Infusing factual knowledge into pre-trained models is fundamental for many knowledge-intensive tasks. In this paper, we proposed Mixture-of-Partitions (MoP), an infusion approach that can handle a very large knowledge graph (KG) by partitioning it in
to smaller sub-graphs and infusing their specific knowledge into various BERT models using lightweight adapters. To leverage the overall factual knowledge for a target task, these sub-graph adapters are further fine-tuned along with the underlying BERT through a mixture layer. We evaluate our MoP with three biomedical BERTs (SciBERT, BioBERT, PubmedBERT) on six downstream tasks (inc. NLI, QA, Classification), and the results show that our MoP consistently enhances the underlying BERTs in task performance, and achieves new SOTA performances on five evaluated datasets.
In this paper we present the FJWU's system submitted to the biomedical shared task at WMT21. We prepared state-of-the-art multilingual neural machine translation systems for three languages (i.e. German, Spanish and French) with English as target lan
guage. Our NMT systems based on Transformer architecture, were trained on combination of in-domain and out-domain parallel corpora developed using Information Retrieval (IR) and domain adaptation techniques.
This paper describes the Fujitsu DMATH systems used for WMT 2021 News Translation and Biomedical Translation tasks. We focused on low-resource pairs, using a simple system. We conducted experiments on English-Hausa, Xhosa-Zulu and English-Basque, and
submitted the results for Xhosa→Zulu in the News Translation Task, and English→Basque in the Biomedical Translation Task, abstract and terminology translation subtasks. Our system combines BPE dropout, sub-subword features and back-translation with a Transformer (base) model, achieving good results on the evaluation sets.
We report the results of the WMT 2021 shared task on Quality Estimation, where the challenge is to predict the quality of the output of neural machine translation systems at the word and sentence levels. This edition focused on two main novel additio
ns: (i) prediction for unseen languages, i.e. zero-shot settings, and (ii) prediction of sentences with catastrophic errors. In addition, new data was released for a number of languages, especially post-edited data. Participating teams from 19 institutions submitted altogether 1263 systems to different task variants and language pairs.
Medical question answering (QA) systems have the potential to answer clinicians' uncertainties about treatment and diagnosis on-demand, informed by the latest evidence. However, despite the significant progress in general QA made by the NLP community
, medical QA systems are still not widely used in clinical environments. One likely reason for this is that clinicians may not readily trust QA system outputs, in part because transparency, trustworthiness, and provenance have not been key considerations in the design of such models. In this paper we discuss a set of criteria that, if met, we argue would likely increase the utility of biomedical QA systems, which may in turn lead to adoption of such systems in practice. We assess existing models, tasks, and datasets with respect to these criteria, highlighting shortcomings of previously proposed approaches and pointing toward what might be more usable QA systems.
In the sixth edition of the WMT Biomedical Task, we addressed a total of eight language pairs, namely English/German, English/French, English/Spanish, English/Portuguese, English/Chinese, English/Russian, English/Italian, and English/Basque. Further,
our tests were composed of three types of textual test sets. New to this year, we released a test set of summaries of animal experiments, in addition to the test sets of scientific abstracts and terminologies. We received a total of 107 submissions from 15 teams from 6 countries.
Biomedical Named Entities are complex, so approximate matching has been used to improve entity coverage. However, the usual approximate matching approach fetches only one matching result, which is often noisy. In this work, we propose a method for bi
omedical NER that fetches multiple approximate matches for a given phrase to leverage their variations to estimate entity-likeness. The model uses pooling to discard the unnecessary information from the noisy matching results, and learn the entity-likeness of the phrase with multiple approximate matches. Experimental results on three benchmark datasets from the biomedical domain, BC2GM, NCBI-disease, and BC4CHEMD, demonstrate the effectiveness. Our model improves the average by up to +0.21 points compared to a BioBERT-based NER.
Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks
such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologies with 4M+ concepts. In contrast with previous pipeline-based hybrid systems, SapBERT offers an elegant one-model-for-all solution to the problem of medical entity linking (MEL), achieving a new state-of-the-art (SOTA) on six MEL benchmarking datasets. In the scientific domain, we achieve SOTA even without task-specific supervision. With substantial improvement over various domain-specific pretrained MLMs such as BioBERT, SciBERTand and PubMedBERT, our pretraining scheme proves to be both effective and robust.
Biomaterials are synthetic or natural materials used for constructing artificial organs, fabricating prostheses, or replacing tissues. The last century saw the development of thousands of novel biomaterials and, as a result, an exponential increase i
n scientific publications in the field. Large-scale analysis of biomaterials and their performance could enable data-driven material selection and implant design. However, such analysis requires identification and organization of concepts, such as materials and structures, from published texts. To facilitate future information extraction and the application of machine-learning techniques, we developed a semantic annotator specifically tailored for the biomaterials literature. The Biomaterials Annotator has been implemented following a modular organization using software containers for the different components and orchestrated using Nextflow as workflow manager. Natural language processing (NLP) components are mainly developed in Java. This set-up has allowed named entity recognition of seventeen classes relevant to the biomaterials domain. Here we detail the development, evaluation and performance of the system, as well as the release of the first collection of annotated biomaterials abstracts. We make both the corpus and system available to the community to promote future efforts in the field and contribute towards its sustainability.
Introducing biomedical informatics (BMI) students to natural language processing (NLP) requires balancing technical depth with practical know-how to address application-focused needs. We developed a set of three activities introducing introductory BM
I students to information retrieval with NLP, covering document representation strategies and language models from TF-IDF to BERT. These activities provide students with hands-on experience targeted towards common use cases, and introduce fundamental components of NLP workflows for a wide variety of applications.
