Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis

Eben Holderness, Antonio Jimeno Yepes, Alberto Lavelli, Anne-Lyse Minard, James Pustejovsky, Fabio Rinaldi (Editors)

Anthology ID:
EACL | Louhi
Association for Computational Linguistics
Bib Export formats:

pdf bib
Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis
Eben Holderness | Antonio Jimeno Yepes | Alberto Lavelli | Anne-Lyse Minard | James Pustejovsky | Fabio Rinaldi

pdf bib
Understanding Social Support Expressed in a COVID-19 Online ForumCOVID-19 Online Forum
Anietie Andy | Brian Chu | Ramie Fathy | Barrington Bennett | Daniel Stokes | Sharath Chandra Guntuku

In online forums focused on health and wellbeing, individuals tend to seek and give the following social support : emotional and informational support. Understanding the expressions of these social supports in an online COVID- 19 forum is important for : (a) the forum and its members to provide the right type of support to individuals and (b) determining the long term effects of the COVID-19 pandemic on the well-being of the public, thereby informing interventions. In this work, we build four machine learning models to measure the extent of the following social supports expressed in each post in a COVID-19 online forum : (a) emotional support given (b) emotional support sought (c) informational support given, and (d) informational support sought. Using these models, we aim to : (i) determine if there is a correlation between the different social supports expressed in posts e.g. when members of the forum give emotional support in posts, do they also tend to give or seek informational support in the same post? (ii) determine how these social supports sought and given changes over time in published posts. We find that (i) there is a positive correlation between the informational support given in posts and the emotional support given and emotional support sought, respectively, in these posts and (ii) over time, users tended to seek more emotional support and give less emotional support.

pdf bib
Integrating Higher-Level Semantics into Robust Biomedical Name Representations
Pieter Fivez | Simon Suster | Walter Daelemans

Neural encoders of biomedical names are typically considered robust if representations can be effectively exploited for various downstream NLP tasks. To achieve this, encoders need to model domain-specific biomedical semantics while rivaling the universal applicability of pretrained self-supervised representations. Previous work on robust representations has focused on learning low-level distinctions between names of fine-grained biomedical concepts. These fine-grained concepts can also be clustered together to reflect higher-level, more general semantic distinctions, such as grouping the names nettle sting and tick-borne fever together under the description puncture wound of skin. It has not yet been empirically confirmed that training biomedical name encoders on fine-grained distinctions automatically leads to bottom-up encoding of such higher-level semantics. In this paper, we show that this bottom-up effect exists, but that it is still relatively limited. As a solution, we propose a scalable multi-task training regime for biomedical name encoders which can also learn robust representations using only higher-level semantic classes. These representations can generalise both bottom-up as well as top-down among various semantic hierarchies. Moreover, we show how they can be used out-of-the-box for improved unsupervised detection of hypernyms, while retaining robust performance on various semantic relatedness benchmarks.

pdf bib
FuzzyBIO : A Proposal for Fuzzy Representation of Discontinuous EntitiesFuzzyBIO: A Proposal for Fuzzy Representation of Discontinuous Entities
Anne Dirkson | Suzan Verberne | Wessel Kraaij

Discontinuous entities pose a challenge to named entity recognition (NER). These phenomena occur commonly in the biomedical domain. As a solution, expansions of the BIO representation scheme that can handle these entity types are commonly used (i.e. BIOHD). However, the extra tag types make the NER task more difficult to learn. In this paper we propose an alternative ; a fuzzy continuous BIO scheme (FuzzyBIO). We focus on the task of Adverse Drug Response extraction and normalization to compare FuzzyBIO to BIOHD. We find that FuzzyBIO improves recall of NER for two of three data sets and results in a higher percentage of correctly identified disjoint and composite entities for all data sets. Using FuzzyBIO also improves end-to-end performance for continuous and composite entities in two of three data sets. Since FuzzyBIO improves performance for some data sets and the conversion from BIOHD to FuzzyBIO is straightforward, we recommend investigating which is more effective for any data set containing discontinuous entities.

pdf bib
Scientific Claim Verification with VerT5eriniVerT5erini
Ronak Pradeep | Xueguang Ma | Rodrigo Nogueira | Jimmy Lin

This work describes the adaptation of a pretrained sequence-to-sequence model to the task of scientific claim verification in the biomedical domain. We propose a system called VerT5erini that exploits T5 for abstract retrieval, sentence selection, and label prediction, which are three critical sub-tasks of claim verification. We evaluate our pipeline on SciFACT, a newly curated dataset that requires models to not just predict the veracity of claims but also provide relevant sentences from a corpus of scientific literature that support the prediction. Empirically, our system outperforms a strong baseline in each of the three sub-tasks. We further show VerT5erini’s ability to generalize to two new datasets of COVID-19 claims using evidence from the CORD-19 corpus.