Year-end Sale % OFF 
Abstract
Complex question answering in real world is a comprehensive and challenging task due to its demand for deeper question understanding and deeper inference. Information retrieval is a common solution and easy to implement, but it cannot answer questions which need long-distance dependencies across multiple documents. Knowledge base (KB) organizes information as a graph, and KB-based inference can employ logic formulas or knowledge embeddings to capture such long-distance semantic associations. However, KB-based inference has not been applied to real-world question answering well, because there are gaps among natural language, complex semantic structure, and appropriate hypothesis for inference. We propose decoupling KB-based inference by transforming a question into a high-level triplet in the KB, which makes it possible to apply KB-based inference methods to answer complex questions. In addition, we create a specialized question answering dataset only for inference, and our method is proved to be effective by conducting experiments on both AI2 Science Questions dataset and ours.
Highlights
Teaching machines to answer complex questions like human beings is a very challenging task at the intersection of nature language processing (NLP), information retrieval (IR), and artificial intelligence (AI), which mainly needs three techniques, i.e., question understanding, answer retrieval, and inference. ere are three subtasks to evaluate the corresponding techniques: Question Answering over Knowledge Base (KBQA) is a typical task to evaluate question understanding; Text Retrieval Question Answering (TREC question answering (QA)) and Reading Comprehension (RC) are good tasks to evaluate answer retrieval and answer selection; Link Prediction and Knowledge Base Completion (KBC) are traditional tasks to evaluate inference
This paper proposes decoupling Knowledge base (KB)-based inference from question answering by transforming a complex QA pair into a virtual high-level hypothesis on the KB
We can obtain the following observations: (1) Combining two types of inference methods with retrieval can improve performances, which proves that decoupling inference by virtual hypothesis is effective and KB-based inference can utilize a mass of extra long-distance knowledge to improve the performance of the retrieval method
Summary
Teaching machines to answer complex questions like human beings is a very challenging task at the intersection of nature language processing (NLP), information retrieval (IR), and artificial intelligence (AI), which mainly needs three techniques, i.e., question understanding, answer retrieval, and inference. ere are three subtasks to evaluate the corresponding techniques: Question Answering over Knowledge Base (KBQA) is a typical task to evaluate question understanding; Text Retrieval Question Answering (TREC QA) and Reading Comprehension (RC) are good tasks to evaluate answer retrieval and answer selection; Link Prediction and Knowledge Base Completion (KBC) are traditional tasks to evaluate inference.After achieving progress in these subtasks, researchers begin to turn their passion to more comprehensive and complex question answering (QA) tasks. Teaching machines to answer complex questions like human beings is a very challenging task at the intersection of nature language processing (NLP), information retrieval (IR), and artificial intelligence (AI), which mainly needs three techniques, i.e., question understanding, answer retrieval, and inference. Ere are three subtasks to evaluate the corresponding techniques: Question Answering over Knowledge Base (KBQA) is a typical task to evaluate question understanding; Text Retrieval Question Answering (TREC QA) and Reading Comprehension (RC) are good tasks to evaluate answer retrieval and answer selection; Link Prediction and Knowledge Base Completion (KBC) are traditional tasks to evaluate inference. After achieving progress in these subtasks, researchers begin to turn their passion to more comprehensive and complex question answering (QA) tasks. Q1: Peach trees have sweet-smelling blossoms and produce rich fruit. What is the main purpose of the flowers of a peach tree? (Answer is A.)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
