Charley Beller

Adding Semantics to Data-Driven Paraphrasing

We add an interpretable semantics to the paraphrase database (PPDB). To date, the relationship between phrase pairs in the database has been weakly defined as approximately equivalent. We show that these pairs represent a variety of relations, including directed entailment (little girl/girl) and exclusion (nobody/someone). We automatically assign semantic entailment relations to entries in PPDB using features derived from past work on discovering inference rules from text and semantic taxonomy induction. We demonstrate that our model assigns these relations with high accuracy. In a downstream RTE task, our labels rival relations from WordNet and improve the coverage of a proof-based RTE system by 17%.

A Comparison of the Events and Relations Across ACE, ERE, TAC-KBP, and FrameNet Annotation Standards

The resurgence of effort within computational semantics has led to increased interest in various types of relation extraction and semantic parsing. While various manually annotated resources exist for enabling this work, these materials have been developed with different standards and goals in mind. In an effort to develop better general understanding across these resources, we provide a summary overview of the standards underlying ACE, ERE, TAC-KBP Slot-filling, and FrameNet. 1 Overview ACE and ERE are comprehensive annotation standards that aim to consistently annotate Entities, Events, and Relations within a variety of documents. The ACE (Automatic Content Extraction) standard was developed by NIST in 1999 and has evolved over time to support different evaluation cycles, the last evaluation having occurred in 2008. The ERE (Entities, Relations, Events) standard was created under the DARPA DEFT program as a lighter-weight version of ACE with the goal of making annotation easier, and more consistent across annotators. ERE attempts to achieve this goal by consolidating some of the annotation type distinctions that were found to be the most problematic in ACE, as well as removing some more complex annotation features. This paper provides an overview of the relationship between these two standards and compares them to the more restricted standard of the TACKBP slot-filling task and the more expansive standard of FrameNet. Sections 3 and 4 examine Relations and Events in the ACE/ERE standards, section 5 looks at TAC-KBP slot-filling, and section 6 compares FrameNet to the other standards.

I’m a Belieber: Social Roles via Self-identification and Conceptual Attributes

Motivated by work predicting coarsegrained author categories in social media, such as gender or political preference, we explore whether Twitter contains information to support the prediction of finegrained categories, or social roles. We find that the simple self-identification pattern “I am a ” supports significantly richer classification than previously explored, successfully retrieving a variety of fine-grained roles. For a given role (e.g., writer), we can further identify characteristic attributes using a simple possessive construction (e.g., writer’s ). Tweets that incorporate the attribute terms in first person possessives (my ) are confirmed to be an indicator that the author holds the associated social role.

Predicting Fine-grained Social Roles with Selectional Preferences

Selectional preferences, the tendencies of predicates to select for certain semantic classes of arguments, have been successfully applied to a number of tasks in computational linguistics including word sense disambiguation, semantic role labeling, relation extraction, and textual inference. Here we leverage the information encoded in selectional preferences to the task of predicting fine-grained categories of authors on the social media platform Twitter. First person uses of verbs that select for a given social role as subject (e.g. I teach ... for teacher) are used to quickly build up binary classifiers for that role.