Finding Answers in Large Collections of Texts: Paragraph Indexing + Abductive Inference
نویسندگان
چکیده
This paper describes a methodology of answering questions by using information retrieved from very large collections of texts. We argue that combinations of information retrieval and extractions techniques cannot be used, due to the open-domain nature of the task. We propose a solution based on indexing techniques that identify paragraphs from texts where the answers can be found. The validity of the answers is obtained through a lightweight process of abduction.
منابع مشابه
LASSO: A Tool for Surfing the Answer Net
This paper presents the architecture, operation and results obtained with the Lasso system developed in the Natural Language Processing Laboratory at SMU. The system relies on a combination of syntactic and semantic techniques, and lightweight abductive inference to nd answers. The search for the answer is based on a novel form of indexing called paragraph indexing. A score of 55.5% for short a...
متن کاملAbductive Processes for Answer Justification
An answer mined from text collections is deemed correct if an explanation or justification is provided. Due to multiple language ambiguities, abduction, or inference to the best explanation, is a possible vehicle for such justifications. To interpret abductively an answer, world knowledge, iexico-semantic knowledge as well as pragmatic knowledge need to be integrated. This paper presents variou...
متن کاملGenerative Paragraph Vector
The recently introduced Paragraph Vector is an efficient method for learning highquality distributed representations for pieces of texts. However, an inherent limitation of Paragraph Vector is lack of ability to infer distributed representations for texts outside of the training set. To tackle this problem, we introduce a Generative Paragraph Vector, which can be viewed as a probabilistic exten...
متن کاملAutomatic keyword extraction using Latent Dirichlet Allocation topic modeling: Similarity with golden standard and users' evaluation
Purpose: This study investigates the automatic keyword extraction from the table of contents of Persian e-books in the field of science using LDA topic modeling, evaluating their similarity with golden standard, and users' viewpoints of the model keywords. Methodology: This is a mixed text-mining research in which LDA topic modeling is used to extract keywords from the table of contents of sci...
متن کاملA Consequence Finding Approach for Full Clausal Abduction
Abductive inference has long been associated with the logic of scientific discovery and automated abduction is now being used in real scientific tasks. But few methods can exploit the full potential of clausal logic and abduce non-ground explanations with indefinite answers. This paper shows how the consequence finding method of Skip Ordered Linear (SOL) resolution can overcome the limitations ...
متن کامل