4.2.4. Semantic paraphrase resolution
Paraphrase resolution is also known as Synonym Resolution, Deduplication, Entity Resolution [70]. It is related to OIE and can concern relations [71–73], entities or both [70]. In adequacy with our interest for work near Big Data features, [70,71] pro- pose unsupervised and scalable approaches for paraphrase resolution. In [70], to scale, the number of comparisons be- tween pairs of strings (which must share a or pair) is limited and strings are clus- tered over time. This idea of gradual merging of clusters is also the reason of the scalability in [71]. Unlike these two pre- vious, [72] tackle polysemy and use extra-characteristics of the input relation instances like distributional similarity, lin- guistic patterns, hypernym graph, etc. Let us note that if [70] tackle the problem of finding which mentions of entities in a text are equivalent, some authors address a similar problem called Entity Linking and which can be helpful in our disam- biguation task. It aims to identify an entry in a given Knowl- edge Base (KB) to which an entity mention in a document refers to [74,75].