Abstract | We present BRAINSUP, an extensible framework for the generation of creative sentences in which users are able to force several words to appear in the sentences and to control the generation process across several semantic dimensions, namely emotions, colors, domain relatedness and phonetic properties. |
Architecture of BRAINSUP | More formally, the user input is a tuple: U = (t,d, c, e,p,w> , where t is the set of target words, (1 is a set of words defining the target domain, 0 and p are, respectively, the color and the emotion towards which the user wants to slant the sentence, p represents the desired phonetic features, and w is a set of weights that control the influence of each dimension on the generative process , as detailed in Section 3.3. |
Architecture of BRAINSUP | The sentence generation process is based on morpho-syntactic patterns which we automatically discover from a corpus of dependency parsed sentences ’P. |
Architecture of BRAINSUP | Algorithm 1 provides a high-level description of the creative sentence generation process . |
Evaluation | We did so to simulate the brainstorming phase behind the slogan generation process , where copywriters start with a set of relevant keywords to come up with a catchy slogan. |
Evaluation | Nonetheless, it is very encouraging to observe that the generation process does not deteriorate the positive impact of the input keywords. |
Model | This observation motivates the generative process of our model. |
Model | Referring to the notations in Table 1, we explain the generative process of JTE-P. |
Model | We now detail the generative process of J TE-P (plate notation in Figure l) as follows: |
Phrase Ranking based on Relevance | This thread of research models bigrams by encoding them into the generative process . |
Related Work | The generative process of ASMs is, however, different from our model. |
Introduction | We model our problem as a joint dependency parsing and role labeling task, assuming a Bayesian generative process . |
Model | Modeling the Generative Process . |
Model | The generative process is described formally as follows: |
Related Work | While previous approaches rely on the feedback to train a discriminative prediction model, our approach models a generative process to guide structure predictions when the feedback is noisy or unavailable. |
Discussion | Using a more realistic generative process for the underlying forms, for example an Adaptor Grammar (Johnson et al., 2007), could address this shortcoming in future work without changing the overall architecture of the model although novel inference algorithms might be required. |
The computational model | This generative process is repeated for each utterance 2', leading to multiple utterances of the form Um, . |
The computational model | The generative process mimics the intuitively plausible idea of generating underlying forms from some kind of syntactic model (here, a Bigram language model) and then mapping the underlying form to an observed surface-form through the application of a phonological rule component, here represented by the collection of rule probabilities pc. |
Model | The generative process of the model follows that of ITG with the following simple grammar |
Model | The generative process is that we draw a complete ITG tree, 75 N P2 as follows: |
Model | depending on 7“ This generative process is mutually recursive: P2 makes draws from P1 and P1 makes draws from P2. |
Experiments | Decoding under our model would be straightforward in principle, as the generative process was designed to closely parallel the search procedure in the phrase-based model.3 Three data sets were used in the experiments: two Chinese to English data sets on small (IWSLT) and larger corpora (FBIS), and Arabic |
Model | The generative process employs the following recursive procedure to construct the target sentence conditioned on the source: |
Model | This generative process resembles the sequence of translation decisions considered by a standard MT decoder (Koehn et al., 2003), but note that our approach differs in that there is no constraint that all words are translated exactly once. |
Decipherment Model for Machine Translation | So, instead we use a simplified generative process for the translation model as proposed by Ravi and Knight (2011b) and used by others (Nuhn et al., 2012) for this task: |
Decipherment Model for Machine Translation | We now extend the generative process (described earlier) to more complex translation models. |
Decipherment Model for Machine Translation | Nonlocal Reordering: The generative process described earlier limits reordering to local or adjacent word pairs in a source sentence. |