Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each Relation
تحسين إدارة الرسم البياني المعرفي باستخدام تحويلات آفينية للكيانات المقابلة لكل علاقة
116
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
للعثور على تضمين مناسب لرجل المعرفة يظل تحديا كبيرا في الوقت الحاضر. باستخدام أساليب شرطة المعرفة السابقة، عادة ما يتم تمثيل كل كيان في رسم بياني المعرفة كجاغر K- الأبعاد. كما نعلم، يمكن التعبير عن تحول أفيني في شكل مضاعفة مصفوفة تليها ناقلات الترجمة. في هذه الورقة، نستفيد أولا مجموعة من التحولات الفوضى المتعلقة بكل علاقة بتشغيل على ناقلات الكيان، ثم يتم استخدام هذه المتجهات المحولة لأداء التضمين مع الأساليب السابقة. تتمثل الميزة الرئيسية لاستخدام تحويلات Affine خصائص هندسة جيدة مع إمكانية الترجمة الشفوية. توضح نتائجنا التجريبية أن التصميم الفديهي المقترح مع تحويلات تفكيك يوفر زيادة ذات دلالة إحصائية في الأداء مع إضافة بعض خطوات معالجة إضافية أو إضافة عدد محدود من المتغيرات الإضافية. اتخاذ Transe كمثال، فإننا نوظف تحويل المقياس (الحالة الخاصة لتحويل أفيركي)، ويعرض فقط متغيرات إضافية لكل علاقة. من المستغرب، فإنه ينطبق على التدوير إلى حد ما على مجموعات البيانات المختلفة. نحن نقدم أيضا تحويلات تفكيكية إلى التدوير والضيق والمعقدة، على التوالي، وكل واحد يتفوق على طريقته الأصلية.
To find a suitable embedding for a knowledge graph remains a big challenge nowadays. By using previous knowledge graph embedding methods, every entity in a knowledge graph is usually represented as a k-dimensional vector. As we know, an affine transformation can be expressed in the form of a matrix multiplication followed by a translation vector. In this paper, we firstly utilize a set of affine transformations related to each relation to operate on entity vectors, and then these transformed vectors are used for performing embedding with previous methods. The main advantage of using affine transformations is their good geometry properties with interpretability. Our experimental results demonstrate that the proposed intuitive design with affine transformations provides a statistically significant increase in performance with adding a few extra processing steps or adding a limited number of additional variables. Taking TransE as an example, we employ the scale transformation (the special case of an affine transformation), and only introduce k additional variables for each relation. Surprisingly, it even outperforms RotatE to some extent on various data sets. We also introduce affine transformations into RotatE, Distmult and ComplEx, respectively, and each one outperforms its original method.
References used
https://aclanthology.org/
rate research
Read More
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities. In this paper, we emphasize the importance of incorporating events
in KG representation learning, and propose an event-enhanced KG embedding model EventKE. Specifically, given the original KG, we first incorporate event nodes by building a heterogeneous network, where entity nodes and event nodes are distributed on the two sides of the network inter-connected by event argument links. We then use entity-entity relations from the original KG and event-event temporal links to inner-connect entity and event nodes respectively. We design a novel and effective attention-based message passing method, which is conducted on entity-entity, event-entity, and event-event relations to fuse the event information into KG embeddings. Experimental results on real-world datasets demonstrate that events can greatly improve the quality of the KG embeddings on multiple downstream tasks.
Numeracy plays a key role in natural language understanding. However, existing NLP approaches, not only traditional word2vec approach or contextualized transformer-based language models, fail to learn numeracy. As the result, the performance of these
models is limited when they are applied to number-intensive applications in clinical and financial domains. In this work, we propose a simple number embedding approach based on knowledge graph. We construct a knowledge graph consisting of number entities and magnitude relations. Knowledge graph embedding method is then applied to obtain number vectors. Our approach is easy to implement, and experiment results on various numeracy-related NLP tasks demonstrate the effectiveness and efficiency of our method.
Most of the existing Knowledge-based Question Answering (KBQA) methods first learn to map the given question to a query graph, and then convert the graph to an executable query to find the answer. The query graph is typically expanded progressively f
rom the topic entity based on a sequence prediction model. In this paper, we propose a new solution to query graph generation that works in the opposite manner: we start with the entire knowledge base and gradually shrink it to the desired query graph. This approach improves both the efficiency and the accuracy of query graph generation, especially for complex multi-hop questions. Experimental results show that our method achieves state-of-the-art performance on ComplexWebQuestion (CWQ) dataset.
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.
Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of-knowledge-graph (OOKG) entities added frequently, and we need to effi
ciently represent these entities. Most existing Knowledge Graph Embedding (KGE) methods cannot represent OOKG entities without costly retraining on the whole KG. To enhance efficiency, we propose a simple and effective method that inductively represents OOKG entities by their optimal estimation under translational assumptions. Moreover, given pretrained embeddings of the in-knowledge-graph (IKG) entities, our method even needs no additional learning. Experimental results on two KGC tasks with OOKG entities show that our method outperforms the previous methods by a large margin with higher efficiency.
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
