Relative clauses are used to provide information about an entity introduced by a noun (phrase) in the matrix clause, the antecedent. They are obligatorily introduced by (a phrase containing) a relative element coreferential with that antecedent, and contain a trace indicating the original position of the relative element. The overall structure of relative clauses is thus as indicated in (82); cf. De Vries (2002: appendix III) for an overview of different syntactic analyses of relative clauses.

For example, the relative pronoun dat in the examples in (81), repeated here as (83), is coreferential with its antecedent boekbook, and the trace ti indicates the original position of the pronoun in the relative clause.

Relative clauses can be either restrictive or non-restrictive. Like other restrictive modifiers, restrictive relative clauses form an intonational unit with their antecedent, while reducing the referent set of the noun phrase by restricting the denotation of the noun. Given this, it is plausible to assume that restrictive relative clauses, like other restrictive modifiers, are part of the NP-domain: in (84) this is expressed by placing the relative clause within the NP square brackets and by coindexing the relative element with some projection of the head noun smaller than NP (which may contain other restrictive modifiers).

Non-restrictive relative clauses are separated from the noun by an intonation break, represented by commas in the examples in (85), and merely provide additional information about the referent set of the full noun phrase, which can be established independently of the relative clause. Given this, we assume that non-restrictive relative clauses are external to the NP, and that the relative element is coindexed with the NP; cf. Section 16.3.2.3.1 for details.

The abstract structure in (85) shows that we assume that the non-restrictive relative clause is still part of the DP-domain; the reasons for this are given in 16.1.2, sub II. Since many researchers have argued that, besides the NP and DP-projections, other intermediate projections can be distinguished within the noun phrase, such as NumP discussed in Section 14.1.2, sub IIA, it may be the case that the relative elements of non-restrictive relative clauses are coindexed with some higher projection between NP and DP. However, the main issue here is to indicate the scope of the two types of relative clauses: a non-restrictive relative clause provides additional information about the referent of the noun phrase, and since the reference of the noun phrase is determined by the determiner, the relative clause must have this determiner in its scope; a restrictive relative clause does not provide information about the referent of the noun phrase, but restricts the denotation of the noun, and it is therefore plausible that it is only the NP that falls within its scope.

Since this section is mainly concerned with the postmodification of nominal heads, the discussion will focus on relative constructions of the type in (84) and (85) above, and semi-free relatives such as (86a); free relative constructions such as (86b), in which there is no overt nominal antecedent, will not be discussed in detail, although some of its distinctive properties will be reviewed in Section 16.3.2.2.

It has been claimed that relative clauses need not be restrictive or non-restrictive in the sense discussed above but can also be used as amount/degree relatives to modify the determiner or (implicit) numeral/quantifier in the noun phrase; cf. De (hoeveelheidi) jenever diei hij drinkt, kan een olifant vellen The amount of jenever he drinks can destroy an elephant. We will not discuss such cases, as they have been discussed mainly for English, with a strong focus on the semantics of the construction; cf. Grosu and Landman (2017) for a detailed review.