Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization

  title={Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization},
  author={Jiho Noh and Ramakanth Kavuluru},
  journal={Findings of the Association for Computational Linguistics: EMNLP 2020},
Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to the patient. Other factors such as demographic attributes, comorbidities, and social determinants may also be pertinent. As such, the retrieval problem is often formulated as ad hoc search but with multiple facets (e.g., disease, mutation) that may need to… 

Figures and Tables from this paper

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

This paper proposes an Unsupervised Document Expansion with Generation (UDEG) framework with a pre-trained language model, which generates diverse supplementary sentences for the original document without using labels on query-document pairs for training.

Improved Biomedical Word Embeddings in the Transformer Era

An Analysis of the Interaction between Ancient Literature Informatization Project and Classical Literature Research Based on Intelligent Computing

  • Jinjin Ma
  • Computer Science
    Mathematical Problems in Engineering
  • 2022
The ancient literature informatization project based on intelligent computing and classical literature research can build a good relationship through interaction, and the work in this area has achieved the initial results.



Designing retrieval models to contrast precision-driven ad hoc search vs. recall-driven treatment extraction in Precision Medicine

The team participated in both tasks of the TREC 2019 Precision Medicine Track, relative to scientific abstracts and clinical trials, and tested two strategies to re-rank the abstracts set in order to have a large variety of treatments returned in the top articles.

Document Retrieval for Biomedical Question Answering with Neural Sentence Matching

  • Jiho NohRamakanth Kavuluru
  • Computer Science
    2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)
  • 2018
An effective biomedical DR system that relies on relevant answer snippets in the BioASQ training datasets and builds an effective question-answer sentence matching neural network that learns a measure of relevance of a sentence to an input question in the form of a matching score.

JULIE Lab & Med Uni Graz @ TREC 2019 Precision Medicine Track

The 2019 Precision Medicine Track at TREC (TREC-PM) aimed at identifying relevant documents from two collections, namely PubMed (biomedical abstracts) and (clinical trials), given

State-of-the-art in biomedical literature retrieval for clinical cases: a survey of the TREC 2014 CDS track

An overview of the task, a survey of the information retrieval methods employed by the participants, an analysis of the results, and a discussion on the future directions for this challenging yet important task are provided.

Overview of the TREC 2020 Precision Medicine Track

The TREC Precision Medicine track was launched to specialize the CDS track to the needs of precision medicine so IR systems can focus on this important issue, and for three years the TREC Clinical Decision Support track sought to evaluate IR systems that provide medical evidence at the point ofcare.

Task-Oriented Query Reformulation with Reinforcement Learning

This work introduces a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned and trains this neural network with reinforcement learning.

Generalizing biomedical relation classification with neural adversarial domain adaptation

This work presents a novel adversarial learning algorithm for unsupervised domain adaptation tasks where no labeled data are available in the target domain and takes advantage of unlabeled data to improve biased classifiers through learning domain-invariant features via an adversarial process.

Text Summarization with Pretrained Encoders

This paper introduces a novel document-level encoder based on BERT which is able to express the semantics of a document and obtain representations for its sentences and proposes a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two.