Robert E. Mercer
YOU?
Author Swipe
View article: Trustworthy Medical Question Answering: An Evaluation-Centric Survey
Trustworthy Medical Question Answering: An Evaluation-Centric Survey Open
Trustworthiness in healthcare question-answering (QA) systems is important for ensuring patient safety, clinical effectiveness, and user confidence. As large language models (LLMs) become increasingly integrated into medical settings, the …
View article: Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification
Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification Open
Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchi…
View article: Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation
Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation Open
The International Classification of Diseases (ICD) serves as a definitive medical classification system encompassing a wide range of diseases and conditions. The primary objective of ICD indexing is to allocate a subset of ICD codes to a m…
View article: Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification
Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification Open
The International Classification of Diseases (ICD) is an authoritative medical classification system of different diseases and conditions for clinical and management purposes. ICD indexing assigns a subset of ICD codes to a medical record.…
View article: Investigating the Learning Behaviour of In-Context Learning: A Comparison with Supervised Learning
Investigating the Learning Behaviour of In-Context Learning: A Comparison with Supervised Learning Open
Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL), where learning a new task from just a few training examples is done without being explicitly pre-trained. However, despite the success of LLMs, ther…
View article: Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning
Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning Open
Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL), where learning a new task from just a few training examples is done without being explicitly pre-trained. However, despite the success of LLMs, ther…
View article: Personality Trait Detection using an Hierarchy of Tree-transformers and Graph Attention Network
Personality Trait Detection using an Hierarchy of Tree-transformers and Graph Attention Network Open
Automatic personality trait detection from a personâs writings is helpful for professionals to assess the mental health of an individual, as well as helping individuals to determine their strengths and weaknesses for making choices such …
View article: A skin lesion hair mask dataset with fine-grained annotations
A skin lesion hair mask dataset with fine-grained annotations Open
Occlusion of skin lesions in dermoscopic images due to hair affects the performance of computer-assisted lesion analysis algorithms. Lesion analysis can benefit from digital hair removal or realistic hair simulation techniques. To assist i…
View article: Identifying Protein-Protein Interaction using Tree-Transformers and Heterogeneous Graph Neural Network
Identifying Protein-Protein Interaction using Tree-Transformers and Heterogeneous Graph Neural Network Open
For a better understanding of the underlying biological mechanisms, it is crucial to identify the reciprocity between proteins. Often, extracting such interactions between proteins from biomedical articles faces challenges due to the compl…
View article: Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII
Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII Open
The BioCreative National Library of Medicine (NLM)-Chem track calls for a community effort to fine-tune automated recognition of chemical names in the biomedical literature. Chemicals are one of the most searched biomedical entities in Pub…
View article: Generating Extractive and Abstractive Summaries in Parallel from Scientific Articles Incorporating Citing Statements
Generating Extractive and Abstractive Summaries in Parallel from Scientific Articles Incorporating Citing Statements Open
Summarization of scientific articles often overlooks insights from citing papers, focusing solely on the document’s content. To incorporate citation contexts, we develop a model to summarize a scientific document using the information in t…
View article: Extracting Drug-Drug and Protein-Protein Interactions from Text using a Continuous Update of Tree-Transformers
Extracting Drug-Drug and Protein-Protein Interactions from Text using a Continuous Update of Tree-Transformers Open
Understanding biological mechanisms requires determining mutual protein-protein interactions (PPI). Obtaining drug-drug interactions (DDI) from scientific articles provides important information about drugs. Extracting such medical entity …
View article: Tension Analysis in Survivor Interviews: A Computational Approach
Tension Analysis in Survivor Interviews: A Computational Approach Open
This study aims to develop computational techniques to analyze and identify points of tensions in interviews with survivors of the 1994 Rwandan genocide. Oral history interviews are a dialogical source composed of questions and answers, pr…
View article: Protein-Protein Interaction Extraction using Attention-based Tree-Structured Neural Network Models
Protein-Protein Interaction Extraction using Attention-based Tree-Structured Neural Network Models Open
