Index of papers in Proc. ACL 2014 that mention

**cosine similarity**

Approach | This is a commonly used setup in the CQA community (Wang et al., 2009).4 Thus, for a given question, all its answers are fetched from the answer collection, and an initial ranking is constructed based on the cosine similarity between theirs and the question’s lemma vector representations, with lemmas weighted using tfidf (Ch. |

Approach | The candidate answers are scored using a linear interpolation of two cosine similarity scores: one between the entire parent document and question (to model global context), and a second between the answer candidate and question (for local context).6 Because the number of answer candidates is typically large (e.g., equal to the number of paragraphs in the textbook), we return the N top candidates with the highest scores. |

Experiments | The following hyper parameters were tuned using grid search to maximize P@1 on each development partition: (a) the segment matching thresholds that determine the minimum cosine similarity between an answer segment and a question for the segment to be labeled QSEG; and (b) |

Models and Features | 6We empirically observed that this combination of scores performs better than using solely the cosine similarity between the answer and question. |

Models and Features | If text before or after a marker out to a given sentence range matches the entire text of the question (with a cosine similarity score larger than a threshold), that argument takes on the label QSEG, or OTHER otherwise. |

Models and Features | The values of the discourse features are the mean of the similarity scores (e. g., cosine similarity using tfidf weighting) of the two marker arguments and the corresponding question. |

Related Work | (2011) extracted 47 cue phrases such as because from a small collection of web documents, and used the cosine similarity between an answer candidate and a bag of words containing these cue phrases as a single feature in their reranking model for non-factoid why QA. |

cosine similarity is mentioned in 12 sentences in this paper.

Topics mentioned in this paper:

- reranking (24)
- cosine similarity (12)
- lexical semantic (12)

Evaluation | To illustrate how the model described above can learn geographically-informed semantic representations of words, table 1 displays the terms with the highest cosine similarity to wicked in Kansas and Massachusetts after running our joint model on the full 1.1 billion words of Twitter data; while wicked in Kansas is close to other evaluative terms like evil and pure and religious terms like gods and spirit, in Massachusetts it is most similar to other intensifiers like super, ridiculously and insanely. |

Evaluation | Table 2 likewise presents the terms with the highest cosine similarity to city in both California and New York; while the terms most evoked by city in California include regional locations like Chinatown, Los Angeles’ South Bay and San Francisco’s East Bay, in New York the most similar terms include hamptons, upstate and borough |

Evaluation | Table 1: Terms with the highest cosine similarity to wicked in Kansas and Massachusetts. |

cosine similarity is mentioned in 6 sentences in this paper.

Topics mentioned in this paper:

- cosine similarity (6)
- joint model (6)
- embeddings (4)

Document Retrieval with Hashing | Given a query document vector q, we use the Cosine similarity measure to evaluate the similarity between q and a document a: in a dataset: |

Document Retrieval with Hashing | However, such a brute-force search does not scale to massive datasets since the search time complexity for each query is 0(n); additionally, the computational cost spent on Cosine similarity calculation is also nontrivial. |

Document Retrieval with Hashing | (1) It tries to preserve the Cosine similarity of the original data with a probabilistic guarantee (Charikar, 2002). |

Experiments | We first evaluate the quality of term vectors and ITQ binary codes by conducting the whole list Cosine similarity ranking and hamming distance ranking, respectively. |

Experiments | For each query document, the top-K candidate documents with highest Cosine similarity scores and shortest hamming distances are returned, then we calculate the average precision for each K. Fig. |

Introduction | for example, one can store 250 million documents with 1.9G memory using only 64 bits for each document while a large news corpus such as the English Gigaword fifth edition1 stores 10 million documents in a 26G hard drive; 2) the time efficiency of manipulating binary codes, for example, computing the hamming distance between a pair of binary codes is several orders of magnitude faster than computing the real-valued cosine similarity over a pair of document vectors. |

cosine similarity is mentioned in 6 sentences in this paper.

