Cosine Similarity .

Given a question q and its :andidate answer 3, their cosine similarity can be :omputed as follows:

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

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-

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.

Cosine similarity We use cosine similarity to compute the overlap of words in adjacent sentences s,- and 3H1 as a measure of continuity.

We compute the min, max, and average value of cosine similarity over the entire summary.

Cosine similarity is thus indicative of both continuity and redundancy.

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.

We now investigate to what extent each of its components—summary-specific features, coreference, and cosine similarity between adjacent sentences—contribute to performance.

Cosine Similarity Word overlap is admittedly a naive measure of similarity, based on lexical identity.

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)).

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.

LexRank is a multidocument summarization system, which first builds a cosine similarity graph of all the candidate sentences.

To formalize this assumption we use the sigmoid of the cosine similarity of two sentences to build it.

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.

The WordNet senses are then ranked according to the cosine similarity between their sense vector and the contextually constrained target verb vector.

Therefore the choice of which word is contextualized does not strongly influence their cosine similarity , and contextualizing both should not add any useful information.

we compute [[swapOBmeadfl and compare it to the lifted first-order vectors of all paraphrase candidates, LOBJ([hint]) and LOBJ([star]), using cosine similarity .

An alternative to structural distance measures would be distance measures between the genres based on pairwise cosine similarities between them.

To assess this, we aggregated all character 4-gram training vectors of each genre and calculated standard cosine similarities .

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.