Cross- & multi-lingual medication detection: a transformer-based analysis

While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable such transfer. Analyses involving pairs of natural languages are often inconclusive and contradictory since languages simultaneously differ in many linguistic aspects. In this paper, we perform a large-scale empirical study to isolate the effects of various linguistic properties by measuring zero-shot transfer between four diverse natural languages and their counterparts constructed by modifying aspects such as the script, word order, and syntax. Among other things, our experiments show that the absence of sub-word overlap significantly affects zero-shot transfer when languages differ in their word order, and there is a strong correlation between transfer performance and word embedding alignment between languages (e.g., R=0.94 on the task of NLI). Our results call for focus in multilingual models on explicitly improving word embedding alignment between languages rather than relying on its implicit emergence.

Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. While studies have shown that monolingual models produce better results than multilingual models, the training datasets must be sufficiently large. We trained a trilingual LitLat BERT-like model for Lithuanian, Latvian, and English, and a monolingual Est-RoBERTa model for Estonian. We evaluate their performance on four downstream tasks: named entity recognition, dependency parsing, part-of-speech tagging, and word analogy. To analyze the importance of focusing on a single language and the importance of a large training set, we compare created models with existing monolingual and multilingual BERT models for Estonian, Latvian, and Lithuanian. The results show that the newly created LitLat BERT and Est-RoBERTa models improve the results of existing models on all tested tasks in most situations.KeywordsNatural language processingBERTTransformersEstonianLatvianLithuanian

A complete inpatient electronic medical record contains a lot of information. In recent years, numerous researchers have carried out research on word segmentation of medical texts. Since the medical record text is written by free text, structuring the medical record text is an important part of the medical record intelligent analysis when these medical named entities are recognized. At present, named entity recognition methods are mainly divided into lexicographical and rule-based methods and machine learning-based methods. The machine learn-based approach takes the named entity recognition task as the annotation problem of sequence data, mainly considering the context information. The features commonly used in feature construction are contextual feature and dictionary features. BERT+LSTM+CRF were used to train the named entity recognition model. Open source CRF++ was adopted as the tool we relied on. We trained the LSTM+F model using the results of the original word segmentation and the information in the context as features. We carried out a 5-fold cross validation. The results showed that the overall F-1 score (MICRO-F) of named entity recognition reached 0.92, which confirmed that the model could accurately complete the task of medical named entity recognition.KeywordsWord segmentationNamed entity recognitionNatural language processing

Named Entity Recognition (NER) is a supervised machine learning task that finds various applications in automated content analysis, as the identification of entities is vital for understanding public discourse. However, sometimes the standard NER labels are not specific enough for a given domain. We introduce Public Entity Recognition (PER). PER is a domain-specific version of NER, that is trained for five entity types that are common to public discourse: politicians, parties, authorities, media, and journalists. PER can be used for pre-processing documents, in a pipeline with other classifiers or directly for analyzing information in texts. The taxonomy for PER is taken from the database of (German) public speakers and aims at low-threshold integration into computational social science research. We experiment with different training settings, involving weakly supervised training and training on manually annotated data. We evaluate multilingual transformer models of different sizes against rule-based entity matching and find that the models do not only outperform the baseline but also reach competitive absolute scores of around .8 and higher in F1. We further test for generalization and domain adaptation. We show that with only around 100–150 additional sentences, the model can be adapted to new languages.

Named Entity Recognition (NER) is increasingly applied to historical text analysis. However, differences in evaluation materials, metrics, and annotation guidelines across existing NER projects make it difficult to systematically compare different approaches to historical NER. This study addresses this issue by constructing an evaluation corpus through the normalization of four annotated datasets from the long 18th century. We evaluate the performance of the Edinburgh Geoparser, spaCy and BERT-based tool on this corpus using five evaluation modes. Results show that even under the most lenient criteria, the highest F1-score remains below 70%, highlighting the challenges of applying existing NER systems to historical texts. Through detailed error analysis, we identify common challenges such as spelling and formatting issues. These findings demonstrate the limitations of NER tools in historical documents. We argue that future work should involve collaboration with historians to ensure that evaluation corpus align with real user needs.

Automatic term extraction (ATE) is a natural language processing task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms. In this paper, we treat ATE as a sequence-labeling task and explore the efficacy of XLMR in evaluating cross-lingual and multilingual learning against monolingual learning in the cross-domain ATE context. Additionally, we introduce NOBI, a novel annotation mechanism enabling the labeling of single-word nested terms. Our experiments are conducted on the ACTER corpus, encompassing four domains and three languages (English, French, and Dutch), as well as the RSDO5 Slovenian corpus, encompassing four additional domains. Results indicate that cross-lingual and multilingual models outperform monolingual settings, showcasing improved F1-scores for all languages within the ACTER dataset. When incorporating an additional Slovenian corpus into the training set, the multilingual model exhibits superior performance compared to state-of-the-art approaches in specific scenarios. Moreover, the newly introduced NOBI labeling mechanism enhances the classifier’s capacity to extract short nested terms significantly, leading to substantial improvements in Recall for the ACTER dataset and consequentially boosting the overall F1-score performance.

