Konferenzbeitrag
Improving Sentence Boundary Detection for Spoken Language Transcripts
This paper presents experiments on sentence boundary detection in transcripts of spoken dialogues. Segmenting spoken language into sentence-like units is a challenging task, due to disfluencies, ungrammatical or fragmented structures and the lack of punctuation. In addition, one of the main bottlenecks for many NLP applications for spoken language is the small size of the training data, as the transcription and annotation of spoken language is by far more time-consuming and labour-intensive than processing written language. We therefore investigate the benefits of data expansion and transfer learning and test different ML architectures for this task. Our results show that data expansion is not straightforward and even data from the same domain does not always improve results. They also highlight the importance of modelling, i.e. of finding the best architecture and data representation for the task at hand. For the detection of boundaries in spoken language transcripts, we achieve a substantial improvement when framing the boundary detection problem as a sentence pair classification task, as compared to a sequence tagging approach.
- Language
-
Englisch
- Subject
-
Automatische Spracherkennung
Gesprochene Sprache
Korpus <Linguistik>
Satzende
Maschinelles Lernen
Sprache
- Event
-
Geistige Schöpfung
- (who)
-
Rehbein, Ines
Ruppenhofer, Josef
Schmidt, Thomas
- Event
-
Veröffentlichung
- (who)
-
Paris : European Language Resources Association
- (when)
-
2020-05-19
- URN
-
urn:nbn:de:bsz:mh39-98382
- Last update
-
06.03.2025, 9:00 AM CET
Data provider
Leibniz-Institut für Deutsche Sprache - Bibliothek. If you have any questions about the object, please contact the data provider.
Object type
- Konferenzbeitrag
Associated
- Rehbein, Ines
- Ruppenhofer, Josef
- Schmidt, Thomas
- Paris : European Language Resources Association
Time of origin
- 2020-05-19
Other Objects (12)
Detecting the boundaries of sentence-like units on spoken German
A New Resource for German Causal Language
There’s no Data like More Data? Revisiting the Impact of Data Size on a Classification Task
Detecting annotation noise in automatically labelled data
I’ve got a construction looks funny – representing and recovering non-standard constructions in UD
Sprucing up the trees – error detection in treebanks
Evaluating the Impact of Coder Errors on Active Learning
Semantic frames as an anchor representation for sentiment analysis
Catching the common cause: extraction and annotation of causal relations and their participants
Yes we can!? Annotating the senses of English modal verbs
Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates
Is it worth the effort? Assessing the benefits of partial automatic pre-labeling for frame-semantic annotation
Detecting the boundaries of sentence-like units on spoken German
A New Resource for German Causal Language
There’s no Data like More Data? Revisiting the Impact of Data Size on a Classification Task
Detecting annotation noise in automatically labelled data
I’ve got a construction looks funny – representing and recovering non-standard constructions in UD
Sprucing up the trees – error detection in treebanks
Evaluating the Impact of Coder Errors on Active Learning
Semantic frames as an anchor representation for sentiment analysis
Catching the common cause: extraction and annotation of causal relations and their participants
Yes we can!? Annotating the senses of English modal verbs
Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates
Is it worth the effort? Assessing the benefits of partial automatic pre-labeling for frame-semantic annotation
Detecting the boundaries of sentence-like units on spoken German
A New Resource for German Causal Language
There’s no Data like More Data? Revisiting the Impact of Data Size on a Classification Task
Detecting annotation noise in automatically labelled data
I’ve got a construction looks funny – representing and recovering non-standard constructions in UD
Sprucing up the trees – error detection in treebanks
Evaluating the Impact of Coder Errors on Active Learning
Semantic frames as an anchor representation for sentiment analysis
Catching the common cause: extraction and annotation of causal relations and their participants
Yes we can!? Annotating the senses of English modal verbs
Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates