Constituency-Tree Recursive Neural Network for Quiz Bowl Answering
نویسندگان
چکیده
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 quiz bowl answering by outperforming multiple baselines. In this work, we introduce a constituency-tree recursive neural network (CT-RNN) and evaluate its performance on a public dataset.
منابع مشابه
Studio Ousia's Quiz Bowl Question Answering System
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 networ...
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 کاملConquering vanishing gradient: Tensor Tree LSTM on aspect-sentiment classification
Our project focus on the problem of aspect specific sentiment analysis using recursive neural networks. Different from the previous studies where labels exist on every node of constituency tree, we have only one label each sentence, which is only on the root node, and it causes a severe vanishing gradient problem for both RNN and RNTN. To deal with such problem, we develop a classification algo...
متن کاملLanguage Processing and Learning Models for Community Question Answering in Arabic
In this paper we focus on the problem of question ranking in community question answering (cQA) forums in Arabic. We address the task with machine learning algorithms using advanced Arabic text representations. The latter are obtained by applying tree kernels to constituency parse trees combined with textual similarities, including word embeddings. Our two main contributions are: (i) an Arabic ...
متن کاملTree-based Convolution: A New Neural Architecture for Sentence Modeling
This paper proposes a new convolutional neural architecture based on treestructures, called the tree-based convolutional neural network (TBCNN). Two variants take advantage of constituency trees and dependency trees, respectively, to model sentences. Compared with traditional “flat” convolutional neural networks (CNNs), TBCNNs explore explicitly sentences’ structural information; compared with ...
متن کامل