Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSequence Mixup for Zero-Shot Cross-Lingual Part-Of-Speech Tagging
مزيج التسلسل لعلامة جزء من جزء لا بلغ تلاشى
269
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كانت هناك جهود في التعلم عبر التحويلات عبر اللغات لمختلف المهام.نقدم نهجا باستخدام طريقة تكبير البيانات الاستكمالية، والابتزاز، لتحسين تعميم النماذج من أجل وضع علامات جزء من الكلام المدربين على لغة مصدر، وتحسين أدائها على اللغات المستهدفة غير المرئية.من خلال التجارب على عشرة لغات مع الهياكل المتنوعة وجذور اللغة، نطرح تطبيقها لتطبيقها على المهام المتبادلة الصفرية الصفرية.
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.
References used
https://aclanthology.org/
rate research
Read More
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 heuristi
cs 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
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.
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.
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.
An available free groundwater were classified
hydrochemical, and determined its fitting for general uses in a part
of Damascus's Ghouta, which suffers water deficiency, where the
study carried out on groundwater samples taken from 20 wells
distri
buted on all study area, the results show that groundwater
classified hydrochemical as calcic water and non potable, and
unsuitable for domestic consumption in broad part from study area,
but arable and recommend to use in irrigation plants that have weak
resistant to salinity, and not preferable to use in industry generally,
but it's good for building and concrete works.
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
