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. |
Introduction | First, the model’s generative process encourages coherence in the local features and placement of relation instances. |
Model | This section describes the generative process , while Sections 4 and 5 discuss declarative constraints. |
Model | 3.2 Generative Process |
Model | There are three steps to the generative process . |
Model | Our model seeks to explain this observed data through a generative process whereby two aligned parse trees are produced jointly. |
Model | In the next two sections, we describe our model in more formal detail by specifying the parameters and generative process by which sentences are formed. |
Model | 3.4 Generative Process |
Model | Here, we describe the generative process our model uses to generate the observed utterances and present the corresponding graphical model. |
Model | For clarity, we assume that the values of the boundary variables bi are given in the generative process . |
Model | The generative process indicates that our model ignores utterance boundaries and views the entire data as concatenated spoken segments. |
Problem Formulation | In the next section, we show the generative process our model uses to generate the observed data. |
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. |
Constraints Shape Topics | In LDA, a document’s token is produced in the generative process by choosing a topic 2 and sampling a word from the multinomial distribution gbz of topic 2. |
Constraints Shape Topics | If that is an unconstrained word, the word is emitted and the generative process for that token is done. |
Constraints Shape Topics | Then the generative process for constrained LDA is: |
Putting Knowledge in Topic Models | introduce ambiguity over the path associated with an observed token in the generative process . |
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. |
Algorithm | The generative process of word distributions for non-emotion topics follows the standard LDA definition with a scalar hyperparameter 607’). |
Algorithm | We summarize the generative process of the EaLDA model as below: |
Algorithm | As an alternative representation, the graphical model of the the generative process is shown by Figure 1. |
Introduction | Although they have limited vocabulary and non-elaborate syntax, they nevertheless present challenges at almost all stages of the generation process . |
The Story Generator | the story generation process as a tree (see Figure 2) whose levels represent different story lengths. |
The Story Generator | So, at each choice point in the generation process , e. g., when selecting a verb for an entity or a frame for a verb, we consider the N best alternatives assuming that these are most likely to appear in a good story. |
Empirical Evaluation | The times reported are from the start of the generation process , eliminating variations due to interpreter startup, input parsing, etc. |
Empirical Evaluation | Note that, as STRUCT is an anytime algorithm, valid sentences are available very early in the generation process , despite the size of the set of adjoining trees. |
Sentence Tree Realization with UCT | If so, we store it, and continue the generation process . |
The IBPOT Model | The IBPOT model defines a generative process for mappings between input and output forms based on three latent variables: the constraint violation matrices F (faithfulness) and M (markedness), and the weight vector w. The cells of the violation matrices correspond to the number of violations of a constraint by a given input-output mapping. |
The IBPOT Model | Represented constraint sampling We begin by resampling M j; for all represented constraints M.l, conditioned on the rest of the violations (M_(jl), F) and the weights w. This is the sampling counterpart of drawing existing features in the IBP generative process . |
The IBPOT Model | This is the sampling counterpart to the Poisson draw for new features in the IBP generative process . |
Abstract | The generative process assumes that each entity mention arises from copying and optionally mutating an earlier name from a similar context. |
Introduction | Our model is an evolutionary generative process based on the name variation model of Andrews et al. |
Introduction | This can also relate seemingly dissimilar names via multiple steps in the generative process: |
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. |
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. |
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. |
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. |
Abstract | We cast the generation process as constraint optimization problems, collectively incorporating multiple interconnected aspects of language composition for content planning, surface realization and discourse structure. |
Introduction | Because the generation process sticks relatively closely to the recognized content, the resulting descriptions often lack the kind of coverage, creativity, and complexity typically found in human-written text. |
Introduction | Our ILP formulation encodes a rich set of linguistically motivated constraints and weights that incorporate multiple aspects of the generation process . |
Method | We assume the following generation process for all the posts in the stream. |
Method | Figure 2: The generation process for all posts. |
Method | Formally, the generation process is summarized in Figure 2. |
Abstract | We inject information extracted from unstructured web search query logs as prior information to enhance the generative process of the natural language utterance understanding model. |
Experiments | This is because we utilize domain priors obtained from the web sources as supervision during generative process as well as unlabeled utterances that enable handling language variability. |
MultiLayer Context Model - MCM | The generative process of our multilayer context model (MCM) (Fig. |
Enriched Two-Tiered Topic Model | Thus; we present enriched TTM (ETTM) generative process (Fig.3), which samples words not only from low-level topics but also from high-level topics as well. |
Enriched Two-Tiered Topic Model | Similar to TTM’s generative process , if wid is related to a given query, then cc 2 1 is deterministic, otherwise cc 6 {0,1} is stochastically determined if wid should be sampled as a background word (2123) or through hierarchical path, i.e., HT pairs. |
Topic Coherence for Summarization | We identify sentences as meta-variables of document clusters, which the generative process models both sentences and documents using tiered topics. |
Introduction | In Section 2 we introduce the probabilistic generative process and show in Sections 2.1 and 2.2 how we incorporate this process in PROMODES and PROMODES-H. We start our experiments with examining the learning behaviour of the algorithms in 31. |
Probabilistic generative model | abilistic generative process consisting of words as observed variables X and their hidden segmentation as latent variables Y. |
Related work | (2002), however, they were interested in finding paradigms as sets of mutual exclusive operations on a word form whereas we are describing a generative process using morpheme boundaries and resulting letter transitions. |
Model | There are four basic layers in the generative process: |
Model | Structural Sparsity The first step of the generative process provides a control on the sparsity of edit-operation probabilities, encoding the linguistic intuition that the correct character-level mappings should be sparse. |
Model | Character-edit Distribution The next step in the generative process is drawing a base distribution Go over character edit sequences (each of which yields a bilingual pair of morphemes). |