@inProceedings{
 title = {A corpus of European Portuguese child and child-directed speech},
 type = {inProceedings},
 year = {2014},
 keywords = {acquisition,child corpus,part-of-speech-tagging},
 city = {Reykjavik},
 id = {18e85f60-9cbb-3651-83d5-a3a50d0bfafa},
 created = {2015-09-07T15:33:14.000Z},
 file_attached = {true},
 profile_id = {99b1950b-b6a6-3be8-bf35-12f6a6311a38},
 group_id = {336b6408-ac60-3ac5-acc3-f17c991bd54f},
 last_modified = {2015-09-23T10:56:35.000Z},
 tags = {LT},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Santos2014a},
 country = {Iceland},
 user_context = {article},
 abstract = {We present a corpus of child and child-directed speech of European Portuguese. This corpus results from the expansion of an already existing database (Santos, 2006). It includes around 52 hours of child-adult interaction and now contains 27,595 child utterances and 70,736 adult utterances. The corpus was transcribed according to the CHILDES system (Child Language Data Exchange System) and using the CLAN software (MacWhinney, 2000). The corpus itself represents a valuable resource for the study of lexical, syntax and discourse acquisition. In this paper, we also show how we used an existing part-of-speech tagger trained on written material (Généreux, Hendrickx & Mendes, 2012) to automatically lemmatize and tag child and child-directed speech and generate a line with part-of-speech information compatible with the CLAN interface. We show that a POS-tagger trained on the analysis of written language can be exploited for the treatment of spoken material with minimal effort, with only a small number of written rules assisting the statistical model.},
 bibtype = {inProceedings},
 author = {Santos, Ana Lúcia and Généreux, Michel and Cardoso, Aida and Agostinho, Celina and Abalada, Silvana},
 booktitle = {Proceedings of the 9h International Conference on Language Resources and Evaluation (LREC 14), 26-31 May 2014, Reykjavik, Iceland}
}

{"_id":"zXTqQtqxRzz4CNJ3A","bibbaseid":"santos-gnreux-cardoso-agostinho-abalada-acorpusofeuropeanportuguesechildandchilddirectedspeech-2014","downloads":0,"creationDate":"2015-09-10T07:59:26.206Z","title":"A corpus of European Portuguese child and child-directed speech","author_short":["Santos, A., L.","Généreux, M.","Cardoso, A.","Agostinho, C.","Abalada, S."],"year":2014,"bibtype":"inProceedings","biburl":null,"bibdata":{"title":"A corpus of European Portuguese child and child-directed speech","type":"inProceedings","year":"2014","keywords":"acquisition,child corpus,part-of-speech-tagging","city":"Reykjavik","id":"18e85f60-9cbb-3651-83d5-a3a50d0bfafa","created":"2015-09-07T15:33:14.000Z","file_attached":"true","profile_id":"99b1950b-b6a6-3be8-bf35-12f6a6311a38","group_id":"336b6408-ac60-3ac5-acc3-f17c991bd54f","last_modified":"2015-09-23T10:56:35.000Z","tags":"LT","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Santos2014a","country":"Iceland","user_context":"article","abstract":"We present a corpus of child and child-directed speech of European Portuguese. This corpus results from the expansion of an already existing database (Santos, 2006). It includes around 52 hours of child-adult interaction and now contains 27,595 child utterances and 70,736 adult utterances. The corpus was transcribed according to the CHILDES system (Child Language Data Exchange System) and using the CLAN software (MacWhinney, 2000). The corpus itself represents a valuable resource for the study of lexical, syntax and discourse acquisition. In this paper, we also show how we used an existing part-of-speech tagger trained on written material (Généreux, Hendrickx & Mendes, 2012) to automatically lemmatize and tag child and child-directed speech and generate a line with part-of-speech information compatible with the CLAN interface. We show that a POS-tagger trained on the analysis of written language can be exploited for the treatment of spoken material with minimal effort, with only a small number of written rules assisting the statistical model.","bibtype":"inProceedings","author":"Santos, Ana Lúcia and Généreux, Michel and Cardoso, Aida and Agostinho, Celina and Abalada, Silvana","booktitle":"Proceedings of the 9h International Conference on Language Resources and Evaluation (LREC 14), 26-31 May 2014, Reykjavik, Iceland","bibtex":"@inProceedings{\n title = {A corpus of European Portuguese child and child-directed speech},\n type = {inProceedings},\n year = {2014},\n keywords = {acquisition,child corpus,part-of-speech-tagging},\n city = {Reykjavik},\n id = {18e85f60-9cbb-3651-83d5-a3a50d0bfafa},\n created = {2015-09-07T15:33:14.000Z},\n file_attached = {true},\n profile_id = {99b1950b-b6a6-3be8-bf35-12f6a6311a38},\n group_id = {336b6408-ac60-3ac5-acc3-f17c991bd54f},\n last_modified = {2015-09-23T10:56:35.000Z},\n tags = {LT},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Santos2014a},\n country = {Iceland},\n user_context = {article},\n abstract = {We present a corpus of child and child-directed speech of European Portuguese. This corpus results from the expansion of an already existing database (Santos, 2006). It includes around 52 hours of child-adult interaction and now contains 27,595 child utterances and 70,736 adult utterances. The corpus was transcribed according to the CHILDES system (Child Language Data Exchange System) and using the CLAN software (MacWhinney, 2000). The corpus itself represents a valuable resource for the study of lexical, syntax and discourse acquisition. In this paper, we also show how we used an existing part-of-speech tagger trained on written material (Généreux, Hendrickx & Mendes, 2012) to automatically lemmatize and tag child and child-directed speech and generate a line with part-of-speech information compatible with the CLAN interface. We show that a POS-tagger trained on the analysis of written language can be exploited for the treatment of spoken material with minimal effort, with only a small number of written rules assisting the statistical model.},\n bibtype = {inProceedings},\n author = {Santos, Ana Lúcia and Généreux, Michel and Cardoso, Aida and Agostinho, Celina and Abalada, Silvana},\n booktitle = {Proceedings of the 9h International Conference on Language Resources and Evaluation (LREC 14), 26-31 May 2014, Reykjavik, Iceland}\n}","author_short":["Santos, A., L.","Généreux, M.","Cardoso, A.","Agostinho, C.","Abalada, S."],"urls":{"Paper":"http://bibbase.org/service/mendeley/3cb37113-7d68-36c6-858d-c0468cbaaaf8/file/204f9d98-d7fb-4e79-450d-8c0a3d60062c/2014-A_corpus_of_European_Portuguese_child_and_child-directed_speech.pdf.pdf"},"bibbaseid":"santos-gnreux-cardoso-agostinho-abalada-acorpusofeuropeanportuguesechildandchilddirectedspeech-2014","role":"author","keyword":["acquisition","child corpus","part-of-speech-tagging"],"downloads":0},"search_terms":["corpus","european","portuguese","child","child","directed","speech","santos","généreux","cardoso","agostinho","abalada"],"keywords":["acquisition","child corpus","part-of-speech-tagging"],"authorIDs":[]}