Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning Entity-Likeness with Multiple Approximate Matches for Biomedical NER
التعلم كيان تشابه مع العديد من المباريات التقريبية ل Biomedical NER
192
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الكيانات الطبية الحيوية المسماة معقدة، لذلك تم استخدام مطابقة تقريبية لتحسين تغطية الكيان.ومع ذلك، فإن نهج المطابقة التقريب المعتادة يجلب نتيجة مطابقة واحدة فقط، والتي غالبا ما تكون صاخبة.في هذا العمل، نقترح طريقة لنقل الطبية الحيوية التي يجلب مباريات تقريبية متعددة لجملة معينة للاستفادة من أشكالها لتقدير تشابه الكيان.يستخدم النموذج تجمع لتجاهل المعلومات غير الضرورية من نتائج المطابقة الصاخبة، وتعلم كيان تشابه العبارة مع العديد من المباريات التقريبية.النتائج التجريبية على ثلاثة مجموعات بيانات معطرة من المجال الطبي الطبيعي، BC2GM، مرض NCBI، و BC4Chemd، إظهار الفعالية.يعمل نموذجنا في تحسين المتوسط بنسبة تصل إلى +0.21 نقطة مقارنة مع NER القائم على BIOBERT.
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 biomedical 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.
References used
https://aclanthology.org/
rate research
Read More
There is an increasing interest in continuous learning (CL), as data privacy is becoming a priority for real-world machine learning applications. Meanwhile, there is still a lack of academic NLP benchmarks that are applicable for realistic CL setting
s, which is a major challenge for the advancement of the field. In this paper we discuss some of the unrealistic data characteristics of public datasets, study the challenges of realistic single-task continuous learning as well as the effectiveness of data rehearsal as a way to mitigate accuracy loss. We construct a CL NER dataset from an existing publicly available dataset and release it along with the code to the research community.
Recent studies in deep learning have shown significant progress in named entity recognition (NER). However, most existing works assume clean data annotation, while real-world scenarios typically involve a large amount of noises from a variety of sour
ces (e.g., pseudo, weak, or distant annotations). This work studies NER under a noisy labeled setting with calibrated confidence estimation. Based on empirical observations of different training dynamics of noisy and clean labels, we propose strategies for estimating confidence scores based on local and global independence assumptions. We partially marginalize out labels of low confidence with a CRF model. We further propose a calibration method for confidence scores based on the structure of entity labels. We integrate our approach into a self-training framework for boosting performance. Experiments in general noisy settings with four languages and distantly labeled settings demonstrate the effectiveness of our method.
Training NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of language, we hypothesize that single label is not sufficient to learn the sp
ectrum of language interpretation. We explore new annotation distribution schemes, assigning multiple labels per example for a small subset of training examples. Introducing such multi label examples at the cost of annotating fewer examples brings clear gains on natural language inference task and entity typing task, even when we simply first train with a single label data and then fine tune with multi label examples. Extending a MixUp data augmentation framework, we propose a learning algorithm that can learn from training examples with different amount of annotation (with zero, one, or multiple labels). This algorithm efficiently combines signals from uneven training data and brings additional gains in low annotation budget and cross domain settings. Together, our method achieves consistent gains in two tasks, suggesting distributing labels unevenly among training examples can be beneficial for many NLP tasks.
Previous work on Entity Linking has focused on resources targeting non-nested proper named entity mentions, often in data from Wikipedia, i.e. Wikification. In this paper, we present and evaluate WikiGUM, a fully wikified dataset, covering all mentio
ns of named entities, including their non-named and pronominal mentions, as well as mentions nested within other mentions. The dataset covers a broad range of 12 written and spoken genres, most of which have not been included in Entity Linking efforts to date, leading to poor performance by a pretrained SOTA system in our evaluation. The availability of a variety of other annotations for the same data also enables further research on entities in context.
Joint entity and relation extraction is challenging due to the complex interaction of interaction between named entity recognition and relation extraction. Although most existing works tend to jointly train these two tasks through a shared network, t
hey fail to fully utilize the interdependence between entity types and relation types. In this paper, we design a novel synchronous dual network (SDN) with cross-type attention via separately and interactively considering the entity types and relation types. On the one hand, SDN adopts two isomorphic bi-directional type-attention LSTM to encode the entity type enhanced representations and the relation type enhanced representations, respectively. On the other hand, SDN explicitly models the interdependence between entity types and relation types via cross-type attention mechanism. In addition, we also propose a new multi-task learning strategy via modeling the interaction of two types of information. Experiments on NYT and WebNLG datasets verify the effectiveness of the proposed model, achieving state-of-the-art performance.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
