Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBox-To-Box Transformations for Modeling Joint Hierarchies
تحويل المربع إلى مربع لنمذجة التسلسلات الهرمية المشتركة
145
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعتبر تمثيل التعلم من الكيانات والعلاقات في قواعد المعرفة المنظمة مجالا نشطا من الأبحاث، مع التركيز بكثير في اختيار الهندسة المناسبة لالتقاط الهياكل الهرمية المستغلة في علاقات ISA أو Haspart. تضيحية الصندوق (Vilnis et al.، 2018؛ لي وآخرون، 2019؛ Dasgupta et al.، 2020)، والتي تمثل المفاهيم مثل تسلسلات النفايات الأبعاد، قادرة على تضمين التسلسلات الهرمية عند التدريب على مجموعة فرعية من الإغلاق المتعتقدين. في Patel et al.، (2020)، يوضح المؤلفون أن التخفيض المتعتقدين فقط مطلوب ومواصلة توسيع نطاق مذكرات الصندوق لالتقاط التسلسلات الهرمية المشتركة عن طريق زيادة الرسم البياني مع العقد الجديدة. في حين أنه من الممكن تمثيل التسلسلات الهرمية المشتركة بهذه الطريقة، يتم فصل المعلمات لكل التسلسل الهرمي، مما يجعل التعميم بين التسلسلات الهرمية بشكل غير قابل للإصلاح. في هذا العمل، نقدم تحول مربع إلى مربع المستفاد يحترم بنية كل التسلسل الهرمي. نوضح أن هذا لا يحسن فقط القدرة على النمذجة الحواف التركيبية في النمذجة، ولكنها قادرة أيضا على التعميم من مجموعة فرعية من الحد المتعدود.
Learning representations of entities and relations in structured knowledge bases is an active area of research, with much emphasis placed on choosing the appropriate geometry to capture the hierarchical structures exploited in, for example, isa or haspart relations. Box embeddings (Vilnis et al., 2018; Li et al., 2019; Dasgupta et al., 2020), which represent concepts as n-dimensional hyperrectangles, are capable of embedding hierarchies when training on a subset of the transitive closure. In Patel et al., (2020), the authors demonstrate that only the transitive reduction is required and further extend box embeddings to capture joint hierarchies by augmenting the graph with new nodes. While it is possible to represent joint hierarchies with this method, the parameters for each hierarchy are decoupled, making generalization between hierarchies infeasible. In this work, we introduce a learned box-to-box transformation that respects the structure of each hierarchy. We demonstrate that this not only improves the capability of modeling cross-hierarchy compositional edges but is also capable of generalizing from a subset of the transitive reduction.
References used
https://aclanthology.org/
rate research
Read More
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translat
ion by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. HKD generates a set of multilingual teacher-assistant models via a selective knowledge distillation mechanism based on the language groups, and then distills the ultimate multilingual model from those assistants in an adaptive way. Experimental results derived from the TED dataset with 53 languages demonstrate the effectiveness of our approach in avoiding the negative transfer effect in MNMT, leading to an improved translation performance (about 1 BLEU score in average) compared to strong baselines.
Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT). Traditionally, a QE system accepts the original source text and translation from a black-box MT system as input. Recently, a few studies indicate that as a b
y-product of translation, QE benefits from the model and training data's information of the MT system where the translations come from, and it is called the glass-box QE''. In this paper, we extend the definition of glass-box QE'' generally to uncertainty quantification with both black-box'' and glass-box'' approaches and design several features deduced from them to blaze a new trial in improving QE's performance. We propose a framework to fuse the feature engineering of uncertainty quantification into a pre-trained cross-lingual language model to predict the translation quality. Experiment results show that our method achieves state-of-the-art performances on the datasets of WMT 2020 QE shared task.
We investigate grounded language learning through real-world data, by modelling a teacher-learner dynamics through the natural interactions occurring between users and search engines; in particular, we explore the emergence of semantic generalization
from unsupervised dense representations outside of synthetic environments. A grounding domain, a denotation function and a composition function are learned from user data only. We show how the resulting semantics for noun phrases exhibits compositional properties while being fully learnable without any explicit labelling. We benchmark our grounded semantics on compositionality and zero-shot inference tasks, and we show that it provides better results and better generalizations than SOTA non-grounded models, such as word2vec and BERT.
The study aimed to know the role of golden marketing in improving the financial performance of private commercial banks in the Syrian coast, where the study community was among those working in these banks. The study used the deductive approach as a
general approach to research, descriptive approach, and the questionnaire as a tool to collect data from a soft sample, where (184) questionnaires were distributed and (155) questionnaires valid for analysis were retrieved.The study adopted the appropriate methods of analysis using the statistical package spss, which were represented in: arithmetic mean, standard deviation, percentage. Arithmetic test (t test) (for one sample). Honesty and consistency tests. The study reached results indicating that the mental image and its stabilization, customer satisfaction with the bank, and customer loyalty to the bank, affect improving the financial performance of the studied commercial banks.
Knowledge bases often consist of facts which are harvested from a variety of sources, many of which are noisy and some of which conflict, resulting in a level of uncertainty for each triple. Knowledge bases are also often incomplete, prompting the us
e of embedding methods to generalize from known facts, however, existing embedding methods only model triple-level uncertainty, and reasoning results lack global consistency. To address these shortcomings, we propose BEUrRE, a novel uncertain knowledge graph embedding method with calibrated probabilistic semantics. BEUrRE models each entity as a box (i.e. axis-aligned hyperrectangle) and relations between two entities as affine transforms on the head and tail entity boxes. The geometry of the boxes allows for efficient calculation of intersections and volumes, endowing the model with calibrated probabilistic semantics and facilitating the incorporation of relational constraints. Extensive experiments on two benchmark datasets show that BEUrRE consistently outperforms baselines on confidence prediction and fact ranking due to its probabilistic calibration and ability to capture high-order dependencies among facts.
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
