Syntactic and Semantic Kernels for Short Text Pair Categorization
By Alessandro Moschitti. 2009
36 citations recorded by the source corpus.
Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy.
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
- Julia Hockenmaier
- Micah Hodosh
- Peter Young
- Ion Androutsopoulos
- Jianfeng Gao
- Prodromos Malakasiotis
- Aliaksei Severyn
- Marie-Francine Moens
In Natural Language Processing
- Julia Hockenmaier
- Micah Hodosh
- Peter Young
- Ion Androutsopoulos
- Prodromos Malakasiotis
- Marie-Francine Moens
- Oleksandr Kolomiyets
- Jianfeng Gao
Citations in the corpus
- Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, positive): “In all other cases, we follow Moschitti (2009) and sum the kernel responses over the cross product of sentences before normalization.”
- Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “Regarding kernel methods, the work in [91,95,96,98,99,133] were the first to exploit tree kernels for modeling answer re-ranking.”
- A survey on question answering technology from an information retrieval perspective (2011, methodology): “The success factor of SVM lies in introducing a syntactic or semantic kernel function [152, 91].”
- A Survey of Paraphrasing and Textual Entailment Methods (2009, methodology): “Consult, for example, the work of Zanzotto and Dell’ Arciprete (2009) and Moschitti (2009) for further discussion of kernels that can be used in paraphrase and textual entailment recognition.”
- Predicting Tasks in Goal-Oriented Spoken Dialog Systems using Semantic Knowledge Bases (2013, background): “(Cristianini et al., 2002) (Wang and Domeni-coni, 2008) (Moschitti, 2009) found that open-242 domain semantic knowledge resources are useful for text classification problems.”