Statistical shallow semantic parsing despite little training data

Bhagat, Rahul; Leuski, Anton; Hovy, Eduard

doi:10.3115/1654494.1654514

Cited by 12 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results evidenced that these semantic classes just by themselves are very helpful to question classification, resulting in an accuracy of 93.2%. Moreover, these semantic classes can also be used to augment the training set, as demonstrated by (Bhagat et al 2005). With all semantic features combined, these authors achieved an accuracy of 94.0% which, to date, outperforms every other question classifier on the standard training set of Li and Roth, for coarse-grained classification.…”

Section: Machine Learning-based Question Classifiersmentioning

confidence: 94%

From symbolic to sub-symbolic information in question classification

et al. 2010

View full text Add to dashboard Cite

Question Answering (QA) is undoubtedly a growing field of current research in Artificial Intelligence. Question classification, a QA subtask, aims to associate a category to each question, typically representing the semantic class of its answer. This step is of major importance in the QA process, since it is the basis of several key decisions. For instance, classification helps reducing the number of possible answer candidates, as only answers matching the question category should be taken into account. This paper presents and evaluates a rulebased question classifier that partially founds its performance in the detection of the question headword and in its mapping into the target category through the use of WordNet. Moreover, we use the rule-based classifier as a features' provider of a machine learning-based question classifier. A detailed analysis of the rule-base contribution is presented. Despite using a very compact feature space, state of the art results are obtained.

show abstract

Section: Machine Learning-based Question Classifiersmentioning

confidence: 94%

From symbolic to sub-symbolic information in question classification

et al. 2010

View full text Add to dashboard Cite

show abstract

“…ELIZA can be seen as the predecessor of nowadays chatbots, such as Cleverbot 2 and ALICE 3 , which try to simulate human conversation. Many of these systems target to pass the Turing test and win the Lobner prize 4 . In what concerns LUNAR, this natural language interface capable of answering questions about moon rocks also deserves some detach, as it started the line of research responsible for a panoply of Natural Language Interfaces with Databases (NLIDB), in the 80s and 90s, which ended up converging in question/answering (QA) systems.…”

Section: Natural Language Understandingmentioning

confidence: 99%

“…Sub-symbolic techniques, as in so many other research fields, are currently being widely applied to NLU. For instance, Bhagat [4] treats NLU as a classification problem, i.e., his final goal is to be able to classify an utterance. Thus, Maximum Entropy and Support Vector Machines are used in some of their experiments.…”

Section: Natural Language Understandingmentioning

confidence: 99%

A critical survey on the use of Fuzzy Sets in Speech and Natural Language Processing

Carvalho

Batista

Coheur

2012

2012 IEEE International Conference on Fuzzy Systems

View full text Add to dashboard Cite

This paper shows how the use and applications of Fuzzy Sets (FS) in Speech and Natural Language Processing (SNLP) have seen a steady decline to a point where FS are virtually unknown or unappealing for most of the researchers currently working in the SNLP field, tries to find the reasons behind this decline, and proposes some guidelines on what could be done to reverse it and make FS assume a relevant role in SNLP.

show abstract

“…In what concerns sub-symbolic NLU, some systems receive text as input [5] and many are dealing with transcriptions from an Automatic Speech Recognizer [9]. In fact, considering speech understanding, the new trends considers NLU from a machine learning point of view.…”

Section: Related Workmentioning

confidence: 99%

Towards the Rapid Development of a Natural Language Understanding Module

Moreira

Mendes

Coheur

et al. 2011

Intelligent Virtual Agents

View full text Add to dashboard Cite

When developing a conversational agent, there is often an urgent need to have a prototype available in order to test the application with real users. A Wizard of Oz is a possibility, but sometimes the agent should be simply deployed in the environment where it will be used. Here, the agent should be able to capture as many interactions as possible and to understand how people react to failure. In this paper, we focus on the rapid development of a natural language understanding module by non experts. Our approach follows the learning paradigm and sees the process of understanding natural language as a classification problem. We test our module with a conversational agent that answers questions in the art domain. Moreover, we show how our approach can be used by a natural language interface to a cinema database.

show abstract

Statistical shallow semantic parsing despite little training data

Cited by 12 publications

References 16 publications

From symbolic to sub-symbolic information in question classification

From symbolic to sub-symbolic information in question classification

A critical survey on the use of Fuzzy Sets in Speech and Natural Language Processing

Towards the Rapid Development of a Natural Language Understanding Module

Contact Info

Product

Resources

About