A new family of information content models with an experimental survey on WordNet

Identifying the Question Similarity of Regulatory Documents in the Pharmaceutical Industry by Using the Recognizing Question Entailment System: Evaluation Study

BACKGROUND

The regulatory affairs (RA) division in a pharmaceutical establishment is the point of contact between regulatory authorities and pharmaceutical companies. They are delegated the crucial and strenuous task of extracting and summarizing relevant information in the most meticulous manner from various search systems. An artificial intelligence (AI)-based intelligent search system that can significantly bring down the manual efforts in the existing processes of the RA department while maintaining and improving the quality of final outcomes is desirable. We proposed a "frequently asked questions" component and its utility in an AI-based intelligent search system in this paper. The scenario is further complicated by the lack of publicly available relevant data sets in the RA domain to train the machine learning models that can facilitate cognitive search systems for regulatory authorities.

OBJECTIVE

In this study, we aimed to use AI-based intelligent computational models to automatically recognize semantically similar question pairs in the RA domain and evaluate the Recognizing Question Entailment-based system.

METHODS

We used transfer learning techniques and experimented with transformer-based models pretrained on corpora collected from different resources, such as Bidirectional Encoder Representations from Transformers (BERT), Clinical BERT, BioBERT, and BlueBERT. We used a manually labeled data set that contained 150 question pairs in the pharmaceutical regulatory domain to evaluate the performance of our model.

RESULTS

The Clinical BERT model performed better than other domain-specific BERT-based models in identifying question similarity from the RA domain. The BERT model had the best ability to learn domain-specific knowledge with transfer learning, which reached the best performance when fine-tuned with sufficient clinical domain question pairs. The top-performing model achieved an accuracy of 90.66% on the test set.

CONCLUSIONS

This study demonstrates the possibility of using pretrained language models to recognize question similarity in the pharmaceutical regulatory domain. Transformer-based models that are pretrained on clinical notes perform better than models pretrained on biomedical text in recognizing the question's semantic similarity in this domain. We also discuss the challenges of using data augmentation techniques to address the lack of relevant data in this domain. The results of our experiment indicated that increasing the number of training samples using back translation and entity replacement did not enhance the model's performance. This lack of improvement may be attributed to the intricate and specialized nature of texts in the regulatory domain. Our work provides the foundation for further studies that apply state-of-the-art linguistic models to regulatory documents in the pharmaceutical industry.

A reproducible experimental survey on biomedical sentence similarity: A string-based method sets the state of the art

This registered report introduces the largest, and for the first time, reproducible experimental survey on biomedical sentence similarity with the following aims: (1) to elucidate the state of the art of the problem; (2) to solve some reproducibility problems preventing the evaluation of most current methods; (3) to evaluate several unexplored sentence similarity methods; (4) to evaluate for the first time an unexplored benchmark, called Corpus-Transcriptional-Regulation (CTR); (5) to carry out a study on the impact of the pre-processing stages and Named Entity Recognition (NER) tools on the performance of the sentence similarity methods; and finally, (6) to bridge the lack of software and data reproducibility resources for methods and experiments in this line of research. Our reproducible experimental survey is based on a single software platform, which is provided with a detailed reproducibility protocol and dataset as supplementary material to allow the exact replication of all our experiments and results. In addition, we introduce a new aggregated string-based sentence similarity method, called LiBlock, together with eight variants of current ontology-based methods, and a new pre-trained word embedding model trained on the full-text articles in the PMC-BioC corpus. Our experiments show that our novel string-based measure establishes the new state of the art in sentence similarity analysis in the biomedical domain and significantly outperforms all the methods evaluated herein, with the only exception of one ontology-based method. Likewise, our experiments confirm that the pre-processing stages, and the choice of the NER tool for ontology-based methods, have a very significant impact on the performance of the sentence similarity methods. We also detail some drawbacks and limitations of current methods, and highlight the need to refine the current benchmarks. Finally, a notable finding is that our new string-based method significantly outperforms all state-of-the-art Machine Learning (ML) models evaluated herein.

HESML: a real-time semantic measures library for the biomedical domain with a reproducible survey

BACKGROUND

Ontology-based semantic similarity measures based on SNOMED-CT, MeSH, and Gene Ontology are being extensively used in many applications in biomedical text mining and genomics respectively, which has encouraged the development of semantic measures libraries based on the aforementioned ontologies. However, current state-of-the-art semantic measures libraries have some performance and scalability drawbacks derived from their ontology representations based on relational databases, or naive in-memory graph representations. Likewise, a recent reproducible survey on word similarity shows that one hybrid IC-based measure which integrates a shortest-path computation sets the state of the art in the family of ontology-based semantic measures. However, the lack of an efficient shortest-path algorithm for their real-time computation prevents both their practical use in any application and the use of any other path-based semantic similarity measure.

RESULTS

To bridge the two aforementioned gaps, this work introduces for the first time an updated version of the HESML Java software library especially designed for the biomedical domain, which implements the most efficient and scalable ontology representation reported in the literature, together with a new method for the approximation of the Dijkstra's algorithm for taxonomies, called Ancestors-based Shortest-Path Length (AncSPL), which allows the real-time computation of any path-based semantic similarity measure.

