تبادل مهام التحليل الدلالي الغني، مثل تمثيل المعنى التجريدي (AMR)، أهداف مماثلة مع استخراج المعلومات (أي) تحويل نصوص اللغة الطبيعية إلى تمثيلات دلالية منظم.للاستفادة من مثل هذه التشابه، نقترح إطارا رواية موجه AMR لاستخراج المعلومات المشترك لاكتشاف الكيانات والعلاقات والأحداث بمساعدة محلل عمرو المدرب مسبقا.يتكون إطارنا من مكونين جديدين: 1) مجمع الرسم البياني الدلالي الذي يستند إلى AMR للسماح للكيان المرشح وحدث الحدث العقد بجمع معلومات الحي من الرسم البياني AMR لرسالة المرور بين عناصر المعرفة ذات الصلة؛2) فك ترميز الرسم البياني AMR لاستخراج عناصر المعرفة بناء على الترتيب الذي يقرره الهياكل الهرمية في عمرو.أظهرت تجارب حول مجموعات البيانات المتعددة أن تشفير الرسوم البيانية للأمور القديمة وتقدم مكاسب كبيرة وقد حققت نهجنا أداء جديد من بين الفنون في جميع الخدمات الفرعية.
The tasks of Rich Semantic Parsing, such as Abstract Meaning Representation (AMR), share similar goals with Information Extraction (IE) to convert natural language texts into structured semantic representations. To take advantage of such similarity, we propose a novel AMR-guided framework for joint information extraction to discover entities, relations, and events with the help of a pre-trained AMR parser. Our framework consists of two novel components: 1) an AMR based semantic graph aggregator to let the candidate entity and event trigger nodes collect neighborhood information from AMR graph for passing message among related knowledge elements; 2) an AMR guided graph decoder to extract knowledge elements based on the order decided by the hierarchical structures in AMR. Experiments on multiple datasets have shown that the AMR graph encoder and decoder have provided significant gains and our approach has achieved new state-of-the-art performance on all IE subtasks.
References used
https://aclanthology.org/
Existing works on information extraction (IE) have mainly solved the four main tasks separately (entity mention recognition, relation extraction, event trigger detection, and argument extraction), thus failing to benefit from inter-dependencies betwe
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
This paper introduces the SemEval-2021 shared task 4: Reading Comprehension of Abstract Meaning (ReCAM). This shared task is designed to help evaluate the ability of machines in representing and understanding abstract concepts.Given a passage and the
The knowledge of the European silk textile production is a typical case for which the information collected is heterogeneous, spread across many museums and sparse since rarely complete. Knowledge Graphs for this cultural heritage domain, when being
This paper describes our system for SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. To accomplish this task, we utilize the Knowledge-Enhanced Graph Attention Network (KEGAT) architecture with a novel semantic space transformation str