Translations are induced using a generative model based on canonical correlation analysis, which explains the monolingual lexicons in terms of latent matchings.

We have presented a novel generative model for bilingual lexicon induction and presented results under a variety of data conditions (section 6.1) and languages (section 6.3) showing that our system can produce accurate lexicons even in highly adverse conditions.

2.1 Generative Model

We propose the following generative model over matchings m and word types (5,13), which we call matching canonical correlation analysis (MCCA).

We have presented a generative model for bilingual lexicon induction based on probabilistic CCA.

We define a generative model over (1) a source lexicon, (2) a target lexicon, and (3) a matching between them (section 2).

The training set is very small, and it is a known fact that generative models tend to work better for small datasets and discriminative models tend to work better for larger datasets (Ng and Jordan, 2002).

For both WSJ 15 and WSJ40, we trained a generative model ; a discriminative model, which used lexicon features, but no grammar features other than the rules themselves; and a feature-based model which had access to all features.

The discriminatively trained generative model (discriminative in Table 3) took approximately 12 minutes per pass through the data, while the feature-based model (feature-based in Table 3) took 35 minutes per pass through the data.

In Figure 3 we show for an example from section 22 the parse trees produced by our generative model and our feature-based discriminative model, and the correct parse.

Although they take much longer to train than generative models , they typically produce higher performing systems, in large part due to the ability to incorporate arbitrary, potentially overlapping features.

A generative model of mention generation is used to guide mention resolution.

Our principal contributions are the approaches we take to evidence generation (leveraging three ways of linking to other emails where evidence might be found: reply chains, social interaction, and topical similarity) and our approach to choosing among candidates (based on a generative model of reference production).

Similarly, approaches in unstructured data (e.g., text) have involved using clustering techniques over biographical facts (Mann and Yarowsky, 2003), within-document resolution (Blume, 2005), and dis-criminative unsupervised generative models (Li et al., 2005).

To address the issue, rather than resort to statistical generation models as in the previous literature (Cohn and Lapata, 2007; Galley and McKeown, 2007), we pursue a particular rule-based approach we call a ‘dependency truncation,’ which as we will see, gives us a greater control over the form that compression takes.

The paper presents a novel sentence trimmer in Japanese, which combines a non-statistical yet generic tree generation model and Conditional Random Fields (CRFs), to address improving the grammaticality of compression while retaining its relevance.

This paper introduced a novel approach to sentence compression in Japanese, which combines a syntactically motivated generation model and CRFs, in or-