Structured prediction models for RNN based sequence labeling in clinical text
Open accessAbstract
Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies for structured prediction in order to improve the exact phrase detection of various medical entities.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
RNN is mainly applied in the area of speech processing and NLP contexts.
“RNN is mainly applied in the area of speech processing and NLP contexts [66, 67].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [67]
The Introduction (page unavailable) says RNN models have increasingly been used for NLP tasks, supporting the NLP portion of the claim. The cited paper does not establish that RNNs are mainly applied in speech processing and NLP, or discuss speech processing as an application. (LLM, conf=0.84)
Experimental — accuracy not yet measuredTraditional algorithms face challenges in analyzing EHR data because such algorithms are not suitable for dealing with huge columns of data.
“traditional algorithms also face challenges in analyzing EHR data due as such algorithms are not suitable for dealing with huge columns of data [44].”
From Secondary Use of Electronic Health Record: Opportunities and Challenges (2020) · cites this paper as [44]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 24 · Cited by 215
- Authors
- Jagannatha, A., & yu, H.
- Affiliations
- Edith Nourse Rogers Memorial Veterans Hospital (US)
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Volume
- 2016
- Pages
- 856-865
- PMC
- PMC5167535
- OpenAlex
- W2488984245
- Cited by
- 215
- References
- 24
- Citations by year
- 2026: 5 · 2025: 12 · 2024: 13 · 2023: 24 · 2022: 16 · 2021: 29 · 2020: 32 · 2019: 50 · 2018: 22 · 2017: 12
- FWCI
- 112.46
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. Department of Veterans Affairs (I01 HX001457)
- National Institutes of Health
- National Heart, Lung, and Blood Institute (R01HL125089, R01HL135219)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- sequence labeling, clinical text, named entity recognition, information extraction, electronic health records, recurrent neural networks, conditional random fields, pair potential, medication extraction, structured prediction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
