DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 27

1
TESOL student teacher discourse : a corpus-based analysis of online and face-to-face interactions
Riordan, Elaine. - London : Routledge, 2018
BLLDB
UB Frankfurt Linguistik
Show details
2
Offers and offer refusals : a postcolonial pragmatics perspective on world Englishes
Anchimbe, Eric A.. - Philadelphia : John Benjamins Publishing Company, 2018
BLLDB
UB Frankfurt Linguistik
Show details
3
Language and television series : a linguistic approach to TV dialogue
Bednarek, Monika. - Cambridge, United Kingdom : Cambridge University Press, 2018
BLLDB
UB Frankfurt Linguistik
Show details
4
Zur Stratifikation des FOLK-Korpus: Konzeption und Strategien
In: Gesprächsforschung. - Gleizendorf bei Nürnberg 19 (2018), 515-552
BLLDB
Show details
5
Dialog Acts Annotations for Online Chats ; Annotation en Actes de Dialogue pour les Conversations d’Assistance en Ligne
In: Actes TALN-RECITAL 2018 ; 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN) ; https://hal.archives-ouvertes.fr/hal-01943345 ; 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2018, Rennes, France (2018)
BASE
Show details
6
Usage-based Learning in Human Interaction with an Adpative Assistant Agent ; Apprentissage basé sur l’usage en interaction humaine avec un assistant adaptatif
Delgrange, Clément. - : HAL CCSD, 2018
In: https://tel.archives-ouvertes.fr/tel-02077000 ; Environnements Informatiques pour l'Apprentissage Humain. Université de Lyon, 2018. Français. ⟨NNT : 2018LYSE1290⟩ (2018)
BASE
Show details
7
Overlapping speech in Caryl Churchill's "Hot Fudge": constructing interactional and interpersonal contexts
In: International journal of literary linguistics. - Mainz, Germany : Johannes Gutenberg-Universität 7 (2018) 3, 1-25
BLLDB
UB Frankfurt Linguistik
Show details
8
Diachronie de l'oral représenté ; Diachronie de l'oral représenté: délimitation et segmentation interne du dialogue (IXe-XVe siècle)
In: Nouvelles voies d’accès au changement linguistique. Actes du colloque de la SIDF ; https://halshs.archives-ouvertes.fr/halshs-01313822 ; Wendy Ayres-Benett; Anne Carlier; Julie Glikman; Thomas Rainsford; Gilles Siouffi; Carine Skupien Dekens. Nouvelles voies d’accès au changement linguistique. Actes du colloque de la SIDF, Classiques Garnier, pp.279-296, 2018, Nouvelles voies d’accès au changement linguistique. Actes du colloque de la SIDF, ⟨10.15122/isbn.978-2-406-06946-1.p.0279⟩ ; http://diachronie.org/colloques/colloque-cambridge-2014 (2018)
BASE
Show details
9
The use of the adjective intensifier "well" in British English: a case study of "The Inbetweeners"
In: English studies. - Abingdon : Routledge, Taylor & Francis Group 99 (2018) 7-8, 793-816
BLLDB
Show details
10
Refusals in Early Modern English drama texts : new insights, new classification
In: Pragmatics. - Amsterdam : John Benjamins Publishing Company 28 (2018) 2, 253-270
BLLDB
Show details
11
Nouvelles voies d'accès au changement linguistique
Carlier, Anne (Herausgeber); Rainsford, Thomas M. (Herausgeber); Glikman, Julie (Herausgeber). - Paris : Classiques Garnier, 2018
BLLDB
UB Frankfurt Linguistik
Show details
12
Challenges of building an authentic emotional speech corpus of spontaneous Japanese dialog
Yoshiko Arimoto. - : Center for Corpus Development, National Institute for Japanese Language and Linguistics, 2018
BASE
Show details
13
A study on dialog act recognition using character-level tokenization
Ribeiro, E.; Ribeiro, R.; de Matos, D. M.. - : Springer, 2018
BASE
Show details
14
The Effect of Data Quantity on Dialog System Input Classification Models ; Datamängdens effekt på modeller för avsiktsklassificering i chattkonversationer
Lipecki, Johan; Lundén, Viggo. - : KTH, Hälsoinformatik och logistik, 2018
