extracted donor names, affiliations and antibody names with average accuracies of 57% and 62% respectively. We also created a dataset of 50 expert-annotated acknowledgements sections that will serve as a gold standard dataset to evaluate extraction algorithms in the future. Contact: madhavi@pitt.edu, madhavi@cs.cmu.edu Database URL: http://tonks.dbmi.pitt.edu/brx Supplementary information: Supplementary data are available at Database online.
- 5 October 2016
- Published by MDPI AG in Preprints.org
Open AccessBio-Resource Exchange: Study of Prevalence of Antibody Donation and Development of a Web Portal to Facilitate it
Bio-molecular reagents like antibodies required in experimental biology are expensive and their effectiveness, among other things, is critical to the success of the experiment. Although such resources are sometimes donated by one investigator to another through personal communication between the two, there is no previous study to our knowledge on the extent of such donations, nor a central platform that directs resource seekers to donors. In this paper, we describe, to our knowledge, a first attempt at building a web-portal titled Bio-Resource Exchange that attempts to bridge this gap between resource seekers and donors in the domain of experimental biology. Users on this portal can request for or donate antibodies, cell-lines and DNA Constructs. This resource could also serve as a crowd-sourced database of resources for experimental biology. Further, in order to index donations outside of our portal, we mined scientific articles to find instances of donations of antibodies and attempted to extract information about these donations at the finest granularity. Specifically, we extracted the name of the donor, his/her affiliation and the name of the antibody for every donation by parsing the acknowledgements sections of articles. To extract annotations at this level, we propose two approaches – a rule based algorithm and a bootstrapped relation learning algorithm. The algorithms extracted donor names, affiliations and antibody names with average accuracies of 57% and 62% respectively. We also created a dataset of 50 expert-annotated acknowledgements sections that will serve as a gold standard dataset to evaluate extraction algorithms in the future. Contact: madhavi@pitt.edu, madhavi@cs.cmu.edu Database URL: http://tonks.dbmi.pitt.edu/brx Supplementary information: Supplementary data are available at Database online.
- Open Access
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
Neural Architectures for Named Entity Recognition
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
Open AccessNeural Architectures for Named Entity Recognition
- 7 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 15 (4) , 1239-1246
Towards Extracting Supporting Information About Predicted Protein-Protein Interactions
One of the goals of relation extraction is to identify protein-protein interactions (PPIs) in biomedical literature. Current systems are capturing binary relations and also the direction and type of an interaction. Besides assisting in the curation PPIs into databases, there has been little real-world application of these algorithms. We describe UPSITE, a text mining tool for extracting evidence in support of a hypothesized interaction. Given a predicted PPI, UPSITE uses a binary relation detector to check whether a PPI is found in abstracts in PubMed. If it is not found, UPSITE retrieves documents relevant to each of the two proteins separately, and extracts contextual information about biological events surrounding each protein, and calculates semantic similarity of the two proteins to provide evidential support for the predicted PPI. In evaluations, relation extraction achieved an Fscore of 0.88 on the HPRD50 corpus, and semantic similarity measured with angular distance was found to be statistically significant. With the development of PPI prediction algorithms, the burden of interpreting the validity and relevance of novel PPIs is on biologists. We suggest that presenting annotations of the two proteins in a PPI side-by-side and a score that quantifies their similarity lessens this burden to some extent.
- 7 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 15 (4) , 1239-1246
Towards Extracting Supporting Information About Predicted Protein-Protein Interactions
One of the goals of relation extraction is to identify protein-protein interactions (PPIs) in biomedical literature. Current systems are capturing binary relations and also the direction and type of an interaction. Besides assisting in the curation PPIs into databases, there has been little real-world application of these algorithms. We describe UPSITE, a text mining tool for extracting evidence in support of a hypothesized interaction. Given a predicted PPI, UPSITE uses a binary relation detector to check whether a PPI is found in abstracts in PubMed. If it is not found, UPSITE retrieves documents relevant to each of the two proteins separately, and extracts contextual information about biological events surrounding each protein, and calculates semantic similarity of the two proteins to provide evidential support for the predicted PPI. In evaluations, relation extraction achieved an Fscore of 0.88 on the HPRD50 corpus, and semantic similarity measured with angular distance was found to be statistically significant. With the development of PPI prediction algorithms, the burden of interpreting the validity and relevance of novel PPIs is on biologists. We suggest that presenting annotations of the two proteins in a PPI side-by-side and a score that quantifies their similarity lessens this burden to some extent.