| Experiments and Results | The MaXEnt classifiers are also from the Stanford toolkit, and both the document and year mention classifiers use its default settings (quadratic prior). |
| Experiments and Results | MaXEnt Unigram is our new discriminative model for this task. |
| Experiments and Results | MaXEnt Time is the discriminative model with rich time features (but not NER) as described in Section 3.3.2 (Time+NER includes NER). |
| Learning Time Constraints | Figure 2: Distribution over years for a single document as output by a MaxEnt classifier. |
| Learning Time Constraints | We train a MaxEnt model on each year mention, to be described next. |
| Learning Time Constraints | We use a MaxEnt classifier trained on the individual year mentions. |
| Timestamp Classifiers | We used a MaxEnt model and evaluated with the same filtering methods based |
| Timestamp Classifiers | Ultimately, this MaxEnt model vastly outperforms these NLLR models. |
| Timestamp Classifiers | The above language modeling and MaxEnt approaches are token-based classifiers that one could apply to any topic classification domain. |
| MultiLayer Context Model - MCM | and predicted dialog act by arg maxa 13(a|ud*): |
| MultiLayer Context Model - MCM | * N M311 a; = arg maXa [6351 a * HF”, M1: ] (6) |
| MultiLayer Context Model - MCM | For each segment wuj in u, its predicted slot are determined by arg maXS P(sj|wuj,d*,sj_1): |