Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userProbabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
Abbilistic Box AgedDings لغير المعرفة المعرفة
88
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما تتكون قواعد المعرفة من الحقائق التي يتم حصادها من مجموعة متنوعة من المصادر، وكثير منها صاخبة وبعضها يتزاعل، مما يؤدي إلى مستوى عدم اليقين لكل ثلاثة أضعاف. ومع ذلك، غالبا ما تكون قواعد المعرفة في كثير من الأحيان غير مكتملة، مما يدفع استخدام طرق التضمين إلى التعميم من الحقائق المعروفة، ومع ذلك، فإن أساليب التضمين الحالية فقط من عدم اليقين على المستوى الثلاثي النموذجي، وتفتقر نتائج المنطق إلى الاتساق العالمي. لمعالجة هذه العيوب، نقترح Beurre، وهي طريقة تضمين مخطط المعرفة غير المؤكدة مع دلالات الاحتمالية المعايرة. نماذج Beurre كل كيان كمربع (أي فرط محاذاة محاذاة المحور) والعلاقات بين كيانين يتحولان إلى صناديق الرأس والذيل. يسمح هندسة الصناديق بحساب فعاليات التقاطعات والأحجام، وينصب النموذج مع دلالات الاحتمال المعايرة وتسهيل دمج القيود العلائقية. تظهر تجارب واسعة على مجموعة من مجموعات البيانات القياسية أن البورصة تتفوق باستمرار على خطوط الأساس حول تنبؤ الثقة وترتيب الحقائق بسبب معايرةها الاحتمالية وقدرتها على التقاط تبعيات عالية النظام بين الحقائق.
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 use 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.
References used
https://aclanthology.org/
rate research
Read More
Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic st
ructures among dialog rounds and (2) identifying several appropriate answers to the given question. To address these challenges, we propose a Sparse Graph Learning (SGL) method to formulate visual dialog as a graph structure learning task. SGL infers inherently sparse dialog structures by incorporating binary and score edges and leveraging a new structural loss function. Next, we introduce a Knowledge Transfer (KT) method that extracts the answer predictions from the teacher model and uses them as pseudo labels. We propose KT to remedy the shortcomings of single ground-truth labels, which severely limit the ability of a model to obtain multiple reasonable answers. As a result, our proposed model significantly improves reasoning capability compared to baseline methods and outperforms the state-of-the-art approaches on the VisDial v1.0 dataset. The source code is available at https://github.com/gicheonkang/SGLKT-VisDial.
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.
Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study these challenges through the problem of tabular natural language infe
rence. We propose easy and effective modifications to how information is presented to a model for this task. We show via systematic experiments that these strategies substantially improve tabular inference performance.
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.
Pre-trained language models have led to substantial gains over a broad range of natural language processing (NLP) tasks, but have been shown to have limitations for natural language generation tasks with high-quality requirements on the output, such
as commonsense generation and ad keyword generation. In this work, we present a novel Knowledge Filtering and Contrastive learning Network (KFCNet) which references external knowledge and achieves better generation performance. Specifically, we propose a BERT-based filter model to remove low-quality candidates, and apply contrastive learning separately to each of the encoder and decoder, within a general encoder--decoder architecture. The encoder contrastive module helps to capture global target semantics during encoding, and the decoder contrastive module enhances the utility of retrieved prototypes while learning general features. Extensive experiments on the CommonGen benchmark show that our model outperforms the previous state of the art by a large margin: +6.6 points (42.5 vs. 35.9) for BLEU-4, +3.7 points (33.3 vs. 29.6) for SPICE, and +1.3 points (18.3 vs. 17.0) for CIDEr. We further verify the effectiveness of the proposed contrastive module on ad keyword generation, and show that our model has potential commercial value.
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
