| Abstract | We evaluate our method on a manually annotated data set, and show that our method outperforms the baseline that handles these two tasks separately, boosting the F1 from 80.2% to 83.6% for NER, and the Accuracy from 79.4% to 82.6% for NEN, respectively. |
| Conclusions and Future work | We evaluate our method on a manually annotated data set. |
| Experiments | We manually annotate a data set to evaluate our method. |
| Related Work | is trained on a manually annotated data set, which achieves an F1 of 81.48% on the test data set; Chiti-cariu et al. |
| Experimental Setup | We also manually annotated the relations expressed in the text, identifying 94 of the Candidate Relations as valid. |
| Experimental Setup | Evaluation Metrics We use our manual annotations to evaluate the type-level accuracy of relation extraction. |
| Experimental Setup | The first, Manual Text, is a variant of our model which directly uses the links derived from manual annotations of preconditions in text. |
| Evaluation | The experiments were performed on the manually annotated Korean test dataset. |
| Introduction | Several datasets that provide manual annotations of semantic relationships are available from MUC (Grishman and Sund-heim, 1996) and ACE (Doddington et al., 2004) projects, but these datasets contain labeled training examples in only a few major languages, including English, Chinese, and Arabic. |
| Introduction | Because manual annotation of semantic relations for such resource-poor languages is very expensive, we instead consider weakly supervised learning techniques (Riloff and Jones, 1999; Agichtein and Gravano, 2000; Zhang, 2004; Chen et al., 2006) to learn the relation extractors without significant annotation efforts. |
| Data and task | The approach uses a small amount of manually annotated article-pairs to train a document-level CRF model for parallel sentence extraction. |
| Data and task | Of these, we manually annotated 91 English-Bulgarian and 79 English-Korean sentence pairs with source and target named entities as well as word-alignment links among named entities in the two languages. |
| Data and task | At test time we use the local+global Wiki-based tagger to define the English entities and we don’t use the manually annotated alignments. |
| Introduction | However, the performance of these methods highly relies on manually annotated training data. |
| Introduction | However, these methods need to manually annotate a lot of training data in each domain. |
| Introduction | The sentiment and topic words are manually annotated . |