BackgroundNatural Language Processing (NLP) applications have developed over the past years in various fields including its application to clinical free text for named entity recognition and relation extraction. However, there has been rapid developments the last few years that there's currently no overview of it. Moreover, it is unclear how these models and tools have been translated into clinical practice. We aim to synthesize and review these developments. MethodsWe reviewed literature from 2010 to date, searching PubMed, Scopus, the Association of Computational Linguistics (ACL), and Association of Computer Machinery (ACM) libraries for studies of NLP systems performing general-purpose (i.e., not disease- or treatment-specific) information extraction and relation extraction tasks in unstructured clinical text (e.g., discharge summaries). ResultsWe included in the review 94 studies with 30 studies published in the last three years. Machine learning methods were used in 68 studies, rule-based in 5 studies, and both in 22 studies. 63 studies focused on Named Entity Recognition, 13 on Relation Extraction and 18 performed both. The most frequently extracted entities were “problem”, “test” and “treatment”. 72 studies used public datasets and 22 studies used proprietary datasets alone. Only 14 studies defined clearly a clinical or information task to be addressed by the system and just three studies reported its use outside the experimental setting. Only 7 studies shared a pre-trained model and only 8 an available software tool. DiscussionMachine learning-based methods have dominated the NLP field on information extraction tasks. More recently, Transformer-based language models are taking the lead and showing the strongest performance. However, these developments are mostly based on a few datasets and generic annotations, with very few real-world use cases. This may raise questions about the generalizability of findings, translation into practice and highlights the need for robust clinical evaluation.

Chinese Medical literature research results are more accurate and representative than other medical texts. This paper studies the extraction method of named entity recognition in Chinese medical literatures on hypertension treatment. This paper proposes a Bi-directional Long Short-Term Memory-Conditional Random Fields (BiLSTM-CRF) model based on Attention mechanism for Chinese named entity recognition. BiLSTM-CRF is used as the model infrastructure while the Attention mechanism is used to learn the dependence of each word on the full text. In addition, the dictionary of literature keywords is built to improve the efficiency of recognition. Compared with the routine BiLSTM-CRF model, the recognition effect of the BILSTM-CRF model based on Attention mechanism was better. The value of Precision, Recall and F1 score were 84.6%, 87.9% and 86.2% respectively. The BiLSTM-CRF model based on Attention mechanism can effectively realize named entity recognition in Chinese medical literatures on hypertension treatment.

Named Entity Recognition (NER) is a fundamental task in information extraction from unstructured text. Most previous machine-learning-based NER systems are domain-specific, which implies that they may only perform well on some specific domains (e.g., Newswire ) but tend to adapt poorly to other related but different domains (e.g., Weblog ). Recently, transfer learning techniques have been proposed to NER. However, most transfer learning approaches to NER are developed for binary classification, while NER is a multiclass classification problem in nature. Therefore, one has to first reduce the NER task to multiple binary classification tasks and solve them independently. In this article, we propose a new transfer learning method, named Transfer Joint Embedding (TJE), for cross-domain multiclass classification, which can fully exploit the relationships between classes (labels), and reduce domain difference in data distributions for transfer learning. More specifically, we aim to embed both labels (outputs) and high-dimensional features (inputs) from different domains (e.g., a source domain and a target domain) into a unified low-dimensional latent space, where 1) each label is represented by a prototype and the intrinsic relationships between labels can be measured by Euclidean distance; 2) the distance in data distributions between the source and target domains can be reduced; 3) the source domain labeled data are closer to their corresponding label-prototypes than others. After the latent space is learned, classification on the target domain data can be done with the simple nearest neighbor rule in the latent space. Furthermore, in order to scale up TJE, we propose an efficient algorithm based on stochastic gradient descent (SGD). Finally, we apply the proposed TJE method for NER across different domains on the ACE 2005 dataset, which is a benchmark in Natural Language Processing (NLP). Experimental results demonstrate the effectiveness of TJE and show that TJE can outperform state-of-the-art transfer learning approaches to NER.

