Paraphrase-Driven Learning for Open Question Answering
نویسندگان
چکیده
We study question answering as a machine learning problem, and induce a function that maps open-domain questions to queries over a database of web extractions. Given a large, community-authored, question-paraphrase corpus, we demonstrate that it is possible to learn a semantic lexicon and linear ranking function without manually annotating questions. Our approach automatically generalizes a seed lexicon and includes a scalable, parallelized perceptron parameter estimation scheme. Experiments show that our approach more than quadruples the recall of the seed lexicon, with only an 8% loss in precision.
منابع مشابه
A Survey on Paraphrase Recognition
Paraphrase Recognition is a task of growing interest in the natural language process (NLP) research during the last years. This task aims to detect if two sentences have the same meaning. Paraphrase relationship described in this work is not the definition given by the common knowledge, but is more natural language oriented since it is driven by a lot of background human knowledge. This type of...
متن کاملUsing Multiple Metrics in Automatically Building Turkish Paraphrase Corpus
Paraphrasing is expressing similar meanings with different words in different order. In this sense it is viewed as translation in the same language. It is an important issue in natural language processing for automatic machine translation, question answering, text summarization and language generation. Studies in paraphrasing can be classified as paraphrase extraction, paraphrase generation, pa...
متن کاملParaphrase Identification using Machine Learning Techniques
Paraphrases are different ways of expressing the same content. Two sentences are said to be paraphrases if they are semantically equivalent. Identification of paraphrases has numerous applications such as Information Extraction, Question Answering, etc. The traditional systems use threshold values to decide whether two sentences are paraphrases. This threshold determination process is independe...
متن کاملParaphrase Generation with Deep Reinforcement Learning
Automatic generation of paraphrases for a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, information retrieval and dialogue. In this paper we present a deep reinforcement learning approach to paraphrase generation. Specifically, we propose a new model for the task, which consi...
متن کاملQuestion categorization for a question answering system using a vector space model
The purpose of the thesis is to assign questions to sense categories, where the sense categories are represented by predefined paraphrase sets of questions. The paraphrase sets are available for each domain in the Question Answering system and consist of different framings of questions that will lead to the same answer in the Question Answering system. A Java program was developed for the categ...
متن کامل