Abstract: This paper researches how different amounts of data affect different word vector models for classification of dialog system user input. A hypothesis is tested that there is a data threshold for dense vector models to reach the state-of-the-art performance that have been shown with recent research, and that character-level n-gram word-vector classifiers are especially suited for Swedish classifiers–because of compounding and the character-level n-gram model ability to vectorize out-of-vocabulary words. Also, a second hypothesis is put forward that models trained with single statements are more suitable for chat user input classification than models trained with full conversations. The results are not able to support neither of our hypotheses but show that sparse vector models perform very well on the binary classification tasks used. Further, the results show that 799,544 words of data is insufficient for training dense vector models but that training the models with full conversations is sufficient for single statement classification as the single-statement- trained models do not show any improvement in classifying single statements. ; Detta arbete undersöker hur olika datamängder påverkar olika slags ordvektormodeller för klassificering av indata till dialogsystem. Hypotesen att det finns ett tröskelvärde för träningsdatamängden där täta ordvektormodeller när den högsta moderna utvecklingsnivån samt att n-gram-ordvektor-klassificerare med bokstavs-noggrannhet lämpar sig särskilt väl för svenska klassificerare söks bevisas med stöd i att sammansättningar är särskilt produktiva i svenskan och att bokstavs-noggrannhet i modellerna gör att tidigare osedda ord kan klassificeras. Dessutom utvärderas hypotesen att klassificerare som tränas med enkla påståenden är bättre lämpade att klassificera indata i chattkonversationer än klassificerare som tränats med hela chattkonversationer. Resultaten stödjer ingendera hypotes utan visar istället att glesa vektormodeller presterar väldigt väl i de genomförda klassificeringstesterna. Utöver detta visar resultaten att datamängden 799 544 ord inte räcker till för att träna täta ordvektormodeller väl men att konversationer räcker gott och väl för att träna modeller för klassificering av frågor och påståenden i chattkonversationer, detta eftersom de modeller som tränats med användarindata, påstående för påstående, snarare än hela chattkonversationer, inte resulterar i bättre klassificerare för chattpåståenden.
Keyword: Chatbot; Chattbot; Chatterbot; Dialog System; Dialogsystem; Language Technology (Computational Linguistics); Natural Language Understanding; Naturlig språkbehandling; Ordinbäddning; Ordvektormodeller; Språkteknologi (språkvetenskaplig databehandling); Text Classification; Textklassificering; Virtual Assistant; Virtuell Assistent; Word Embedding; Word Vector Models
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-237282
BASE
Hide details
15
Диалог в устном академическом дискурсе ... : DIALOG IN ORAL ACADEMIC DISCOURSE ...
BASE
Show details
16
Interactive technologies in teaching a foreign language at higher educational establishment
In: International Letters of Social and Humanistic Sciences ; 71 ; 54-59 (2018)
BASE
Show details
17
Multimodal continuous turn-taking prediction using multiscale RNNs ; ICMI 2018 - 20th ACM International Conference on Multimodal Interaction
Harte, Naomi. - 2018
BASE
Show details
18
On-Talk and Off-Talk Detection: A Discrete Wavelet Transform Analysis of Electroencephalogram ; 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)
BASE
Show details
19
Chats and Chunks: Annotation and Analysis of Multiparty Long Casual Conversations ; Eleventh International Conference on Language Resources and Evaluation (LREC 2018)
BASE
Show details
20
Just Talking -- Modelling Casual Conversation ; 19th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Vogel, Carl. - 2018
BASE
Show details

Page: 1 2

Catalogues
5
0
0
0
0
0
0
Bibliographies
8
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
19
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern