Question Classification by Weighted Combination of Lexical, Syntactic and Semantic Features

Loni, Babak; Tulder, Gijs van; Wiggers, Pascal; Tax, David M. J.; Loog, Marco

doi:10.1007/978-3-642-23538-2_31

Cited by 21 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A benchmark dataset built by Li and Roth [3] is widely used in literature, and NLP techniques able to analyze the question are more or less well established [4]. On the other hand, different authors chose to extract from questions a broad variety of features [5], usually divided into lexical, syntactic and semantic [6,7]. Different works focused on the extraction of particular words, like whword and head-word [8], but good results were gained as long as the number of employed features was increased to a very high number [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Extracting Compact Sets of Features for Question Classification in Cognitive Systems: A Comparative Study

Pota

Fuggi

Esposito

et al. 2015

2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)

View full text Add to dashboard Cite

Question Classification is one of the key tasks of Cognitive Systems based on the Question Answering paradigm. It aims at identifying the type of the possible answer for a question expressed in natural language. Machine learning techniques are typically employed for this task, and exploit a high number of features extracted from labelled questions of benchmark training sets in order to achieve good classification results. However, the high dimensionality of the feature space often limits the possibility of applying more efficient classification approaches, due to high training costs. In this work, more compact sets of lexical and syntactic features are proposed to distinguish question classes. In particular, the widely used unigrams are substituted with a smaller number of features, extracted by modifying typical Natural Language Processing procedures for question analysis. The accuracy values gained on a benchmark dataset by using these different sets of features are compared among them and with the state-of-the-art, taking into account the required complexity at the same time. The new sets of extracted features show a good trade-off between accuracy and complexity.

show abstract

Section: Introductionmentioning

confidence: 99%

Extracting Compact Sets of Features for Question Classification in Cognitive Systems: A Comparative Study

Pota

Fuggi

Esposito

et al. 2015

2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)

View full text Add to dashboard Cite

show abstract

“…This feature aims at individuating the most informative word of the question for classification purposes. Introduced in [8], it is widely used and recognized to be useful [3,4,6,8,20]. It is extracted here from the parse tree, by using redefined rules, similar to those proposed by Collins [21], already modified in other works [6,8].…”

Section: Features Extraction and Representationmentioning

confidence: 98%

“…This is the mostly used set of features, since it usually allows obtaining the best results [3,4,6,8]. Unigrams are obtained from the set of tagged tokens of the question, by eliminating tokens with some tags, like DT, IN, and punctuation.…”

Section: Features Extraction and Representationmentioning

confidence: 99%

“…The UIUC benchmark dataset of classified questions [2] is widely used in literature to train and test QC modules. On the other hand, while NLP methods are quite well established, a broad variety of features, usually divided into lexical, syntactic and semantic [3,4], can be extracted from questions [5]. Support Vector Machines (SVMs) were revealed as the best machine learning method for this context [4][5][6][7], primarily for their feasibility to manage many features, since good results were gained as long as features were employed in a very high number [3,4,[6][7][8].…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Forward-Selection Algorithm for SVM-Based Question Classification in Cognitive Systems

Pota

Esposito

Pietro

2016

Smart Innovation, Systems and Technologies

View full text Add to dashboard Cite

Cognitive Systems have attracted attention in last years, especially regarding high interactivity of Question Answering systems. In this context, Question Classification plays an important role for individuation of answer type. It involves the use of Natural Language Processing of the question, the extraction of a broad variety of features, and the use of machine learning algorithms to map features with a given taxonomy of question classes. In this work, a novel learning approach is proposed, based on the use of Support Vector Machines, for building a set of classifiers, each one to use for different questions and comprising the respective features, chosen through a particular forward-selection procedure. This approach aims at decreasing the total number of features, by avoiding those giving scarce information and/or noise. A Question Classification framework is implemented, comprising new sets of features with low numerosity. The application on a benchmark dataset shows classification accuracy competitive with the state-of-the-art, by considering a lower number of features.

show abstract

“…A request is classified into the six actionable types mentioned earlier, for which we developed a mul- (Loni et al, 2011) due to the general question-based construct of the requests. Apache OpenNLP (Apache Software Foundation, 2011) was used to generate unigrams, bigrams, trigrams, chunking, and tagged unigrams, while Stanford Parser's implemented Collins rules (Collins, 2003) were used to obtain the headword.…”

Section: Request Type Classificationmentioning

confidence: 99%

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Katagiri

Nakano

Fernández

et al. 2016

View full text Add to dashboard Cite

We extend special thanks to our Local co-Chairs, Ron Artstein and Alesia Gainer, and their team of student volunteers. We know SIGDIAL 2016 would not have been possible without Ron and Alesia, who invested so much effort in arranging the conference venue and accommodations, handling registration, making banquet arrangements, and handling numerous other preparations for the conference. The student volunteers for on-site assistance also deserve our appreciation.Ethan Selfridge, Sponsorships Chair, has earned our appreciation for recruiting and liaising with our conference sponsors, many of whom continue to contribute year after year. Sponsorships support valuable aspects of the program, such as the invited speakers and conference banquet. In recognition of this, we gratefully acknowledge the support of our sponsors: (Platinum level) Microsoft Research, Xerox and PARC, Intel, (Gold level) Facebook, (Silver level) Amazon Alexa, Interactions, Educational Testing Service, Honda Research Institute, and Yahoo!. At the same time, we thank Priscilla Rasmussen at the ACL for tirelessly handling the financial aspects of sponsorship for SIGDIAL 2016, and for securing our ISBN.iii We also thank the SIGdial board, especially officers Amanda Stent, Jason Williams and Kristiina Jokinen for their advice and support from beginning to end.Finally, we thank all the authors of the papers in this volume, and all the conference participants for making this stimulating event a valuable opportunity for growth in the research areas of discourse and dialogue. AbstractThis paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent QNetworks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state. IntroductionTask-oriented dialog systems have been an important branch of spoken dialog system (SDS) research (Raux et al., 2005; Young, 2006; Bohus and Rudnicky, 2003). The SDS agent has to achieve some predefined targets (e.g. booking a flight) through natural language interaction with the users. The typical structure of a task-oriented dialog system is outlined in Figure 1 (Young, 2006). This pipeline consists of several independently-developed modules: natural language understanding (the NLU) maps the user utterances to some semantic representation. This information is further processed by the dialog state tracker (DST), which accumulates the input of the turn along with the dialog history. The DST outputs the current dialog state and the dialog policy selects the next system action based on the dialog state. Then natural language gene...

show abstract

Question Classification by Weighted Combination of Lexical, Syntactic and Semantic Features

Cited by 21 publications

References 15 publications

Extracting Compact Sets of Features for Question Classification in Cognitive Systems: A Comparative Study

Extracting Compact Sets of Features for Question Classification in Cognitive Systems: A Comparative Study

A Forward-Selection Algorithm for SVM-Based Question Classification in Cognitive Systems

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Contact Info

Product

Resources

About