We present ConceptResolver, a component for the N ever-Ending Language Learner (NELL) (Carlson et al., 2010) that handles both phenomena by identifying the latent concepts that noun phrases refer to.

When ConceptResolver is run on N ELL’s knowledge base, 87% of the word senses it creates correspond to real-world concepts, and 85% of noun phrases that it suggests refer to the same concept are indeed synonyms.

A major limitation of many of these systems is that they fail to distinguish between noun phrases and the underlying concepts they refer to.

Furthermore, two synonymous noun phrases like “apple” and “Apple

Figure 1: An example mapping from noun phrases (left) to a set of underlying concepts (right).

In this paper, we first regard all noun phrases , including the target, as extended targets for simplicity.

In addition to the noun phrases including the target, we further expand the extended target set with the following three methods:

It is common that people use definite or demonstrative noun phrases or pronouns referring to the target in a tweet and express sentiments directly on them.

As a result, many structures that in other treebanks would be prepositional phrases with embedded noun phrases — and thus nonlocal constituents — are flat prepositional phrases here.

The task for these models is chunking, so we evaluate performance on identification of multiword chunks of all constituent types as well as only noun phrases .

We also evaluate our models based on their performance at identifying base noun phrases , NPs that do not contain nested NPs.