#### Filter Results:

#### Publication Year

1999

2016

#### Co-author

#### Key Phrase

#### Publication Venue

#### Data Set Used

Learn More

Universal schema builds a knowledge base (KB) of entities and relations by jointly embedding all relation types from input KBs as well as textual patterns observed in raw text. In most previous applications of universal schema, each textual pattern is represented as a single embedding, preventing generalization to unseen patterns. Recent work employs a… (More)

Accurately segmenting a citation string into fields for authors, titles, etc. is a challenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft constraints , where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation performance. On the other… (More)

We introduce structured prediction energy networks (SPENs), a flexible framework for structured prediction. A deep architecture is used to define an energy function of candidate labels, and then predictions are produced by using back-propagation to iteratively optimize the energy with respect to the labels. This deep architecture captures dependencies… (More)

Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words' local context, a natural way to induce context-dependent representations is to perform inference in a probabilistic latent-variable sequence model. Given the recent success of continuous vector space word… (More)

- Sameer Singh, Limin Yao, David Belanger, Ari Kobren, Sam Anzaroot, Mike Wick +5 others
- TAC
- 2013

We employ universal schema for slot filling and cold start. In universal schema, we allow each surface pattern from raw text, and each type defined in ontology, i.e. TACKBP slots to represent relations. And we use matrix factorization to discover implications among surface patterns and target slots. First, we identify mentions of entities from the whole… (More)

Linear chains and trees are basic building blocks in many applications of graphi-cal models, and they admit simple exact maximum a-posteriori (MAP) inference algorithms based on message passing. However, in many cases this computation is prohibitively expensive, due to quadratic dependence on variables' domain sizes. The standard algorithms are inefficient… (More)

Dual decomposition provides the opportunity to build complex, yet tractable, structured prediction models using linear constraints to link together submodels that have available MAP inference routines. However, since some constraints might not hold on every single example, such models can often be improved by relaxing the requirement that these constraints… (More)