In order to comprehend underlying biological processes, it is necessary to identify interactions between proteins. It is typically quite difficult to extract a protein-protein interaction (PPI) from text data as text data is complex in nat…
View article: MeSHup: A Corpus for Full Text Biomedical Document Indexing
MeSHup: A Corpus for Full Text Biomedical Document Indexing Open
Medical Subject Heading (MeSH) indexing refers to the problem of assigning a given biomedical document with the most relevant labels from an extremely large set of MeSH terms. Currently, the vast number of biomedical articles in the PubMed…
View article: Evaluation Benchmarks for Spanish Sentence Representations
Evaluation Benchmarks for Spanish Sentence Representations Open
Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate these models. In the case of Spanish, there are few ways t…
View article: KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling
KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling Open
Currently, Medical Subject Headings (MeSH) are manually assigned to every biomedical article published and subsequently recorded in the PubMed database to facilitate retrieving relevant information. With the rapid growth of the PubMed data…
View article: BioCite: A Deep Learning-based Citation Linkage Framework for Biomedical Research Articles
BioCite: A Deep Learning-based Citation Linkage Framework for Biomedical Research Articles Open
Research papers reflect scientific advances. Citations are widely used in research publications to support the new findings and show their benefits, while also regulating the information flow to make the contents clearer for the audience. …
View article: Privacy Preference Inference via Collaborative Filtering
Privacy Preference Inference via Collaborative Filtering Open
Studies of online social behaviour indicate that users often fail to specify privacy settings that match their privacy behaviour. This issue has caused a dilemma whether to use publicly available data for targeted advertisement and persona…
View article: An Experimental Comparison of the Geometry of Models Trained on Natural Language and Synthetic Data
An Experimental Comparison of the Geometry of Models Trained on Natural Language and Synthetic Data Open
Deep learning models have been used successfully to solve many Natural Language Processing problems, but less is known about the mechanisms that make them work. Unlike simpler models that can be understood mathematically, experimental comp…
View article: Encoding Dependency Information inside Tree Transformer
Encoding Dependency Information inside Tree Transformer Open
Representing a sentence in a high dimensional space is fundamental for most natural language processing (NLP) tasks at present. These representations depend on the underlying structures upon which they are built. Two scenarios are possible…
View article: Modelling Sentence Pairs via Reinforcement Learning: An Actor-Critic Approach to Learn the Irrelevant Words
Modelling Sentence Pairs via Reinforcement Learning: An Actor-Critic Approach to Learn the Irrelevant Words Open
Learning sentence representation is a fundamental task in Natural Language Processing. Most of the existing sentence pair modelling architectures focus only on extracting and using the rich sentence pair features. The drawback of utilizing…
View article: Investigating Citation Linkage as a Sentence Similarity Measurement Task Using Deep Learning
Investigating Citation Linkage as a Sentence Similarity Measurement Task Using Deep Learning Open
Research publications reflect advancements in the corresponding research domain. In these research publications, scientists often use citations to bolster the presented research findings and portray the improvements that come with these fi…
View article: Multi-Channel Convolutional Neural Network for Twitter Emotion and Sentiment Recognition
Multi-Channel Convolutional Neural Network for Twitter Emotion and Sentiment Recognition Open
Jumayel Islam, Robert E. Mercer, Lu Xiao. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.
View article: Incorporating Figure Captions and Descriptive Text in MeSH Term Indexing
Incorporating Figure Captions and Descriptive Text in MeSH Term Indexing Open
The goal of text classification is to automatically assign categories to documents. Deep learning automatically learns effective features from data instead of adopting human-designed features. In this paper, we focus specifically on biomed…
View article: Annotation of Rhetorical Moves in Biochemistry Articles
Annotation of Rhetorical Moves in Biochemistry Articles Open
This paper focuses on the real world application of scientific writing and on determining rhetorical moves, an important step in establishing the argument structure of biomedical articles. Using the observation that the structure of schola…
View article: Identifying Protein-Protein Interaction Using Tree LSTM and Structured Attention
Identifying Protein-Protein Interaction Using Tree LSTM and Structured Attention Open
Identifying interactions between proteins is important to understand underlying biological processes. Extracting a protein-protein interaction (PPI) from the raw text is often very difficult. Previous supervised learning methods have used …
View article: Improving Tree-LSTM with Tree Attention
Improving Tree-LSTM with Tree Attention Open
In Natural Language Processing (NLP), we often need to extract information from tree topology. Sentence structure can be represented via a dependency tree or a constituency tree structure. For this reason, a variant of LSTMs, named Tree-LS…