Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userKLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships
KLMO: رسم بياني المعرفة نموذج اللغة المحددة مسبقا مع علاقات حبيبات دقيقة
208
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توفر التفاعلات بين الكيانات في الرسم البياني للمعرفة (KG) معرفة غنية لتعلم تمثيل اللغة. ومع ذلك، تركز نماذج اللغة المحددة على المعرفة المعزوفة المعرفة الحالية (PLMS) فقط على معلومات الكيان وتجاهل العلاقات الجميلة بين الكيانات. في هذا العمل، نقترح دمج كجم (بما في ذلك كلا من الكيانات والعلاقات) في عملية التعلم اللغوي للحصول على نموذج اللغة المحسنة KG، وهي KLMO. على وجه التحديد، تم تصميم مجمع المعرفة الرواية للنموذج صراحة التفاعل بين الكيان يمتد في النص وجميع الكيانات والعلاقات في كجم سياقي. يتم استخدام هدف تنبؤ العلاقة لدمج معلومات العلاقة من خلال الإشراف البعيد. يتم استخدام هدف ربط الكيان بشكل أكبر لربط كيان يمتد في نص إلى كيانات في كجم. وبهذه الطريقة، يمكن دمج المعرفة المهيكلة بشكل فعال في تمثيلات اللغة. توضح النتائج التجريبية أن KLMO يحقق تحسينات كبيرة على العديد من المهام التي يحركها المعرفة، مثل تصنيف الكيانات وتصنيف العلاقة، مقارنة مع PLMs المعرفة المعززة للحكومة.
Interactions between entities in knowledge graph (KG) provide rich knowledge for language representation learning. However, existing knowledge-enhanced pretrained language models (PLMs) only focus on entity information and ignore the fine-grained relationships between entities. In this work, we propose to incorporate KG (including both entities and relations) into the language learning process to obtain KG-enhanced pretrained Language Model, namely KLMo. Specifically, a novel knowledge aggregator is designed to explicitly model the interaction between entity spans in text and all entities and relations in a contextual KG. An relation prediction objective is utilized to incorporate relation information by distant supervision. An entity linking objective is further utilized to link entity spans in text to entities in KG. In this way, the structured knowledge can be effectively integrated into language representations. Experimental results demonstrate that KLMo achieves great improvements on several knowledge-driven tasks, such as entity typing and relation classification, comparing with the state-of-the-art knowledge-enhanced PLMs.
References used
https://aclanthology.org/
rate research
Read More
To obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While the latter approach typically outperforms
the former, it requires great human effort to generate suitable datasets of sufficient size. In this paper, we show how PLMs can be leveraged to obtain high-quality sentence embeddings without the need for labeled data, finetuning or modifications to the pretraining objective: We utilize the generative abilities of large and high-performing PLMs to generate entire datasets of labeled text pairs from scratch, which we then use for finetuning much smaller and more efficient models. Our fully unsupervised approach outperforms strong baselines on several semantic textual similarity datasets.
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of labeled d
ata that is costly to collect. To address this drawback, we adopt a transfer learning approach and propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking (DB). To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair (QQP) and the ParaNMT datasets and is robust to domain shift between the two datasets of distinct distributions. We also demonstrate that our model transfers to paraphrasing in other languages without any additional finetuning.
Taxonomies are symbolic representations of hierarchical relationships between terms or entities. While taxonomies are useful in broad applications, manually updating or maintaining them is labor-intensive and difficult to scale in practice. Conventio
nal supervised methods for this enrichment task fail to find optimal parents of new terms in low-resource settings where only small taxonomies are available because of overfitting to hierarchical relationships in the taxonomies. To tackle the problem of low-resource taxonomy enrichment, we propose Musubu, an efficient framework for taxonomy enrichment in low-resource settings with pretrained language models (LMs) as knowledge bases to compensate for the shortage of information. Musubu leverages an LM-based classifier to determine whether or not inputted term pairs have hierarchical relationships. Musubu also utilizes Hearst patterns to generate queries to leverage implicit knowledge from the LM efficiently for more accurate prediction. We empirically demonstrate the effectiveness of our method in extensive experiments on taxonomies from both a SemEval task and real-world retailer datasets.
In this paper we present a system that exploits different pre-trained Language Models for assigning domain labels to WordNet synsets without any kind of supervision. Furthermore, the system is not restricted to use a particular set of domain labels.
We exploit the knowledge encoded within different off-the-shelf pre-trained Language Models and task formulations to infer the domain label of a particular WordNet definition. The proposed zero-shot system achieves a new state-of-the-art on the English dataset used in the evaluation.
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.
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
