Uncertainty Detection in Natural Language Texts

Vincze, Veronika

doi:10.14232/phd.2291

Cited by 35 publications

(30 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The uncertainty annotation of this text differed greatly from our corpus of Hungarian Wikipedia articles and news (Vincze, 2014), which domains are much closer to standard language use. Table 1 shows the distribution of the different types of uncertainty cues in these domains.…”

Section: Uncertainty In Hungarian Webtextmentioning

confidence: 93%

Annotating Uncertainty in Hungarian Webtext

Vincze¹,

Simkó²,

Varga³

2014

Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop

Self Cite

View full text Add to dashboard Cite

Uncertainty detection has been a popular topic in natural language processing, which manifested in the creation of several corpora for English. Here we show how the annotation guidelines originally developed for English standard texts can be adapted to Hungarian webtext. We annotated a small corpus of Facebook posts for uncertainty phenomena and we illustrate the main characteristics of such texts, with special regard to uncertainty annotation. Our results may be exploited in adapting the guidelines to other languages or domains and later on, in the construction of automatic uncertainty detectors. BackgroundDetecting uncertainty in natural language texts has received a considerable amount of attention in the last decade (Farkas et al., 2010;Morante and Sporleder, 2012). Several manually annotated corpora have been created, which serve as training and test databases of state-of-the-art uncertainty detectors based on supervised machine learning techniques. Most of these corpora are constructed for English, however, their domains and genres are diverse: biological texts (Medlock and Briscoe, 2007;Kim et al., 2008;Settles et al., 2008;Shatkay et al., 2008;Vincze et al., 2008;Nawaz et al., 2010) The diversity of the resources also manifests in the fact that the annotation principles behind the corpora might slightly differ, which led Szarvas et al. (2012) to compare the annotation schemes of three corpora (BioScope, FactBank and WikiWeasel) and they offered a unified classification of semantic uncertainty phenomena, on the basis of which these corpora were reannotated, using uniform guidelines. Some other uncertainty-related linguistic phenomena are described as discourse-level uncertainty in Vincze (2013). As a first objective of our paper, we will carry out a pilot study and investigate how these unified guidelines can be adapted to texts written in a language that is typologically different from English, namely, Hungarian.As a second goal, we will also focus on annotating texts in a new domain: social media textsapart from Wei et al. (2013) -have not been extensively investigated from the uncertainty detection perspective. As the use and communication through the internet is becoming more and more important in people's lives, the huge amount of data available from this domain is a valuable source of information for computation linguistics. However, processing texts from the web -especially social media texts from blogs, status updates, chat logs and comments -revealed that they are very challenging for applications trained on standard texts. Most studies in this area focus on English, for instance, sentiment analysis from tweets has been the focus of recent challenges (Wilson et al., 2013) and Facebook posts have been analysed from the perspective of computational psychology (Celli et al., 2013). A syntactically

show abstract

Section: Uncertainty In Hungarian Webtextmentioning

confidence: 93%

Annotating Uncertainty in Hungarian Webtext

Vincze¹,

Simkó²,

Varga³

2014

Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…As I mentioned earlier in Chapter 1, there is a plethora of work on uncertainty annotation for English (Rubin, 2007;Szarvas et al, 2008;Saurí and Pustejovsky, 2009;Matsuyoshi et al, 2010;Farkas et al, 2010;Rubinstein et al, 2013;Wei et al, 2013), Japanese (Hendrickx et al, 2012), Chinese (Cui and Chi, 2013), Portuguese (Hendrickx et al, 2012;Avila and Mello, 2013), and Hungarian (Vincze, 2014). However, prior to my own preliminary work (Al-Sabbagh et al, 2014a) and the work I presented in this chapter, there are no Arabic uncertainty-annotated corpora, to the best of my knowledge.…”

Section: Related Workmentioning

confidence: 99%

“…ere is a plethora of work on English (Matsuyoshi et al, 2010;Prabhakaran, 2010;Rubin, 2007;Rubinstein et al, 2013;Ruppenhofer and Rehbein, 2012;Saurí and Pustejovsky, 2009;Szarvas et al, 2008;Tang et al, 2010;Vincze et al, 2011;Wei et al, 2013), French (Goujon, 2009), Portuguese (Hendrickx et al, 2012;Avila and Mello, 2013), and Swedish (Mowery et al, 2012), yet nothing for agglutinative morphologically-rich languages except for Hungarian (Vincze, 2014). One reason for the li le research on agglutinative morphologically-rich languages with a exible word order is the lack of uncertainty-annotated corpora for such languages.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, exible word order results in very long dependencies that are not usually present in the English language. As a result, only Vincze (2014) has worked on uncertainty automatic analysis for agglutinative morphologically-rich languages with a exible word order, represented by Hungarian; yet, she has limited her work to uncertainty detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Unified Framework to Identify and Extract Uncertainty Cues, Holders, and Scopes in One Fell-Swoop

Al-Sabbagh

Gîrju

Diesner

2015

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

“…Such tasks include information extraction, question answering, medical information retrieval, opinion detection, sentiment analysis (Karttunen and Zaenen, 2005;Vincze, 2014a;Díaz et al, 2016) and knowledge base population (KBP). In KBP, we need to distinguish, e.g., "X may be Basque" and "X was rumored to be Basque" (uncertain) from "X is Basque" (certain) to decide whether to add the fact "Basque(X)" to a knowledge base.…”

Section: Introductionmentioning

confidence: 99%

Exploring Different Dimensions of Attention for Uncertainty Detection

Adel

Schütze

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Neural networks with attention have proven effective for many natural language processing tasks. In this paper, we develop attention mechanisms for uncertainty detection. In particular, we generalize standardly used attention mechanisms by introducing external attention and sequence-preserving attention. These novel architectures differ from standard approaches in that they use external resources to compute attention weights and preserve sequence information. We compare them to other configurations along different dimensions of attention. Our novel architectures set the new state of the art on a Wikipedia benchmark dataset and perform similar to the state-of-the-art model on a biomedical benchmark which uses a large set of linguistic features.

show abstract

Uncertainty Detection in Natural Language Texts

Cited by 35 publications

References 63 publications

Annotating Uncertainty in Hungarian Webtext

Annotating Uncertainty in Hungarian Webtext

A Unified Framework to Identify and Extract Uncertainty Cues, Holders, and Scopes in One Fell-Swoop

Exploring Different Dimensions of Attention for Uncertainty Detection

Contact Info

Product

Resources

About