Topics mentioned in this paper:

- reranking (11)
- Cosine similarity (6)
- similarity measures (4)

CoSimRank | This is similar to cosine similarity except that the l-norm is used instead of the 2-norm. |

Extensions | We are not including this method in our experiments, but we will give the equation here, as traditional document similarity measures (e.g., cosine similarity ) perform poorly on this task although there also are known alternatives with good results (Sahami and Heilman, 2006). |

Extensions | To calculate PPR+cos, we computed 20 iterations with a decay factor of 0.8 and used the cosine similarity with the 2-norm in the denominator to compare two vectors. |

Extensions | We compute 20 iterations of PPR+cos to reach convergence and then calculate a single cosine similarity . |

Related Work | Another important similarity measure is cosine similarity of Personalized PageRank (PPR) vectors. |

Related Work | These approaches use at least one of cosine similarity , PageRank and SimRank. |

cosine similarity is mentioned in 6 sentences in this paper.

Topics mentioned in this paper:

- similarity measure (20)
- PageRank (13)
- cosine similarity (6)

Solution Graph | cos: The cosine similarity between the named entity textual mention and the KB entry title. |

Solution Graph | ijim: While the cosine similarity between a textual mention in the document and the candidate |

Solution Graph | The cosine similarity between “Essex” and “Danbury, Essex” is higher than that between “Essex” and “Essex County Cricket Club”, which is not helpful in the NED setting. |

cosine similarity is mentioned in 4 sentences in this paper.

Topics mentioned in this paper:

- named entity (7)
- confidence score (6)
- edge weights (5)

Experimental Setup | 1) Cosine- 1 st: we rank the utterances in the chat log based on the cosine similarity between the utterance and query. |

Experimental Setup | 2) Cosine-all: we rank the utterances in the chat log based on the cosine similarity between the utterance and query and then select the utterances with a cosine similarity greater than 0; |

Experimental Setup | Query Relevance: another interesting observation is that relying only on the cosine similarity (i.e., cosine-all) to measure the query relevance presents a quite strong baseline. |

Phrasal Query Abstraction Framework | We use the K-mean clustering algorithm by cosine similarity as a distance function between sentence vectors composed of tfidf scores. |

cosine similarity is mentioned in 4 sentences in this paper.

Topics mentioned in this paper:

- I’m (8)
- manual evaluation (6)
- extractive system (5)

Discussion | One of the most effective similarity measures is the cosine similarity , which is a normalized dot product. |

Discussion | Indeed, taking Hp as above, and cosine similarity as the only feature (i.e., w E R), yields the distribution |

Our Proposal: A Latent LC Approach | These measures give complementary perspectives on the similarity between the predicates, as the cosine similarity is symmetric between the LHS and RHS predicates, while BInc takes into account the directionality of the inference relation. |

cosine similarity is mentioned in 3 sentences in this paper.

Topics mentioned in this paper:

- feature set (25)
- distributional representation (11)
- POS tag (8)

Models for Measuring Grammatical Competence | The similarity between a test response and a score-specific vector is then calculated by a cosine similarity metric. |

Models for Measuring Grammatical Competence | Although a total of 4 cosine similarity scores (one per score group) were generated, only 0034from among the four similarity scores, and cosmazc, |

Models for Measuring Grammatical Competence | 0 0034: the cosine similarity score between the test response and the vector of POS bigrams for the highest score class (level 4); and, |

cosine similarity is mentioned in 3 sentences in this paper.

Topics mentioned in this paper:

- bigrams (22)
- MaxEnt (15)
- language acquisition (9)

Machine Learning with Edit-Turn-Pairs | We used the cosine similarity , longest common subsequence, and word n- gram similarity measures. |

Machine Learning with Edit-Turn-Pairs | Cosine similarity was applied on binary weighted term vectors (L2 norm). |

Machine Learning with Edit-Turn-Pairs | Cosine similarity , longest common subsequence, and word n-gram similarity were also applied to measure the similarity between the edit comment and the turn text as well as the similarity between the edit comment and the turn topic name. |

cosine similarity is mentioned in 3 sentences in this paper.

Topics mentioned in this paper:

- manually annotated (4)
- turkers (4)
- Cosine similarity (3)