ACE-2004 defines 7 coarse-grained entity types , each of which are then refined into 43 fine-

grained entity types .

Using the ACE data annotated with mentions and predefined entity types, we build a fine-grained mention entity typing (MET) classifier to disambiguate between 44 labels (43 fine-grained and a null label to indicate not a mention).

We describe our mention entity typing system in Section 4 and features for the RE system in Section 5.

These mention candidates are then fed to our mention entity typing (MET) classifier for type prediction (more details in Section 6.3).

Abbreviations: Lm: predicted entity label for mention m using the mention entity typing (MET) classifier described in Section 4; PM ET: prediction probability according to the MET classifier; 75: used for thresholding.

In (Roth and Yih, 2007), the authors used entity types to constrain the (first dimensional) relation types allowed among them.

Due to space limitations, we refer the reader to our prior work (Chan and Roth, 2010) for the lexical, structural, mention-level, entity type , and dependency features.

Table 2: Features used in our mention entity typing (MET) system.

and whether they satisfy certain semantic entity type constraints.

For the overall performance, we use the average Precision, Recall and F1, where the weight of each name entity type is proportional to the number of entities of that type.

Tables 2-5 report the results on each entity type, indicating that our method consistently yields better results on all entity types .

Following the common practice , we adopt a sequential labeling approach to jointly resolve these subtasks, i.e., for each word in the input tweet, a label is assigned to it, indicating both the boundary and entity type .