Natural language processing (NLP) has significantly advanced our ability to model and interact with human language through technology. However, these advancements have disproportionately benefited high-resource languages with abundant data for training complex models. Low-resource languages, often spoken by smaller or marginalized communities, need help realizing the full potential of NLP applications. The primary challenges in developing NLP applications for low-resource languages stem from the need for large, well-annotated datasets, standardized tools, and linguistic resources. This scarcity of resources hinders the performance of data-driven approaches that have excelled in high-resource settings. Further, low-resource languages frequently exhibit complex grammatical structures, diverse vocabularies, and unique social contexts, which pose additional challenges for standard NLP techniques. Innovative strategies are emerging to address these challenges. Researchers are actively collecting and curating datasets, even utilizing community engagement platforms to expand data resources. Transfer learning, where models pre-trained on high-resource languages are adapted to low-resource settings, has shown significant promise. Multilingual models like Multilingual Bidirectional Encoder Representations from Transformers (mBERT) and Cross Lingual Models (XLM-R), trained on vast quantities of multilingual data, offer a powerful avenue for cross-lingual knowledge transfer. Additionally, researchers are exploring integrating multimodal approaches, combining textual data with images, audio, or video, to enhance NLP performance in low-resource language scenarios. This survey covers applications like part-of-speech tagging, morphological analysis, sentiment analysis, hate speech detection, dependency parsing, language identification, discourse annotation guidelines, question answering, machine translation, information retrieval, and predictive authoring for augmentative and alternative communication systems. The review also highlights machine learning approaches, deep learning approaches, Transformers, and cross-lingual transfer learning as practical techniques. Developing practical NLP applications for low-resource languages is crucial for preserving linguistic diversity, fostering inclusion within the digital world, and expanding our understanding of human language. While challenges remain, the strategies outlined in this survey demonstrate the ongoing progress and highlight the potential for NLP to empower communities that speak low-resource languages and contribute to a more equitable landscape within language technology.

BackgroundDisease named entity recognition (NER) is a fundamental step in information processing of medical texts. However, disease NER involves complex issues such as descriptive modifiers in actual practice. The accurate identification of disease NER is a still an open and essential research problem in medical information extraction and text mining tasks.MethodsA hybrid model named Semantics Bidirectional LSTM and CRF (SBLC) for disease named entity recognition task is proposed. The model leverages word embeddings, Bidirectional Long Short Term Memory networks and Conditional Random Fields. A publically available NCBI disease dataset is applied to evaluate the model through comparing with nine state-of-the-art baseline methods including cTAKES, MetaMap, DNorm, C-Bi-LSTM-CRF, TaggerOne and DNER.ResultsThe results show that the SBLC model achieves an F1 score of 0.862 and outperforms the other methods. In addition, the model does not rely on external domain dictionaries, thus it can be more conveniently applied in many aspects of medical text processing.ConclusionsAccording to performance comparison, the proposed SBLC model achieved the best performance, demonstrating its effectiveness in disease named entity recognition.

Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a small set of parameters for each new setting (language pair or domain). In this work we study the compositionality of language and domain adapters in the context of Machine Translation. We aim to study, 1) parameter-efficient adaptation to multiple domains and languages simultaneously (full-resource scenario) and 2) cross-lingual transfer in domains where parallel data is unavailable for certain language pairs (partial-resource scenario). We find that in the partial resource scenario a naive combination of domain-specific and language-specific adapters often results in `catastrophic forgetting' of the missing languages. We study other ways to combine the adapters to alleviate this issue and maximize cross-lingual transfer. With our best adapter combinations, we obtain improvements of 3-4 BLEU on average for source languages that do not have in-domain data. For target languages without in-domain data, we achieve a similar improvement by combining adapters with back-translation. Supplementary material is available at https://tinyurl.com/r66stbxj.

Chinese agricultural diseases and pests named entity recognition with multi-scale local context features and self-attention mechanism

Named Entity Recognition (NER) is a part of extraction and is used for Natural Language Processing (NLP). NER system helps us to find various names from unstructured text or a text file and classifies them into various categories. The attention-based keyword extracting concept has been established to solve the problem of detecting redundant data and inessential data and does not consider them. Researchers are highly concerned about attention mechanisms. In this study, we focus on the most recent algorithms which are trained with the attention-based mechanism for NER. We briefly describe attention-based models, objectives of these models, datasets used in each method, and efficiency. Our focus is to give some decisions on which model is exceptionally efficient depending on the dataset and NER category.

Named entity annotation means an entity that needs to be labeled in a prediction sequence on a given text sequence. Labeling high-quality medical entities from Chinese medical texts plays an important role in named entity recognition, and construction of medical knowledge graph. Named entity annotation in medical texts is the premise of the full-supervised and semi-supervised named entities recognition. The current mainstream named entity annotation require a lot of manpower on the corpus labeling, which is laborious and time consuming. For medical entities widely distributed in Chinese medical texts, in this paper, we propose a small number of manually labeled medical entities to autonomously learn medical text features, and iteratively generating new labeled entities. The model automatically iterates the annotations from the original medical text collection to be processed and generates a valid medical entity. The autonomously medical entity labeling work makes it easy to label Chinese medical texts. This framework is tested on real Chinese medical records, and the experimental results show that the method can effectively identify the entities, and has certain practical value.