Experiments | Cosine Similarity . |
Experiments | Given a question q and its :andidate answer 3, their cosine similarity can be :omputed as follows: |
Experiments | Method P@1(%) MRR (%) Nearest Answer 21.25 38.72 Cosine Similarity 23.15 43.50 HowNet 22.55 41.63 KL divergence 25 .30 51.40 DBN (without FT) 41.45 59.64 DBN (with FT) 45.00 62.03 |
Introduction | Because of this situation, the traditional relevance computing methods based on word co-occurrence, such as Cosine similarity and KL—divergence, are not effective for question- |
Abstract | Focus, coherence and referential clarity are best evaluated by a class of features measuring local coherence on the basis of cosine similarity between sentences, coreference information, and summarization specific features. |
Indicators of linguistic quality | Cosine similarity We use cosine similarity to compute the overlap of words in adjacent sentences s,- and 3H1 as a measure of continuity. |
Indicators of linguistic quality | We compute the min, max, and average value of cosine similarity over the entire summary. |
Indicators of linguistic quality | Cosine similarity is thus indicative of both continuity and redundancy. |
Results and discussion | For all four other questions, the best feature set is Continuity, which is a combination of summarization specific features, coreference features and cosine similarity of adjacent sentences. |
Results and discussion | We now investigate to what extent each of its components—summary-specific features, coreference, and cosine similarity between adjacent sentences—contribute to performance. |
Extractive Caption Generation | Cosine Similarity Word overlap is admittedly a naive measure of similarity, based on lexical identity. |
Results | We compare four extractive models based on word overlap, cosine similarity , and two probabilistic similarity measures, namely KL and JS divergence and two abstractive models based on words (see equation (8)) and phrases (see equation (15)). |
Results | As can be seen the probabilistic models (KL and J S divergence) outperform word overlap and cosine similarity (all differences are statistically significant, p < 0.01).6 They make use of the same topic model as the image annotation model, and are thus able to select sentences that cover common content. |
Impact on Survey Generation | LexRank is a multidocument summarization system, which first builds a cosine similarity graph of all the candidate sentences. |
Proposed Method | To formalize this assumption we use the sigmoid of the cosine similarity of two sentences to build it. |
Proposed Method | Intuitively, if a sentence has higher similarity with the reference paper, it should have a higher potential of being in class 1 or C. The flag of each sentence here is a value between 0 and l and is determined by its cosine similarity to the reference. |
Experiment: Ranking Word Senses | The WordNet senses are then ranked according to the cosine similarity between their sense vector and the contextually constrained target verb vector. |
Experiments: Ranking Paraphrases | Therefore the choice of which word is contextualized does not strongly influence their cosine similarity , and contextualizing both should not add any useful information. |
Experiments: Ranking Paraphrases | we compute [[swapOBmeadfl and compare it to the lifted first-order vectors of all paraphrase candidates, LOBJ([hint]) and LOBJ([star]), using cosine similarity . |
Discussion | An alternative to structural distance measures would be distance measures between the genres based on pairwise cosine similarities between them. |
Discussion | To assess this, we aggregated all character 4-gram training vectors of each genre and calculated standard cosine similarities . |
Discussion | Inspecting the distance matrix visually, we determined that the cosine similarity could clearly distinguish between Fiction and NonFiction texts but not between any other genres. |