Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
نقل عبر اللغات لتصنيف النص مع الرسم البياني غير المتجانس القائم في القاموس
344
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في تصنيف النص عبر اللغات، يطلب من أن البيانات التدريبية الخاصة بمهام المهام في لغات مصدر عالية الموارد متوفرة، حيث تكون المهمة مطابقة لتلك لغة مستهدفة منخفضة الموارد. ومع ذلك، يمكن أن يكون جمع هذه البيانات التدريبية غير ممكنة بسبب تكلفة العلامات وخصائص المهام ومخاوف الخصوصية. تقترح هذه الورقة حل بديل يستخدم فقط تضييق كلمة مهمة من المهام لغات الموارد عالية الموارد وقواميس ثنائية اللغة. أولا، نبني رسم بياني غير متجانس (DHG) من القواميس ثنائية اللغة. هذا يفتح إمكانية استخدام الشبكات العصبية الرسم البيانية للتحويل عبر اللغات. التحدي المتبقي هو عدم تجانس DHG لأنه يتم النظر في لغات متعددة. لمعالجة هذا التحدي، نقترح شبكة عصبية غير متجانسة مقرها القاموس (Dhgnet) التي تعالج بفعالية عدم تجانس DHG بشكل فعال بمقدار تجميعتين، وهي مجامعات على مستوى الكلمة ومستوى اللغة. توضح النتائج التجريبية أن أسلوبنا تفوق النماذج المحددة على الرغم من أنها لا تصل إلى كورسا كبيرة. علاوة على ذلك، يمكن أن يؤدي ذلك بشكل جيد على الرغم من أن القواميس تحتوي على العديد من الترجمات غير الصحيحة. تتيح قوتها لاستخدام مجموعة واسعة من القواميس مثل القاموس المصنوع تلقائيا وقاموس التعيد الجماعي، وهو أمر مناسب لتطبيقات العالم الحقيقي.
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can be infeasible because of the labeling cost, task characteristics, and privacy concerns. This paper proposes an alternative solution that uses only task-independent word embeddings of high-resource languages and bilingual dictionaries. First, we construct a dictionary-based heterogeneous graph (DHG) from bilingual dictionaries. This opens the possibility to use graph neural networks for cross-lingual transfer. The remaining challenge is the heterogeneity of DHG because multiple languages are considered. To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations. Experimental results demonstrate that our method outperforms pretrained models even though it does not access to large corpora. Furthermore, it can perform well even though dictionaries contain many incorrect translations. Its robustness allows the usage of a wider range of dictionaries such as an automatically constructed dictionary and crowdsourced dictionary, which are convenient for real-world applications.
References used
https://aclanthology.org/
rate research
Read More
Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural networ
k (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.
Multilingual question answering over knowledge graph (KGQA) aims to derive answers from a knowledge graph (KG) for questions in multiple languages. To be widely applicable, we focus on its zero-shot transfer setting. That is, we can only access train
ing data in a high-resource language, while need to answer multilingual questions without any labeled data in target languages. A straightforward approach is resorting to pre-trained multilingual models (e.g., mBERT) for cross-lingual transfer, but there is a still significant gap of KGQA performance between source and target languages. In this paper, we exploit unsupervised bilingual lexicon induction (BLI) to map training questions in source language into those in target language as augmented training data, which circumvents language inconsistency between training and inference. Furthermore, we propose an adversarial learning strategy to alleviate syntax-disorder of the augmented data, making the model incline to both language- and syntax-independence. Consequently, our model narrows the gap in zero-shot cross-lingual transfer. Experiments on two multilingual KGQA datasets with 11 zero-resource languages verify its effectiveness.
Graph convolutional networks (GCNs) have been applied recently to text classification and produced an excellent performance. However, existing GCN-based methods do not assume an explicit latent semantic structure of documents, making learned represen
tations less effective and difficult to interpret. They are also transductive in nature, thus cannot handle out-of-graph documents. To address these issues, we propose a novel model named inductive Topic Variational Graph Auto-Encoder (T-VGAE), which incorporates a topic model into variational graph-auto-encoder (VGAE) to capture the hidden semantic information between documents and words. T-VGAE inherits the interpretability of the topic model and the efficient information propagation mechanism of VGAE. It learns probabilistic representations of words and documents by jointly encoding and reconstructing the global word-level graph and bipartite graphs of documents, where each document is considered individually and decoupled from the global correlation graph so as to enable inductive learning. Our experiments on several benchmark datasets show that our method outperforms the existing competitive models on supervised and semi-supervised text classification, as well as unsupervised text representation learning. In addition, it has higher interpretability and is able to deal with unseen documents.
Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis o
n how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR.
Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of cross-lingual entity alignment under adversarial attacks. This paper
proposes an adversarial attack model with two novel attack techniques to perturb the KG structure and degrade the quality of deep cross-lingual entity alignment. First, an entity density maximization method is employed to hide the attacked entities in dense regions in two KGs, such that the derived perturbations are unnoticeable. Second, an attack signal amplification method is developed to reduce the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness.
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
