Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userReducing Confusion in Active Learning for Part-Of-Speech Tagging
تقليل الارتباك في التعلم النشط لعلامات جزء من الكلام
269
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يستخدم التعلم النشط (AL) خوارزمية اختيار البيانات لتحديد عينات تدريب مفيدة لتقليل تكلفة التوضيحية. هذه هي الآن أداة أساسية لبناء محلل تحويلات تحويلية منخفضة الموارد مثل Taggers جزء من الكلام (POS). يتم تصميم الاستدلال الموجودة بشكل عام بشكل عام على مبدأ اختيار مثيلات تدريبية غير مؤكدة ولكنها قد تقلل من هذه الحالات تقليل عدد كبير من الأخطاء. ومع ذلك، في دراسة تجريبية عبر ست لغات متنوعة من النطباض (الألمانية والسويدية والاجنية والشابات الشمالية والفارسية والأوكرانية)، وجدنا النتيجة المثيرة للدهشة أنه حتى في سيناريو أوراكل حيث نعرف عدم اليقين الحقيقي للتوقعات، هذه الاستدلال الحالية بعيدون عن الأمثل. بناء على هذا التحليل، نطرح مشكلة آل كما اختيار الحالات التي تقلل من الارتباك بين أزواج من علامات الإخراج معينة. تظهر تجربة واسعة النطاق على اللغات المذكورة أعلاه أن استراتيجيتنا المقترحة تتفوق على استراتيجيات آجال أخرى من هامش مهم. نقدم أيضا نتائج مساعدة توضح أهمية المعايرة المناسبة للنماذج، والتي نضمنها من خلال التدريب المبريد، وتحليلا إظهار كيفية تحديد استراتيجيتنا المقترحة أمثلة تتابع بشكل وثيق توزيع بيانات Oracle. يتم إصدار الرمز علني هنا
Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing AL heuristics are generally designed on the principle of selecting uncertain yet representative training instances, where annotating these instances may reduce a large number of errors. However, in an empirical study across six typologically diverse languages (German, Swedish, Galician, North Sami, Persian, and Ukrainian), we found the surprising result that even in an oracle scenario where we know the true uncertainty of predictions, these current heuristics are far from optimal. Based on this analysis, we pose the problem of AL as selecting instances that maximally reduce the confusion between particular pairs of output tags. Extensive experimentation on the aforementioned languages shows that our proposed AL strategy outperforms other AL strategies by a significant margin. We also present auxiliary results demonstrating the importance of proper calibration of models, which we ensure through cross-view training, and analysis demonstrating how our proposed strategy selects examples that more closely follow the oracle data distribution. The code is publicly released here.1
References used
https://aclanthology.org/
rate research
Read More
We train and test five open-source taggers, which use different methods, on three Swedish corpora, which are of comparable size but use different tagsets. The KB-Bert tagger achieves the highest accuracy for part-of-speech and morphological tagging,
while being fast enough for practical use. We also compare the performance across tagsets and across different genres in one of the corpora. We perform manual error analysis and perform a statistical analysis of factors which affect how difficult specific tags are. Finally, we test ensemble methods, showing that a small (but not significant) improvement over the best-performing tagger can be achieved.
There have been efforts in cross-lingual transfer learning for various tasks. We present an approach utilizing an interpolative data augmentation method, Mixup, to improve the generalizability of models for part-of-speech tagging trained on a source
language, improving its performance on unseen target languages. Through experiments on ten languages with diverse structures and language roots, we put forward its applicability for downstream zero-shot cross-lingual tasks.
We present the first multi-task learning model -- named PhoNLP -- for joint Vietnamese part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing. Experiments on Vietnamese benchmark datasets show that PhoNLP produces state-o
f-the-art results, outperforming a single-task learning approach that fine-tunes the pre-trained Vietnamese language model PhoBERT (Nguyen and Nguyen, 2020) for each task independently. We publicly release PhoNLP as an open-source toolkit under the Apache License 2.0. Although we specify PhoNLP for Vietnamese, our PhoNLP training and evaluation command scripts in fact can directly work for other languages that have a pre-trained BERT-based language model and gold annotated corpora available for the three tasks of POS tagging, NER and dependency parsing. We hope that PhoNLP can serve as a strong baseline and useful toolkit for future NLP research and applications to not only Vietnamese but also the other languages. Our PhoNLP is available at https://github.com/VinAIResearch/PhoNLP
In this work, we provide an extensive part-of-speech analysis of the discourse of social media users with depression. Research in psychology revealed that depressed users tend to be self-focused, more preoccupied with themselves and ruminate more abo
ut their lives and emotions. Our work aims to make use of large-scale datasets and computational methods for a quantitative exploration of discourse. We use the publicly available depression dataset from the Early Risk Prediction on the Internet Workshop (eRisk) 2018 and extract part-of-speech features and several indices based on them. Our results reveal statistically significant differences between the depressed and non-depressed individuals confirming findings from the existing psychology literature. Our work provides insights regarding the way in which depressed individuals are expressing themselves on social media platforms, allowing for better-informed computational models to help monitor and prevent mental illnesses.
Code-mixing (CM) is a frequently observed phenomenon that uses multiple languages in an utterance or sentence. There are no strict grammatical constraints observed in code-mixing, and it consists of non-standard variations of spelling. The linguistic
complexity resulting from the above factors made the computational analysis of the code-mixed language a challenging task. Language identification (LI) and part of speech (POS) tagging are the fundamental steps that help analyze the structure of the code-mixed text. Often, the LI and POS tagging tasks are interdependent in the code-mixing scenario. We project the problem of dealing with multilingualism and grammatical structure while analyzing the code-mixed sentence as a joint learning task. In this paper, we jointly train and optimize language detection and part of speech tagging models in the code-mixed scenario. We used a Transformer with convolutional neural network architecture. We train a joint learning method by combining POS tagging and LI models on code-mixed social media text obtained from the ICON shared task.
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
