Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHiTRANS: A Hierarchical Transformer Network for Nested Named Entity Recognition
HITRANS: شبكة محول هرمية للتعرف على الكيان المسمى المتداخل
301
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تم دراسة التعرف على الكيان المسمى Nestate (NNER) على نطاق واسع، تهدف إلى تحديد جميع الكيانات المتداخلة من تمديدات محتملة (I.E.، واحد أو أكثر من الرموز المستمرة). ومع ذلك، فإن الدراسات الحديثة لأي نانر إما التركيز على مخططات العلامات الشاقة أو الاستفادة من الهياكل المعقدة، والتي تفشل في تعلم تمثيلات فعالة من جملة المدخلات مع كيانات متداخلة للغاية. بمعنى حدسي، ستساهم تمثيلات صريحة في نانر بسبب معلومات السياق الغنية التي تحتوي عليها. في هذه الدراسة، نقترح شبكة محول هرمية (HITRANS) للمهمة NNER، والتي تتحلل جملة الإدخال إلى تمثال متعدد الحبوب وتعزز التعلم التمثيل بطريقة هرمية. على وجه التحديد، نستخدم أول وحدة من المرحلة الأولى لتوليد تمثيلات تمتد عن طريق معلومات السياق التجميعية بناء على شبكة محول من أسفل إلى أعلى وهبوطا. ثم تم تصميم طبقة التنبؤ الملصق للتعرف على الكيانات المتداخلة هرمية، والتي تستكشف بشكل طبيعي التبعيات الدلالية بين تمديد مختلفة. تثبت تجارب مجموعات بيانات Genia و ACE-2004 و ACE-2005 و NNE أن طريقةنا المقترحة تحقق أداء أفضل بكثير من النهج التي من بين الفني.
Nested Named Entity Recognition (NNER) has been extensively studied, aiming to identify all nested entities from potential spans (i.e., one or more continuous tokens). However, recent studies for NNER either focus on tedious tagging schemas or utilize complex structures, which fail to learn effective span representations from the input sentence with highly nested entities. Intuitively, explicit span representations will contribute to NNER due to the rich context information they contain. In this study, we propose a Hierarchical Transformer (HiTRANS) network for the NNER task, which decomposes the input sentence into multi-grained spans and enhances the representation learning in a hierarchical manner. Specifically, we first utilize a two-phase module to generate span representations by aggregating context information based on a bottom-up and top-down transformer network. Then a label prediction layer is designed to recognize nested entities hierarchically, which naturally explores semantic dependencies among different spans. Experiments on GENIA, ACE-2004, ACE-2005 and NNE datasets demonstrate that our proposed method achieves much better performance than the state-of-the-art approaches.
References used
https://aclanthology.org/
rate research
Read More
Although pre-trained big models (e.g., BERT, ERNIE, XLNet, GPT3 etc.) have delivered top performance in Seq2seq modeling, their deployments in real-world applications are often hindered by the excessive computations and memory demand involved. For ma
ny applications, including named entity recognition (NER), matching the state-of-the-art result under budget has attracted considerable attention. Drawing power from the recent advance in knowledge distillation (KD), this work presents a novel distillation scheme to efficiently transfer the knowledge learned from big models to their more affordable counterpart. Our solution highlights the construction of surrogate labels through the k-best Viterbi algorithm to distill knowledge from the teacher model. To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning.To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts. We further discuss ablation results to dissect our gains.
As a result of unstructured sentences and some misspellings and errors, finding named entities in a noisy environment such as social media takes much more effort. ParsTwiNER contains about 250k tokens, based on standard instructions like MUC-6 or CoN
LL 2003, gathered from Persian Twitter. Using Cohen's Kappa coefficient, the consistency of annotators is 0.95, a high score. In this study, we demonstrate that some state-of-the-art models degrade on these corpora, and trained a new model using parallel transfer learning based on the BERT architecture. Experimental results show that the model works well in informal Persian as well as in formal Persian.
Abstract We take a step towards addressing the under- representation of the African continent in NLP research by bringing together different stakeholders to create the first large, publicly available, high-quality dataset for named entity recognition
(NER) in ten African languages. We detail the characteristics of these languages to help researchers and practitioners better understand the challenges they pose for NER tasks. We analyze our datasets and conduct an extensive empirical evaluation of state- of-the-art methods across both supervised and transfer learning settings. Finally, we release the data, code, and models to inspire future research on African NLP.1
Pretrained language models like BERT have advanced the state of the art for many NLP tasks. For resource-rich languages, one has the choice between a number of language-specific models, while multilingual models are also worth considering. These mode
ls are well known for their crosslingual performance, but have also shown competitive in-language performance on some tasks. We consider monolingual and multilingual models from the perspective of historical texts, and in particular for texts enriched with editorial notes: how do language models deal with the historical and editorial content in these texts? We present a new Named Entity Recognition dataset for Dutch based on 17th and 18th century United East India Company (VOC) reports extended with modern editorial notes. Our experiments with multilingual and Dutch pretrained language models confirm the crosslingual abilities of multilingual models while showing that all language models can leverage mixed-variant data. In particular, language models successfully incorporate notes for the prediction of entities in historical texts. We also find that multilingual models outperform monolingual models on our data, but that this superiority is linked to the task at hand: multilingual models lose their advantage when confronted with more semantical tasks.
Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models. However, most existing techniques focus on augmenting in-domain data in low-resource scenarios where annotated data is quite limite
d. In this work, we take this research direction to the opposite and study cross-domain data augmentation for the NER task. We investigate the possibility of leveraging data from high-resource domains by projecting it into the low-resource domains. Specifically, we propose a novel neural architecture to transform the data representation from a high-resource to a low-resource domain by learning the patterns (e.g. style, noise, abbreviations, etc.) in the text that differentiate them and a shared feature space where both domains are aligned. We experiment with diverse datasets and show that transforming the data to the low-resource domain representation achieves significant improvements over only using data from high-resource domains.
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
