Studio Ousia's Quiz Bowl Question Answering System
نویسندگان
چکیده
In this chapter, we describe our question answering system, which was the winning system at the Human–Computer Question Answering (HCQA) Competition at the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS). The competition requires participants to address a factoid question answering task referred to as quiz bowl. To address this task, we use two novel neural network models and combine these models with conventional information retrieval models using a supervised machine learning model. Our system achieved the best performance among the systems submitted in the competition and won a match against six top human quiz experts by a wide margin.
منابع مشابه
Constituency-Tree Recursive Neural Network for Quiz Bowl Answering
Quiz bowl answering represents a challenging task in natural language processing where few indication entities of answers are given in the questions. Traditional approaches such as manual feature engineering and bag of words representations can fail to reason the correct answers due to such lack of direct indications. Recently recursive neural network (RNN) model shows promising performance in ...
متن کاملAutomatic Classification of Quiz Bowl Questions LIN/COS 280 Final Project
The goal of automatic classification is to determine of which category out of a predefined set of categories a sample is most likely a member, given a training set of already-classified samples. For this project, I apply several classifiers to the problem of automatically categorizing quiz bowl questions. The American Competition Federation (ACF), in particular, makes past competition questions...
متن کاملA Neural Network for Factoid Question Answering over Paragraphs
Text classification methods for tasks like factoid question answering typically use manually defined string matching rules or bag of words representations. These methods are ineffective when question text contains very few individual words (e.g., named entities) that are indicative of the answer. We introduce a recursive neural network (rnn) model that can reason over such input by modeling tex...
متن کاملCrowdsourcing for Multiple-Choice Question Answering
We leverage crowd wisdom for multiple-choice question answering, and employ lightweight machine learning techniques to improve the aggregation accuracy of crowdsourced answers to these questions. In order to develop more effective aggregation methods and evaluate them empirically, we developed and deployed a crowdsourced system for playing the “Who wants to be a millionaire?” quiz show. Analyzi...
متن کاملارایه یک پیکره پرسش و پاسخ مذهبی در زبان فارسی
Question answering system is a field in natural language processing and information retrieval noticed by researchers in these decades. Due to a growing interest in this field of research, the need to have appropriate data sources is perceived. Most researches about developing question answering corpus area have been done in English so far, but in other languages as Persian, the lack of these co...
متن کامل