Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Dylex: دمج المعجم الديناميكي في بيرت للحصول على وضع التسلسل
469
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
ثبت أن دمج المعرفة المعجمية في نماذج التعلم العميق قد تكون فعالة للغاية لمهام وضع التسلسل.ومع ذلك، فإن الأمر السابق يعمل عادة صعوبة في التعامل مع المعجم الديناميكي النطاق الذي يسبب غالبا ضوضاء مطابقة مفرطة ومشاكل التحديثات المتكررة.في هذه الورقة، نقترح Dylex، ونهج تأريك معجم التوصيل لمهام تسلسل التسلسل القائمة على بيرت.بدلا من الاستفادة من تضمين الكلمات في المعجم في الأساليب التقليدية، فإننا نعتمد تضمين العلامات اللاإرادي للكلمة لتجنب إعادة تدريب التمثيل أثناء تحديث المعجم.علاوة على ذلك، فإننا نوظف طريقة تنظيف المعرفة المعلنة المعجمية الفعالة لإعلام الضوضاء المطابقة.وأخيرا، نقدم آلية الانتباه المعرفة القائم على العقيد الحكيمة لضمان استقرار الإطار المقترح.تجارب تجارب عشرة مجموعات من ثلاث مهام تشير إلى أن الإطار المقترح يحقق سوتا جديدة، حتى مع المعجم على نطاق واسع جدا.
Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause excessive matching noise and problems of frequent updates. In this paper, we propose DyLex, a plug-in lexicon incorporation approach for BERT based sequence labeling tasks. Instead of leveraging embeddings of words in the lexicon as in conventional methods, we adopt word-agnostic tag embeddings to avoid re-training the representation while updating the lexicon. Moreover, we employ an effective supervised lexical knowledge denoising method to smooth out matching noise. Finally, we introduce a col-wise attention based knowledge fusion mechanism to guarantee the pluggability of the proposed framework. Experiments on ten datasets of three tasks show that the proposed framework achieves new SOTA, even with very large scale lexicons.
References used
https://aclanthology.org/
rate research
Read More
Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach to acceler
ate PLMs' inference, named TR-BERT, which could flexibly adapt the layer number of each token in inference to avoid redundant calculation. Specially, TR-BERT formulates the token reduction process as a multi-step token selection problem and automatically learns the selection strategy via reinforcement learning. The experimental results on several downstream NLP tasks show that TR-BERT is able to speed up BERT by 2-5 times to satisfy various performance demands. Moreover, TR-BERT can also achieve better performance with less computation in a suite of long-text tasks since its token-level layer number adaption greatly accelerates the self-attention operation in PLMs. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/TR-BERT.
In recent years pre-trained language models (PLM) such as BERT have proven to be very effective in diverse NLP tasks such as Information Extraction, Sentiment Analysis and Question Answering. Trained with massive general-domain text, these pre-traine
d language models capture rich syntactic, semantic and discourse information in the text. However, due to the differences between general and specific domain text (e.g., Wikipedia versus clinic notes), these models may not be ideal for domain-specific tasks (e.g., extracting clinical relations). Furthermore, it may require additional medical knowledge to understand clinical text properly. To solve these issues, in this research, we conduct a comprehensive examination of different techniques to add medical knowledge into a pre-trained BERT model for clinical relation extraction. Our best model outperforms the state-of-the-art systems on the benchmark i2b2/VA 2010 clinical relation extraction dataset.
The task of converting a nonstandard text to a standard and readable text is known as lexical normalization. Almost all the Natural Language Processing (NLP) applications require the text data in normalized form to build quality task-specific models.
Hence, lexical normalization has been proven to improve the performance of numerous natural language processing tasks on social media. This study aims to solve the problem of Lexical Normalization by formulating the Lexical Normalization task as a Sequence Labeling problem. This paper proposes a sequence labeling approach to solve the problem of Lexical Normalization in combination with the word-alignment technique. The goal is to use a single model to normalize text in various languages namely Croatian, Danish, Dutch, English, Indonesian-English, German, Italian, Serbian, Slovenian, Spanish, Turkish, and Turkish-German. This is a shared task in 2021 The 7th Workshop on Noisy User-generated Text (W-NUT)'' in which the participants are expected to create a system/model that performs lexical normalization, which is the translation of non-canonical texts into their canonical equivalents, comprising data from over 12 languages. The proposed single multilingual model achieves an overall ERR score of 43.75 on intrinsic evaluation and an overall Labeled Attachment Score (LAS) score of 63.12 on extrinsic evaluation. Further, the proposed method achieves the highest Error Reduction Rate (ERR) score of 61.33 among the participants in the shared task. This study highlights the effects of using additional training data to get better results as well as using a pre-trained Language model trained on multiple languages rather than only on one language.
Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transiti
on sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of rich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration.
In this paper, we propose a knowledge infusion mechanism to incorporate domain knowledge into language transformers. Weakly supervised data is regarded as the main source for knowledge acquisition. We pre-train the language models to capture masked k
nowledge of focuses and aspects and then fine-tune them to obtain better performance on the downstream tasks. Due to the lack of publicly available datasets for multi-label classification of Chinese medical questions, we crawled questions from medical question/answer forums and manually annotated them using eight predefined classes: persons and organizations, symptom, cause, examination, disease, information, ingredient, and treatment. Finally, a total of 1,814 questions with 2,340 labels. Each question contains an average of 1.29 labels. We used Baidu Medical Encyclopedia as the knowledge resource. Two transformers BERT and RoBERTa were implemented to compare performance on our constructed datasets. Experimental results showed that our proposed model with knowledge infusion mechanism can achieve better performance, no matter which evaluation metric including Macro F1, Micro F1, Weighted F1 or Subset Accuracy were considered.
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
