An official website of the United States government
Systematic reviews (SRs) are a crucial component of evidence-based clinical practice. Unfortunately, SRs are labor-intensive and unscalable with the exponential growth in literature. Automating evidence synthesis using machine learning models has been proposed but solely focuses on the text and ignores additional features like citation information. Recent work demonstrated that citation embeddings can outperform the text itself, suggesting that better network representation may expedite SRs. Yet, how to utilize the rich information in heterogeneous information networks (HIN) for network embeddings is understudied. Existing HIN models fail to produce a high-quality embedding compared to simply running state-of-the-art homogeneous network models. To address existing HIN model limitations, we propose SR-CoMbEr, a community-based multi-view graph convolutional network for learning better embeddings for evidence synthesis. Our model automatically discovers article communities to learn robust embeddings that simultaneously encapsulate the rich semantics in HINs. We demonstrate the effectiveness of our model to automate 15 SRs.
more »
« less
Textual Evidence Mining via Spherical Heterogeneous Information Network Embedding
Scientific literature, as one of the major knowledge resources, provides abundant textual evidence that has great potential to support high-quality scientific hypothesis validation. In this paper, we study the problem of textual evidence mining in scientific literature: given a scientific hypothesis as a query triplet, find the textual evidence sentences in scientific literature that support the input query. A critical challenge for textual evidence mining in scientific literature is to retrieve high-quality textual evidence without human supervision. Because it is non-trivial to obtain a large set of human-annotated articles con-taining evidence sentences in scientific literature. To tackle this challenge, we propose EVIDENCEMINER, a high-quality textual evidence retrieval method for scientific literature without human-annotated training examples. To achieve high-quality textual evidence retrieval, we leverage heterogeneous information from both existing knowledge bases and massive unstructured text. We propose to construct a large heterogeneous information network (HIN) to build connections between the user-input queries and the candidate evidence sentences. Based on the constructed HIN, we propose a novel HIN embedding method that directly embeds the nodes onto a spherical space to improve the retrieval performance. Quantitative experiments on a huge biomedical literature corpus (over 4 million sentences) demonstrate that EVIDENCEMINER significantly outperforms baseline methods for unsupervised textual evidence retrieval. Case studies also demonstrate that our HIN construction and embedding greatly benefit many downstream applications such as textual evidence interpretation and synonym meta-pattern discovery.
more »
« less
- PAR ID:
- 10279811
- Date Published:
- Journal Name:
- BigData'20: IEEE 2020 Int. Conf. on Big Data, Dec. 2020
- Volume:
- 2020
- Issue:
- 1
- Page Range / eLocation ID:
- 828 to 837
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)As heterogeneous networks have become increasingly ubiquitous, Heterogeneous Information Network (HIN) embedding, aiming to project nodes into a low-dimensional space while preserving the heterogeneous structure, has drawn increasing attention in recent years. Many of the existing HIN embedding methods adopt meta-path guided random walk to retain both the semantics and structural correlations between different types of nodes. However, the selection of meta-paths is still an open problem, which either depends on domain knowledge or is learned from label information. As a uniform blueprint of HIN, the network schema comprehensively embraces the high-order structure and contains rich semantics. In this paper, we make the first attempt to study network schema preserving HIN embedding, and propose a novel model named NSHE. In NSHE, a network schema sampling method is first proposed to generate sub-graphs (i.e., schema instances), and then multi-task learning task is built to preserve the heterogeneous structure of each schema instance. Besides preserving pairwise structure information, NSHE is able to retain high-order structure (i.e., network schema). Extensive experiments on three real-world datasets demonstrate that our proposed model NSHE significantly outperforms the state-of-the-art methods.more » « less
-
Karin Verspoor, Kevin Bretonnel (Ed.)In a recent project, the Language Applications Grid was augmented to support the mining of scientific publications. The results of that effort have now been repurposed to focus on Covid-19 literature, including modification of the LAPPS Grid “AskMe” query and retrieval engine. We describe the AskMe system and discuss its functionality as compared to other query engines available to search covid-related publications.more » « less
-
Abstract Scientific literature is one of the most significant resources for sharing knowledge. Researchers turn to scientific literature as a first step in designing an experiment. Given the extensive and growing volume of literature, the common approach of reading and manually extracting knowledge is too time consuming, creating a bottleneck in the research cycle. This challenge spans nearly every scientific domain. For the materials science, experimental data distributed across millions of publications are extremely helpful for predicting materials properties and the design of novel materials. However, only recently researchers have explored computational approaches for knowledge extraction primarily for inorganic materials. This study aims to explore knowledge extraction for organic materials. We built a research dataset composed of 855 annotated and 708,376 unannotated sentences drawn from 92,667 abstracts. We used named‐entity‐recognition (NER) with BiLSTM‐CNN‐CRF deep learning model to automatically extract key knowledge from literature. Early‐phase results show a high potential for automated knowledge extraction. The paper presents our findings and a framework for supervised knowledge extraction that can be adapted to other scientific domains.more » « less
-
Textual entailment models are increasingly applied in settings like fact-checking, presupposition verification in question answering, or summary evaluation. However, these represent a significant domain shift from existing entailment datasets, and models underperform as a result. We propose WiCE, a new fine-grained textual entailment dataset built on natural claim and evidence pairs extracted from Wikipedia. In addition to standard claim-level entailment, WiCE provides entailment judgments over sub-sentence units of the claim, and a minimal subset of evidence sentences that support each subclaim. To support this, we propose an automatic claim decomposition strategy using GPT-3.5 which we show is also effective at improving entailment models’ performance on multiple datasets at test time. Finally, we show that real claims in our dataset involve challenging verification and retrieval problems that existing models fail to address.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/BigData50022.2020.9377958
