Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map
SOM-NCSCM: نموذج ضغط صيني عصبي فعال معزز مع خريطة التنظيم الذاتي
225
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تم دراسة ضغط الجملة (SC)، التي تهدف إلى تقصير الأحكام مع الاحتفاظ بكلمات مهمة تعبر عن المعاني الأساسية، لسنوات عديدة في العديد من اللغات، خاصة باللغة الإنجليزية. ومع ذلك، فإن التحسينات في مهمة SC الصينية لا تزال قليلة جدا بسبب العديد من الصعوبات: نادرة من كوربورا الموازية، وتحبيب تجزئة مختلفة من الجمل الصينية، والأداء غير الكامل للتحليلات النحوية. علاوة على ذلك، تم التحقيق في نماذج SC الصينية بأكملها حتى الآن. في هذا العمل، نبني مجموعة بيانات SC من الجمل العامية الصينية من نظام الإجابة على مدى واقعية في مجال الاتصالات السلكية واللاسلكية، ثم نقترح نموذج صيني عصبي SC معزز مع خريطة تنظيم ذاتية (SOM-NCSCM)، إلى احصل على رؤية قيمة من البيانات وتحسين أداء نموذج SC الصيني العصبي بأكمله بطريقة صالحة. تظهر النتائج التجريبية أننا يمكن أن تستفيد بشكل كبير من التحقيق العميق في التشابه بين البيانات، وتحقيق درجة F1 واعدة قدرها 89.655 وفرز Bleu4 البالغة 70.116، والتي توفر أيضا خط أساس لمزيد من الأبحاث حول مهمة SC الصينية.
Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English. However, improvements on Chinese SC task are still quite few due to several difficulties: scarce of parallel corpora, different segmentation granularity of Chinese sentences, and imperfect performance of syntactic analyses. Furthermore, entire neural Chinese SC models have been under-investigated so far. In this work, we construct an SC dataset of Chinese colloquial sentences from a real-life question answering system in the telecommunication domain, and then, we propose a neural Chinese SC model enhanced with a Self-Organizing Map (SOM-NCSCM), to gain a valuable insight from the data and improve the performance of the whole neural Chinese SC model in a valid manner. Experimental results show that our SOM-NCSCM can significantly benefit from the deep investigation of similarity among data, and achieve a promising F1 score of 89.655 and BLEU4 score of 70.116, which also provides a baseline for further research on Chinese SC task.
References used
https://aclanthology.org/
rate research
Read More
One ofa car's suspension system functions is to isolate vibrations resulting from road on the driver and ensure a comfortable ride. But the design of control systems for semi-active suspension systems is difficult because of the non-linearity of the
constituent elements of these systems which make the researches related to it characterized by complexity. So in order to improve the performance of semi-active suspension systems without bearing the effort of designing a model based controller, a control system is designed using self-organizing fuzzy controller based on the principle of delay-in-penalty to control a semi-active suspension system which uses a magneto rheological damper. The controller tries to enhance system performance using the desired response as it is described in the penalty table. The fuzzy logic controller is based on two inputs namely sprung mass velocity and unsprung mass velocity. Using a quarter car model with 2 degree-of-freedom the system is modeled and simulated in MATLAB &Simulink® and the results are compared to the widely used sky-hook strategy. the simulation showed the ability of the self-organizing fuzzy controller to provide good results in minimizing sprung mass acceleration in variousroad profiles compared to sky-hookstrategy.
The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field. Considering that pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, we present a Q
uadrupletBERT model for effective and efficient retrieval in this paper. Unlike most existing BERT-style retrieval models, which only focus on the ranking phase in retrieval systems, our model makes considerable improvements to the retrieval phase and leverages the distances between simple negative and hard negative instances to obtaining better embeddings. Experimental results demonstrate that our QuadrupletBERT achieves state-of-the-art results in embedding-based large-scale retrieval tasks.
In this paper, we propose a global, self- explainable solution to solve a prominent NLP problem: Entity Resolution (ER). We formu- late ER as a graph partitioning problem. Every mention of a real-world entity is represented by a node in the graph, an
d the pairwise sim- ilarity scores between the mentions are used to associate these nodes to exactly one clique, which represents a real-world entity in the ER domain. In this paper, we use Clique Partition- ing Problem (CPP), which is an Integer Pro- gram (IP) to formulate ER as a graph partition- ing problem and then highlight the explainable nature of this method. Since CPP is NP-Hard, we introduce an efficient solution procedure, the xER algorithm, to solve CPP as a combi- nation of finding maximal cliques in the graph and then performing generalized set packing using a novel formulation. We discuss the advantages of using xER over the traditional methods and provide the computational exper- iments and results of applying this method to ER data sets.
Abstract Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters. This has led to various attempts of compressing such models, but existing m
ethods have not considered the differences in the predictive power of various model components or in the generalizability of the compressed models. To understand the connection between model compression and out-of-distribution generalization, we define the task of compressing language representation models such that they perform best in a domain adaptation setting. We choose to address this problem from a causal perspective, attempting to estimate the average treatment effect (ATE) of a model component, such as a single layer, on the model's predictions. Our proposed ATE-guided Model Compression scheme (AMoC), generates many model candidates, differing by the model components that were removed. Then, we select the best candidate through a stepwise regression model that utilizes the ATE to predict the expected performance on the target domain. AMoC outperforms strong baselines on dozens of domain pairs across three text classification and sequence tagging tasks.1
In this paper we investigate the etymology of Romanian words. We start from the Romanian lexicon and automatically extract information from multiple etymological dictionaries. We evaluate the results and perform extensive quantitative and qualitative analyses with the goal of building an etymological map of the language.
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
