regex - Regular expression for recognizing in-text citations -

i'm trying create regular expression capture in-text citations.

here's few example sentences of in-text citations:

1. ... , reported results in (nivre et al., 2007) not representative ...

2. ... 2 systems used markov chain approach (sagae , tsujii 2007).

3. nivre (2007) showed ...

4. ... attaching , labeling dependencies (chen et al., 2007; dredze et al., 2007).

currently, regular expression have

\(\d*\d\d\d\d\) 

which matches examples 1-3, not example 4. how can modify capture example 4?

thanks!

i’ve been using purpose lately:

#!/usr/bin/env perl  use 5.010; use utf8; use strict; use autodie; use warnings qw< fatal >; use open qw< :std io :utf8 >;  $citation_rx = qr{     \( (?:         \s*          # optional author list         (?:              # has start capitalized             \p{uppercase_letter}                      # have lower case letter, or maybe apostrophe             (?=  [\p{lowercase_letter}\p{quotation_mark}] )              # before run of letters , admissible punctuation             [\p{alphabetic}\p{dash_punctuation}\p{quotation_mark}\s,.] +          ) ?  # hook if , if want authors optional!!          # reasonable year         \b (18|19|20) \d\d           # citation series suffix, six-parter         [a-f] ?         \b                           # trailing semicolon separate multiple citations         ; ?           \s*     ) +     \) }x;  while (<data>) {     while (/$citation_rx/gp) {         ${^match};     }  }   __end__ ... , reported results in (nivré et al., 2007) not representative ... ... 2 systems used markov chain approach (sagae , tsujii 2007). nivre (2007) showed ... ... attaching , labelling dependencies (chen et al., 2007; dredze et al., 2007). 

when run, produces:

(nivré et al., 2007) (sagae , tsujii 2007) (2007) (chen et al., 2007; dredze et al., 2007)