Introduction | Word embedding is used as the input to learn translation confidence score , which is combined with commonly used features in the conventional log-linear model. |
Our Model | yum] is the confidence score of how plausible the parent node should be created. |
Our Model | The recurrent input vector film] is concatenated with parent node representation sum] to compute the confidence score yum] . |
Phrase Pair Embedding | The one-hot representation vector is used as the input, and a one-hidden-layer network generates a confidence score . |
Phrase Pair Embedding | To train the neural network, we add the confidence scores to the conventional log-linear model as features. |
Phrase Pair Embedding | We use recurrent neural network to generate two smoothed translation confidence scores based on source and target word embeddings. |
Related Work | RNNLM (Mikolov et al., 2010) is firstly used to generate the source and target word embeddings, which are fed into a one-hidden-layer neural network to get a translation confidence score . |
Related Work | Together with other commonly used features, the translation confidence score is integrated into a conventional log-linear model. |
Related Work | Given the representations of the smaller phrase pairs, recursive auto-encoder can generate the representation of the parent phrase pair with a reordering confidence score . |
Concept-based Representation for Medical Records Retrieval | In particular, MetaMap (Aronson, 2001) can take a text string as the input, segment it into phrases, and then map each phrase to multiple UMLS CUIs with confidence scores . |
Concept-based Representation for Medical Records Retrieval | The confidence score is an indicator of the quality of the phrase-to-concept mapping by MetaMap. |
Concept-based Representation for Medical Records Retrieval | confidence score as well as more detailed information about this concept. |
Experiments | As shown in Equation (3), the Balanced method regularizes the weights through two components: (1) normalized confidence score of each aspect, |
Weighting Strategies for Concept-based Representation | Although MetaMap is able to rank all the candidate concepts with the confidence score and pick the most likely one, the accuracy is not very high. |
Weighting Strategies for Concept-based Representation | i(e) is the normalized confidence score of the mapping for concept 6 generated by MetaMap. |
Weighting Strategies for Concept-based Representation | Since each concept mapping is associated with a confidence score , we can incorporate them into the regularization function as follows: |
Experiments | The preliminary relation extractor of our optimization framework is not limited to the MaxEnt extractor, and can take any sentence level relation extractor with confidence scores . |
Experiments | Furthermore, the confidence scores which MultiR outputs are not normalized to the same scale, which brings us difficulties in setting up a confidence threshold to select the candidates. |
The Framework | We first train a preliminary sentence level extractor which can output confidence scores for its predictions, e.g., a maximum entropy or logistic regression model, and use this local extractor to produce local predictions. |
The Framework | Now the confidence score of a relation 7“ E R75 being assigned to tuple t can be calculated as: |
The Framework | The first component is the sum of the original confidence scores of all the selected candidates, and the second one is the sum of the maximal mention-level confidence scores of all the selected candidates. |
Abstract | Each node has an initial confidence score , e.g. |
Solution Graph | Each candidate has associated with it an initial confidence score , also detailed below. |
Solution Graph | Initial confidence scores of all candidates for a single NE mention are normalized to sum to l. |
Solution Graph | One is a setup where a ranking based solely on different initial confidence scores is used |
Conclusion & Future Work | Finally, we observe a negative correlation between the classifier confidence scores and a SAC, as expected. |
Discussion | In other words, the goal is to show that the confidence scores of a sentiment classifier are negatively correlated with SAC. |
Discussion | The confidence score of a classifier8 for given text t is computed as follows: |
Discussion | Table 3 presents the accuracy of the classifiers along with the correlations between the confidence score and observed SAC values. |
Experiments | The new KB covers all super relations and stores the knowledge in the format of (rela-tionJiame, argument_l, argumentl, confidence), where the confidence is computed based on the relation detector confidence score and relation popularity in the corpus. |
Experiments | If we detect multiple relations in the question, and the same answer is generated from more than one relations, we sum up all those confidence scores to make such answers more preferable. |
Experiments | In this scenario, we sort the answers based upon the confidence scores and only consider up to p answers for each question. |
Introduction | Confidence scores from an ASR system (which incorporate N-gram probabilities) are optimized in order to produce the most likely sequence of words rather than the accuracy of individual word detections. |
Term Detection Re-scoring | For each term t and document d we propose interpolating the ASR confidence score for a particular detection td with the top scoring hit in d which we’ll call £1. |
Term Detection Re-scoring | However to verify that this approach is worth pursuing, we sweep a range of small 04 values, on the assumption that we still do want to mostly rely on the ASR confidence score for term detection. |