Corpus-based semantic role approach in information retrieval

Moreda, Paloma; Navarro, Borja; Palomar, Manuel

doi:10.1016/j.datak.2006.06.010

Cited by 24 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Specifically, these ML algorithms have improved NLP tasks such as word sense disambiguation (WSD) [14][15][16], part-of-speech tagging [17][18][19], text classification [20] including a brand new task to classify emails [21], machine translation [22,23] and named entity recognition, [24][25][26][27], among others. In addition, ML techniques are also used to improve the performance of final applications like information retrieval [28] or question answering [29], adding to these systems modules that are implemented using ML techniques.…”

Section: Main Methods and Current Status In The Fieldmentioning

confidence: 99%

Combining automatic acquisition of knowledge with machine learning approaches for multilingual temporal recognition and normalization

Saquete

Ferrández

et al. 2008

Information Sciences

View full text Add to dashboard Cite

Section: Main Methods and Current Status In The Fieldmentioning

confidence: 99%

Combining automatic acquisition of knowledge with machine learning approaches for multilingual temporal recognition and normalization

Saquete

Ferrández

et al. 2008

Information Sciences

View full text Add to dashboard Cite

“…For instance, semantic features have been applied to Information Retrieval and Question Answering (Moreda, Navarro, & Palomar, 2007;Moreda et al, 2011).…”

Section: Conclusion and Further Workmentioning

confidence: 99%

Applying semantic knowledge to the automatic processing of temporal expressions and events in natural language

Llorens

Saquete

Navarro-Colorado

2013

Information Processing & Management

View full text Add to dashboard Cite

“…Thus, each sentence corresponding to each emotion was processed by the SRL system by [30]. Subsequently we extracted from the output of this system the triplets corresponding to the actor, action and object related to each verb.…”

Section: H Expanding Emotinet With New Knowledge From Web Sourcesmentioning

confidence: 99%

“…For this, we employed the semantic role labelling (SRL) system introduced by [30]. In order to build the core of knowledge in the EmotiNet KB, we chose a subset of 175 examples (25 per emotion), which we denote by T. The criteria for choosing this subset were the simplicity of the sentences and the variety of actions described.…”

Section: B Modelling Situations With Semantic Rolesmentioning

confidence: 99%

Affect Detection from Social Contexts Using Commonsense Knowledge Representations

Balahur

Hermida

2012

2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing

View full text Add to dashboard Cite

In the past years, an important volume of research in Natural Language Processing has concentrated on the development of automatic systems to deal with affect in text. In spite of this interest, the performance of the approaches is still very low. An explanation to this fact is that emotion is most of the times not expressed through specific words, but by evoking situations that have an affective meaning. Dealing with this phenomenon requires automatic systems to have "knowledge" on the situation, the concepts it describes and their interaction. This necessity motivated us to develop the EmotiNet knowledge base -a resource for the detection of emotion from text based on commonsense knowledge on concepts, their interaction and their affective consequence. In this article, we present an overview of the process undergone to build EmotiNet, propose methods to extend the knowledge it contains and analyze the performance of implicit affect detection using this resource. Additionally, we compare the results obtained with EmotiNet to the use of well-established methods for affect detection. The results of our extensive evaluations show that the approach using EmotiNet is appropriate for capturing and storing the structure of implicitly expressed affect, that the knowledge it contains can be easily extended to improve the results of this task and that methods employing EmotiNet obtain better results than existing methods for emotion detection.

show abstract

Corpus-based semantic role approach in information retrieval

Cited by 24 publications

References 26 publications

Combining automatic acquisition of knowledge with machine learning approaches for multilingual temporal recognition and normalization

Combining automatic acquisition of knowledge with machine learning approaches for multilingual temporal recognition and normalization

Applying semantic knowledge to the automatic processing of temporal expressions and events in natural language

Affect Detection from Social Contexts Using Commonsense Knowledge Representations

Contact Info

Product

Resources

About