CONCLUSIONS

We introduce a set of reproducible benchmarks showing that HESML outperforms by several orders of magnitude the current state-of-the-art libraries in the three aforementioned biomedical ontologies, as well as the real-time performance and approximation quality of the new AncSPL shortest-path algorithm. Likewise, we show that AncSPL linearly scales regarding the dimension of the common ancestor subgraph regardless of the ontology size. Path-based measures based on the new AncSPL algorithm are up to six orders of magnitude faster than their exact implementation in large ontologies like SNOMED-CT and GO. Finally, we provide a detailed reproducibility protocol and dataset as supplementary material to allow the exact replication of all our experiments and results.

A New Family of Similarity Measures for Scoring Confidence of Protein Interactions Using Gene Ontology

The large-scale protein-protein interaction (PPI) data has the potential to play a significant role in the endeavor of understanding cellular processes. However, the presence of a considerable fraction of false positives is a bottleneck in realizing this potential. There have been continuous efforts to utilize complementary resources for scoring confidence of PPIs in a manner that false positive interactions get a low confidence score. Gene Ontology (GO), a taxonomy of biological terms to represent the properties of gene products and their relations, has been widely used for this purpose. We utilize GO to introduce a new set of specificity measures: Relative Depth Specificity (RDS), Relative Node-based Specificity (RNS), and Relative Edge-based Specificity (RES), leading to a new family of similarity measures. We use these similarity measures to obtain a confidence score for each PPI. We evaluate the new measures using four different benchmarks. We show that all the three measures are quite effective. Notably, RNS and RES more effectively distinguish true PPIs from false positives than the existing alternatives. RES also shows a robust set-discriminating power and can be useful for protein functional clustering as well.

Protocol for a reproducible experimental survey on biomedical sentence similarity

Measuring semantic similarity between sentences is a significant task in the fields of Natural Language Processing (NLP), Information Retrieval (IR), and biomedical text mining. For this reason, the proposal of sentence similarity methods for the biomedical domain has attracted a lot of attention in recent years. However, most sentence similarity methods and experimental results reported in the biomedical domain cannot be reproduced for multiple reasons as follows: the copying of previous results without confirmation, the lack of source code and data to replicate both methods and experiments, and the lack of a detailed definition of the experimental setup, among others. As a consequence of this reproducibility gap, the state of the problem can be neither elucidated nor new lines of research be soundly set. On the other hand, there are other significant gaps in the literature on biomedical sentence similarity as follows: (1) the evaluation of several unexplored sentence similarity methods which deserve to be studied; (2) the evaluation of an unexplored benchmark on biomedical sentence similarity, called Corpus-Transcriptional-Regulation (CTR); (3) a study on the impact of the pre-processing stage and Named Entity Recognition (NER) tools on the performance of the sentence similarity methods; and finally, (4) the lack of software and data resources for the reproducibility of methods and experiments in this line of research. Identified these open problems, this registered report introduces a detailed experimental setup, together with a categorization of the literature, to develop the largest, updated, and for the first time, reproducible experimental survey on biomedical sentence similarity. Our aforementioned experimental survey will be based on our own software replication and the evaluation of all methods being studied on the same software platform, which will be specially developed for this work, and it will become the first publicly available software library for biomedical sentence similarity. Finally, we will provide a very detailed reproducibility protocol and dataset as supplementary material to allow the exact replication of all our experiments and results.

Semantic concept model using Wikipedia semantic features

Wikipedia has become a high coverage knowledge source which has been used in many research areas such as natural language processing, text mining and information retrieval. Several methods have been introduced for extracting explicit or implicit relations from Wikipedia to represent semantics of concepts/words. However, the main challenge in semantic representation is how to incorporate different types of semantic relations to capture more semantic evidences of the associations of concepts. In this article, we propose a semantic concept model that incorporates different types of semantic features extracting from Wikipedia. For each concept that corresponds to an article, four semantic features are introduced: template links, categories, salient concepts and topics. The proposed model is based on the probability distributions that are defined for these semantic features of a Wikipedia concept. The template links and categories are the document-level features which are directly extracted from the structured information included in the article. On the other hand, the salient concepts and topics are corpus-level features which are extracted to capture implicit relations among concepts. For the salient concepts feature, the distributional-based method is utilised on the hypertext corpus to extract this feature for each Wikipedia concept. Then, the probability product kernel is used to improve the weight of each concept in this feature. For the topic feature, the Labelled latent Dirichlet allocation is adapted on the supervised multi-label of Wikipedia to train the probabilistic model of this feature. Finally, we used the linear interpolation for incorporating these semantic features into the probabilistic model to estimate the semantic relation probability of the specific concept over Wikipedia articles. The proposed model is evaluated on 12 benchmark datasets in three natural language processing tasks: measuring the semantic relatedness of concepts/words in general and in the biomedical domain, semantic textual relatedness measurement and measuring the semantic compositionality of noun compounds. The model is also compared with five methods that depends on separate semantic features in Wikipedia. Experimental results show that the proposed model achieves promising results in three tasks and outperforms the baseline methods in most of the evaluation datasets. This implies that incorporation of explicit and implicit semantic features is useful for representing semantics of concepts in Wikipedia.