Abstract | 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. |
Abstract | 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. |
Introduction | A major limitation of many of these systems is that they fail to distinguish between noun phrases and the underlying concepts they refer to. |
Introduction | Furthermore, two synonymous noun phrases like “apple” and “Apple |
Introduction | Figure 1: An example mapping from noun phrases (left) to a set of underlying concepts (right). |
Target-dependent Sentiment Classification | In this paper, we first regard all noun phrases , including the target, as extended targets for simplicity. |
Target-dependent Sentiment Classification | In addition to the noun phrases including the target, we further expand the extended target set with the following three methods: |
Target-dependent Sentiment Classification | 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. |
CD | 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. |
Introduction | 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 . |
Tasks and Benchmark | We also evaluate our models based on their performance at identifying base noun phrases , NPs that do not contain nested NPs. |