Recruiting comparative crosslinguistic evidence to address competing accounts of agrammatic aphasia

Several hypotheses have been advanced whose aim has been to provide a descriptive generalization of comprehension patterns in agrammatic aphasia in terms of current linguistic theory, most notably, the Trace-Deletion Hypothesis. The basic insight of these syntactic accounts of aphasia is that chains are disrupted. In this paper, we seek to confront the Trace-Deletion Hypothesis (TDH) and one of its variants, the Double-Dependency Hypothesis (DDH), with discriminating, crosslinguistic data. We adduce evidence that on raising constructions both hypotheses are able to derive Spanish agrammatic data correctly. However, neither the TDH nor the DDH are able to account for above-chance performance on SV or VS truncated passives. Finally, only the DDH explains the observed data on passive constructions in which a postverbal subject follows the by phrase (V-by phrase-S). The VS word order data are the critical cases because focusing simply on English would not allow these structures to be tested and, in the case of the V-by phrase-S passive, both hypotheses make different predictions. While the data on raising constructions extend the range of both the TDH and the DDH, the VS data suggest that modifications are required. (C) 1999 Academic Press.