Learning Question Classifiers

By Xin Li, Dan Roth. 2002

1,719 citations recorded by the source corpus.

In order to respond correctly to a free form factual question given a large collection of texts, one needs to understand the question to a level that allows determining some of the constraints the question imposes on a possible answer. These constraints may include a semantic classification of the sought after answer and may even suggest using different strategies when looking for and verifying a candidate answer.This paper presents a machine learning approach to question classification. We learn a hierarchical classifier that is guided by a layered semantic hierarchy of answer types, and eventually classifies questions into fine-grained classes. We show accurate results on a large collection of free-form questions used in TREC 10.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Skip-Thought Vectors (2015, methodology): “10-fold cross-validation is used for evaluation on the first 4 datasets, while TREC has a pre-defined train/test split.”
Generating Sentences from a Continuous Space (2015, methodology): “Question classification We also conduct experiments on the TREC Question Classification dataset of Li and Roth (2002). Following Kiros”
A Convolutional Neural Network for Modelling Sentences (2014, methodology): “Li and Roth (2002), Blunsom et al. (2006), Huang et al. (2008) and Silva et al. (2011).”
Finetuned Language Models Are Zero-Shot Learners (2021, neutral): “Question classification: TREC (Li & Roth, 2002; Hovy et al., 2001) 4.”
Representation Learning with Contrastive Predictive Coding (2018, methodology): “For the classification tasks we used the following datasets: movie review sentiment (MR) [43], customer product reviews (CR) [44], subjectivity/objectivity [45], opinion polarity (MPQA) [46] and question-type classification (TREC) [47].”
SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers (2021, background): “(iii) TREC-6 6 : a question classiﬁcation task proposed by Li and Roth (2002), where each question should be classi-ﬁed into one of 6 question types.”
Convolutional Neural Networks for Sentence Classification (2014, background): “) (Li and Roth, 2002).”
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019, background): “• TREC : Fine grained question-type classiﬁ-cation from TREC (Li and Roth, 2002).”
WikiQA: A Challenge Dataset for Open-Domain Question Answering (2015, neutral): “The performance is comparable to (Li and Roth, 2002).”
Universal Sentence Encoder (2018, background): “TREC : Fine grained question classification sourced from TREC (Li and Roth, 2002).”
A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification (2015, neutral): “(5) TREC: Question classification dataset (Li and Roth, 2002).”
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples (2017, background): “Question Type (QT) [28]), which contains 1000 training examples and 500 testing examples.”
Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN (2018, background): “Topical text classification is a fundamental text mining problem for many applications, such as news classification [18], question answering [28], search result organization [11], online advertising [2], etc.”
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction (2019, methodology): “We also include the TREC query classification datasets (Li and Roth, 2002), which have a large set of labels, but they describe the desired response type (e.”