الفهم القراءة الآلة التفاعلية (IMRC) هو مهام فهم الجهاز حيث تكون مصادر المعرفة يمكن ملاحظتها جزئيا.يجب أن يتفاعل الوكيل مع بيئة بالتتابع لجمع المعرفة اللازمة من أجل الإجابة على سؤال.نحن نفترض أن تمثيلات الرسم البياني هي تحيزات حثي جيدة، والتي يمكن أن تكون بمثابة آلية ذاكرة الوكيل في مهام IMRC.نستكشف أربع فئات مختلفة من الرسوم البيانية التي يمكنها التقاط معلومات نصية على مختلف المستويات.نحن تصف الأساليب التي تقوم ببناء وتحديث هذه الرسوم البيانية هذه ديناميكيا أثناء جمع المعلومات، وكذلك النماذج العصبية لتشفير تمثيلات الرسم البياني في وكلاء RL.تشير تجارب واسعة النطاق على ISquad إلى أن تمثيلات الرسم البياني يمكن أن تؤدي إلى تحسينات كبيرة في الأداء لعوامل RL.
Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.
References used
https://aclanthology.org/
Knowledge Graphs (KGs) have become increasingly popular in the recent years. However, as knowledge constantly grows and changes, it is inevitable to extend existing KGs with entities that emerged or became relevant to the scope of the KG after its cr
Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this task by utilizing entities' contextual information. Specifically, we d
The design of expressive representations of entities and relations in a knowledge graph is an important endeavor. While many of the existing approaches have primarily focused on learning from relational patterns and structural information, the intrin
With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social biases, a
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large