Neural Belief Tracker: Data-Driven Dialogue State Tracking
Citations
796 citations
623 citations
583 citations
Cites methods from "Neural Belief Tracker: Data-Driven ..."
...Most models use a structured approach [Mrkšić et al., 2016], with the most recent work making use of both global and local modules to learns representations of the user utterance and previous system actions [Zhong et al., 2018]....
[...]
...Most models use a structured approach (Mrkšić et al., 2016), with the most recent work making use of both global and local modules to learns representations of the user utterance and previous system actions (Zhong et al....
[...]
415 citations
410 citations
Cites background from "Neural Belief Tracker: Data-Driven ..."
...The corpus was later extended to additional two languages for cross-lingual research (Mrkšić et al., 2017b)....
[...]
...…framework and machine learning for various system components, such as natural language understanding (Henderson et al., 2013; Mesnil et al., 2015; Mrkšić et al., 2017a), dialogue management (Gašić and Young, 2014; Tegho et al., 2018), language generation (Wen et al., 2015; Kiddon et al.,…...
[...]
...These difficulties have led to the same solution of using statistical framework and machine learning for various system components, such as natural language understanding (Henderson et al., 2013; Mesnil et al., 2015; Mrkšić et al., 2017a), dialogue management (Gašić and Young, 2014; Tegho et al....
[...]
References
111,197 citations
"Neural Belief Tracker: Data-Driven ..." refers methods in this paper
...To train the models, we use the Adam optimizer (Kingma and Ba, 2015) with crossentropy loss, backpropagating through all the NBT subcomponents while keeping the pre-trained word vectors fixed (in order to allow the model to deal...
[...]
33,597 citations
"Neural Belief Tracker: Data-Driven ..." refers methods in this paper
...Dropout (Srivastava et al., 2014) was used for regularisation (with 50% dropout rate on all intermediate representations)....
[...]
30,558 citations
"Neural Belief Tracker: Data-Driven ..." refers methods in this paper
...Using GloVe vectors (Pennington et al., 2014) in place of Paragram-SL999 (Wieting et al., 2015) drastically reduced the models’ goal tracking capabilities....
[...]
...Table 2 shows the performance of NBT-CNN5 models making use of three different word vector collections: 1) ‘random’ word vectors initialised using the XAVIER initialisation (Glorot and Bengio, 2010); 2) distributional GloVe vectors (Pennington et al., 2014), trained using co-occurrence information in large textual corpora; and 3) semantically specialised ParagramSL999 vectors (Wieting et al....
[...]
30,124 citations
"Neural Belief Tracker: Data-Driven ..." refers methods in this paper
...Figure 4 shows the t-SNE visualisation (van der Maaten and Hinton, 2008) of the user utterance representations produced by the NBT-DNN model with tied parameters....
[...]
14,799 citations
"Neural Belief Tracker: Data-Driven ..." refers methods in this paper
...We obtain summary n-gram representations by pushing these representations through a rectified linear unit (ReLU) activation function (Nair and Hinton, 2010) and max-pooling over time (i....
[...]