Introduction | The semantic similarity of words is a longstanding topic in computational linguistics because it is theoretically intriguing and has many applications in the field. |
Introduction | A number of semantic similarity measures have been proposed based on this hypothesis (Hindle, 1990; Grefenstette, 1994; Dagan et al., 1994; Dagan et al., 1995; Lin, 1998; Dagan et al., 1999). |
Introduction | In general, most semantic similarity measures have the following form: |
Conclusion | We showed that our system outperforms two baselines and sometimes approaches human-level performance, especially because it can exploit the sequential structure of the script descriptions to separate clusters of semantically similar events. |
Evaluation | with a weighted edge; the weight reflects the semantic similarity of the nodes’ event descriptions as described in Section 5.2. |
Evaluation | Levenshtein Baseline: This system follows the same steps as our system, but using Levenshtein distance as the measure of semantic similarity for MSA and for node merging (cf. |
Evaluation | The clustering system, which can’t exploit the sequential information from the ESDs, has trouble distinguishing semantically similar phrases (high recall, low precision). |
Introduction | Crucially, our algorithm exploits the sequential structure of the ESDs to distinguish event descriptions that occur at different points in the script storyline, even when they are semantically similar . |
Temporal Script Graphs | 5.2 Semantic similarity |
Temporal Script Graphs | Intuitively, we want the MSA to prefer the alignment of two phrases if they are semantically similar , i.e. |
Analysis and Discussion | Our aim in this paper is to characterize the semantic similarity of bilingual hierarchical rules. |
Experiments | The improved similarity function Alg2 makes it possible to incorporate monolingual semantic similarity on top of the bilingual semantic similarity , thus it may improve the accuracy of the similarity estimate. |
Introduction | The source and target sides of the rules with (*) at the end are not semantically equivalent; it seems likely that measuring the semantic similarity from their context between the source and target sides of rules might be helpful to machine translation. |
Related Work | Our work is different from all the above approaches in that we attempt to discriminate among hierarchical rules based on: 1) the degree of bilingual semantic similarity between source and target translation units; and 2) the monolingual semantic similarity between occurrences of source or target units as part of the given rule, and in general. |
Similarity Functions | A common way to calculate semantic similarity is by vector space cosine distance; we will also |
Similarity Functions | Therefore, on top of the degree of bilingual semantic similarity between a source and a target translation unit, we have also incorporated the monolingual semantic similarity between all occurrences of a source or target unit, and that unit’s occurrence as part of the given rule, into the sense similarity measure. |
Integrating Semantic Constraint into Surprisal | This can be achieved by turning a vector model of semantic similarity into a probabilistic language model. |
Models of Processing Difficulty | Semantic similarities are then modeled in terms of geometric similarities within the space. |
Models of Processing Difficulty | Despite its simplicity, the above semantic space (and variants thereof) has been used to successfully simulate lexical priming (e.g., McDonald 2000), human judgments of semantic similarity (Bullinaria and Levy 2007), and synonymy tests (Pado and Lapata 2007) such as those included in the Test of English as Foreign Language (TOEFL). |
Substructure Spaces for BTKs | In this section, we define seven lexical features to measure semantic similarity of a given subtree pair. |
Substructure Spaces for BTKs | baseline only assesses semantic similarity using the lexical features. |
Substructure Spaces for BTKs | In other words, to capture the semantic similarity , structure features requires lexical features to cooperate. |
Experimental Evaluation | semantic similarity , reply, and quotation. |
System Design | On the one hand, the semantic similarity between two nodes can be measured with any commonly adopted metric, such as cosine similarity and J accard coefficient (Baeza—Yates and Ribeiro-Neto, 1999). |
System Design | Considering the semantic similarity between nodes, we use another variant of the PageRank algorithm to calculate the weight of comment |