Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGlyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction
الأحرف الرسومية المحسنة الطابع الصيني مسبقا للتدريب على تنبؤية معجمية
297
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتم تعريف Sememes على أنها الوحدات الذرية لوصف المعنى الدلالي للمفاهيم.نظرا لصعوبة التعليق يدويا في التسجيل يدويا واستنادا إلى التعليق بين الخبراء، فقد تم اقتراح مهمة تنبؤات النظرة المعجمية.ومع ذلك، فإن الأساليب السابقة تعتمد بشدة على Word أو Arttersdings، وتجاهل المعلومات المحبوسة الدقيقة.في هذه الورقة، نقترح طريقة رواية ما قبل التدريب والتي تم تصميمها لتحسين دمج المعلومات الداخلية للشخصية الصينية.يتم استخدام تمثيل الأحرف الصيني المحسنة Glyph (دول مجلس التعاون الخليجي) لمساعدة تنبؤة النظر.نقوم بتجربة وتقييم النموذج لدينا على HOWNET، وهو قاعدة المعرفة الشمالية الشهيرة.تظهر النتائج التجريبية أن أسلوبنا تتفوق على نماذج المعلومات غير الخارجية الموجودة.
Sememes are defined as the atomic units to describe the semantic meaning of concepts. Due to the difficulty of manually annotating sememes and the inconsistency of annotations between experts, the lexical sememe prediction task has been proposed. However, previous methods heavily rely on word or character embeddings, and ignore the fine-grained information. In this paper, we propose a novel pre-training method which is designed to better incorporate the internal information of Chinese character. The Glyph enhanced Chinese Character representation (GCC) is used to assist sememe prediction. We experiment and evaluate our model on HowNet, which is a famous sememe knowledge base. The experimental results show that our method outperforms existing non-external information models.
References used
https://aclanthology.org/
rate research
Read More
Chinese character decomposition has been used as a feature to enhance Machine Translation (MT) models, combining radicals into character and word level models. Recent work has investigated ideograph or stroke level embedding. However, questions remai
n about different decomposition levels of Chinese character representations, radical and strokes, best suited for MT. To investigate the impact of Chinese decomposition embedding in detail, i.e., radical, stroke, and intermediate levels, and how well these decompositions represent the meaning of the original character sequences, we carry out analysis with both automated and human evaluation of MT. Furthermore, we investigate if the combination of decomposed Multiword Expressions (MWEs) can enhance the model learning. MWE integration into MT has seen more than a decade of exploration. However, decomposed MWEs has not previously been explored.
Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets. In this paper, however, we verbalize the entire English Wikidata KG, and discuss the unique c
hallenges associated with a broad, open-domain, large-scale verbalization. We further show that verbalizing a comprehensive, encyclopedic KG like Wikidata can be used to integrate structured KGs and natural language corpora. In contrast to the many architectures that have been developed to integrate these two sources, our approach converts the KG into natural text, allowing it to be seamlessly integrated into existing language models. It carries the further advantages of improved factual accuracy and reduced toxicity in the resulting language model. We evaluate this approach by augmenting the retrieval corpus in a retrieval language model and showing significant improvements on the knowledge intensive tasks of open domain QA and the LAMA knowledge probe.
Due to the increasing concerns for data privacy, source-free unsupervised domain adaptation attracts more and more research attention, where only a trained source model is assumed to be available, while the labeled source data remain private. To get
promising adaptation results, we need to find effective ways to transfer knowledge learned in source domain and leverage useful domain specific information from target domain at the same time. This paper describes our winning contribution to SemEval 2021 Task 10: Source-Free Domain Adaptation for Semantic Processing. Our key idea is to leverage the model trained on source domain data to generate pseudo labels for target domain samples. Besides, we propose Negation-aware Pre-training (NAP) to incorporate negation knowledge into model. Our method win the 1st place with F1-score of 0.822 on the official blind test set of Negation Detection Track.
Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low-resource ones. However, due to significant typological differences and
contradictions between some languages, such models usually perform poorly on many languages and cross-lingual settings, which shows the difficulty of learning a single model to handle massive diverse languages well at the same time. To alleviate this issue, we present a new multilingual pre-training pipeline. We propose to generate language representation from multilingual pre-trained model and conduct linguistic analysis to show that language representation similarity reflects linguistic similarity from multiple perspectives, including language family, geographical sprachbund, lexicostatistics, and syntax. Then we cluster all the target languages into multiple groups and name each group as a representation sprachbund. Thus, languages in the same representation sprachbund are supposed to boost each other in both pre-training and fine-tuning as they share rich linguistic similarity. We pre-train one multilingual model for each representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
Predicting the complexity level of a word or a phrase is considered a challenging task. It is even recognized as a crucial step in numerous NLP applications, such as text rearrangements and text simplification. Early research treated the task as a bi
nary classification task, where the systems anticipated the existence of a word's complexity (complex versus uncomplicated). Other studies had been designed to assess the level of word complexity using regression models or multi-labeling classification models. Deep learning models show a significant improvement over machine learning models with the rise of transfer learning and pre-trained language models. This paper presents our approach that won the first rank in the SemEval-task1 (sub stask1). We have calculated the degree of word complexity from 0-1 within a text. We have been ranked first place in the competition using the pre-trained language models Bert and RoBERTa, with a Pearson correlation score of 0.788.
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
