Annotating discourse markers in spontaneous speech corpora on an example for the Slovenian language

Verdonik, Darinka; Rojc, Matej; Stabej, Marko

doi:10.1007/s10579-007-9035-7

Cited by 10 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is used more frequently in the Turdis-2 Corpus, but the difference in frequency is less pronounced (there are five times as many instances in the Turdis-2 Corpus as in the BNSIint Corpus) than for the previous set of discourse markers. In general, according to Verdonik (2007) and Verdonik, Rojc et al (2007), the most significant pragmatic functions, as well as the contextual factors shaping the use of dobro . .…”

Section: Dobro 'Right 'mentioning

confidence: 99%

“…According to Verdonik (2007) and Verdonik, Rojc et al (2007), glejte 'look' is used approximately twice as frequently in telephone conversations as in television interviews. It is used to attract the hearers' attention, it signals that the speaker is about to explain something.…”

Section: Glejte 'Look' and Veste 'You Know'mentioning

confidence: 99%

“…For Slovenian, which is the language used in this analysis, there have been relatively few studies exploring their use: Pisanski Peterlin (2005), Schlamberger Brezar (2007), Smolej (2004), and Verdonik, Rojc et al (2007).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The impact of context on discourse marker use in two conversational genres

2008

Self Cite

View full text Add to dashboard Cite

The relationships between text or talk and the context are among the basic fields of pragmatic research and an insight into their nature may contribute to a better understanding of language use. In this article, we use the results of an analysis of discourse marker use in two different conversational genres (telephone conversation and television interviews) in an attempt to examine the impact of context on the use of discourse markers, generalized for each analysed genre. In the first stage of the analysis, we observe important differences between the two genres: discourse markers are far more frequently used in telephone conversations than in television interviews. In the second stage of the analysis, we identify several contextual factors which contribute to the differences in the use of discourse markers. In this way, we obtain insight into this particular aspect of genre context-talk relationships, and identify some of the characteristics of the genres in question.K E Y W O R D S : context-talk relationships, conversational genre, discourse markers, language use, pragmatic expression, sociocognitive context model

show abstract

Section: Dobro 'Right 'mentioning

confidence: 99%

Section: Glejte 'Look' and Veste 'You Know'mentioning

confidence: 99%

See 1 more Smart Citation

The impact of context on discourse marker use in two conversational genres

2008

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data with DM annotation is scarcer for languages other than English. In a corpus of transcribed conversations in Slovenian, Verdonik et al (2007) annotated transcripts of 106 minutes of speech (15,517 words) with about twenty types of Slovenian DMs and their variants, finding 2,158 tokens. In an analysis of Dutch connectors, Penning and Theune (2007) counted DMs in a corpus of about 97,000 words, using sampling to estimate the frequency of lexical items that can serve as DMs or non-DMs.…”

Section: Dm Frequencies In the Icsi-mr And Other Corporamentioning

confidence: 99%

Automatic identification of discourse markers in dialogues: An in-depth study of like and well

Popescu-Belis¹,

Zufferey²

2011

Computer Speech & Language

View full text Add to dashboard Cite

The lexical items like and well can serve as discourse markers (DMs), but can also play numerous other roles, such as verb or adverb. Identifying the occurrences that function as DMs is an important step for language understanding by computers. In this study, automatic classifiers using lexical, prosodic/positional and sociolinguistic features are trained over transcribed dialogues, manually annotated with DM information. The resulting classifiers improve stateof-the-art performance, at about 90% recall and 79% precision for like (84.5% accuracy, κ = 0.69), and 99% recall and 98% precision for well (97.5% accuracy, κ = 0.88). Automatic feature analysis shows that lexical collocations are the most reliable indicators, followed by prosodic/positional features, while sociolinguistic features are marginally useful for the identification of DM like. The differentiated processing of each type of DM improves classification accuracy, suggesting that these types should be treated individually.

show abstract

“…Recently, Fitzgerald and Jelinek (2008) presented a new annotation scheme for spontaneous speech reconstruction, which has also been extended to Czech by Hajič et al (2008). Among related work on other Slavic languages, we can mention the paper about discourse marker annotation in spoken Slovenian by Verdonik et al (2007).…”

Section: Introductionmentioning

confidence: 99%

Design, creation, and analysis of Czech corpora for structural metadata extraction from speech

Kolář

2010

Lang Resources & Evaluation

View full text Add to dashboard Cite

Structural metadata extraction (MDE) research aims to develop techniques for automatic conversion of raw speech recognition output to forms that are more useful to humans and downstream automatic processes. The MDE annotation includes inserting boundaries of sentence-like units to the flow of speech, labeling non-content words like filled pauses and discourse markers for optional removal, and identifying sections of disfluent speech. This paper describes design, creation, and analysis of data resources for structural MDE from spoken Czech. The annotation is based on the LDC's MDE annotation standard for English, with changes applied to accommodate specific phenomena of Czech. In addition to the necessary language-dependent modifications, we further proposed and applied several language-independent modifications slightly refining the original annotation scheme. We created two Czech MDE speech corpora-one in the domain of broadcast news and the other in the domain of broadcast conversations. Both corpora have already been published at LDC. The analysis section of this paper presents a variety of statistics about fillers, edit disfluencies, and sentence-like units. The two Czech corpora are not only compared with each other, but also with statistics relating to the available English MDE corpora. We also report the statistics indicating that edit disfluencies have a different part of speech (POS) distribution in comparison with the overall POS distribution. The findings from the corpus analysis should help guide strategies for developing automatic MDE systems.

show abstract

Annotating discourse markers in spontaneous speech corpora on an example for the Slovenian language

Cited by 10 publications

References 28 publications

The impact of context on discourse marker use in two conversational genres

The impact of context on discourse marker use in two conversational genres

Automatic identification of discourse markers in dialogues: An in-depth study of like and well

Design, creation, and analysis of Czech corpora for structural metadata extraction from speech

Contact Info

Product

Resources

About