Findings of the VarDial Evaluation Campaign 2017
Citations
281 citations
113 citations
Cites background or methods from "Findings of the VarDial Evaluation ..."
...Last year, in the second edition of the ADI task (Zampieri et al., 2017), we offered the input represented as (i) automatic text transcriptions generated using large-vocabulary speech recognition (LVCSR), and (ii) acoustic features....
[...]
...For training and development, we released the same data as for last year’s VarDial evaluation campaign (Zampieri et al., 2017)....
[...]
...The second iteration of the ADI task (Zampieri et al., 2017) introduced multi-modality for dialect identification, using i-vectors for the acoustic representation in addition to lexical features....
[...]
...This year’s second edition of the VarDial Evaluation Campaign was preceded by the first edition of the campaign in 2017 with four shared tasks (Zampieri et al., 2017)....
[...]
...The previous GDI task was part of the first VarDial evaluation campaign (Zampieri et al., 2017)....
[...]
107 citations
Cites background from "Findings of the VarDial Evaluation ..."
...For instance, several evaluation campaigns were dedicated to discriminating between language varieties (Malmasi et al., 2016; Zampieri et al., 2017)....
[...]
...More recently, discriminating between Arabic Dialects has been the goal of a dedicated shared task (Zampieri et al., 2017; Malmasi et al., 2016), encouraging researchers to submit systems to recognize the dialect of speech transcripts along with acoustic features for dialects of four main regions: Egyptian, Gulf, Levantine and North African, in addition to MSA....
[...]
...Character n-grams Character n-grams have shown to be the most effective in language and dialect identification tasks (Zampieri et al., 2017)....
[...]
...More recently, discriminating between Arabic Dialects has been the goal of a dedicated shared task (Zampieri et al., 2017; Malmasi et al., 2016), encouraging researchers to submit systems to recognize the dialect of speech transcripts along with acoustic features for dialects of four main regions:…...
[...]
98 citations
Cites background from "Findings of the VarDial Evaluation ..."
...More recently, discriminating between Arabic dialects has been the goal of a dedicated shared task (Zampieri et al., 2017), encouraging researchers to submit systems to recognize the dialect of speech transcripts along with acoustic features for dialects of four main regions: Egyptian, Gulf, Levantine and North African, in addition to MSA....
[...]
...More recently, discriminating between Arabic dialects has been the goal of a dedicated shared task (Zampieri et al., 2017), encouraging researchers to submit systems to recognize the dialect of speech transcripts along with acoustic features for dialects of four main regions: Egyptian, Gulf,…...
[...]
94 citations
Cites background from "Findings of the VarDial Evaluation ..."
...4In (Salameh et al., 2018), the Corpus 6 test set corresponds to the 2,000 sentences from Corpus 26 corresponding to the Corpus 6’s five cities and MSA....
[...]
...The participants were provided with a dataset from the MADAR corpus (Bouamor et al., 2018), a largescale collection of parallel sentences in the travel domain covering the dialects of 25 cities from the Arab World in addition to MSA (Table 1 shows the list of cities)....
[...]
...Dialect Identification The goal of this subtask is to classify written Arabic sentences into one of 26 labels representing the specific city dialect of the sentences, or MSA....
[...]
...An example of a 27-way parallel sentence (25 cities plus MSA and English) extracted from Corpus 26 is given in Table 2....
[...]
...We refer to it as Corpus 6 (5 cities plus MSA)....
[...]
References
[...]
2,459 citations
1,559 citations
"Findings of the VarDial Evaluation ..." refers methods in this paper
...For the constrained setup, we also provided parallel datasets coming from OPUS (Tiedemann, 2012) that could be used for training cross-lingual parsers in any way....
[...]
1,111 citations
"Findings of the VarDial Evaluation ..." refers methods in this paper
...ing language pairs from the Universal Dependencies (UD) project (Nivre et al., 2016) that match the setup and come close to a realistic case for the approach (using UD release 1....
[...]
...We do so by simulating the resource-poor situation by selecting language pairs from the Universal Dependencies (UD) project (Nivre et al., 2016) that match the setup and come close to a realistic case for the approach (using UD release 1.4)....
[...]
489 citations
"Findings of the VarDial Evaluation ..." refers methods in this paper
...…Transfer learning and annotation projection are popular approaches in this field and various techniques and models have been proposed in the literature in particular in connection with dependency parsing (Hwa et al., 2005; McDonald et al., 2013; Täckström et al., 2012; Tiedemann, 2014)....
[...]
384 citations
"Findings of the VarDial Evaluation ..." refers methods in this paper
...7 Transfer learning and annotation projection are popular approaches in this field and various techniques and models have been proposed in the literature in particular in connection with dependency parsing (Hwa et al., 2005; McDonald et al., 2013; Täckström et al., 2012; Tiedemann, 2014)....
[...]
...…Transfer learning and annotation projection are popular approaches in this field and various techniques and models have been proposed in the literature in particular in connection with dependency parsing (Hwa et al., 2005; McDonald et al., 2013; Täckström et al., 2012; Tiedemann, 2014)....
[...]