<?xml version="1.0" standalone="yes"?>
<Paper uid="P85-1020">
  <Title>MOVEMENT IN ACTIVE PRODUCTION NETWORKS</Title>
  <Section position="6" start_page="162" end_page="164" type="concl">
    <SectionTitle>
3. MOVI~W..NT
</SectionTitle>
    <Paragraph position="0"> From the APN perspective, movement (limited here to left-extrapnsition) necessitates the endogenous reactivation of a trace that was created earlier in the process. To cap..</Paragraph>
    <Paragraph position="1"> ture the trace so that expectations for its reactivation can be posted, we use the following type of rule: (seq (5 vl ...</Paragraph>
    <Paragraph position="2"> X... ) ($ v2 ... (and X X-see Y) ...). When an instance, XO, first activatea this rule, vl is bound to XO; the second occurrence X in the rule is constrained to match instances of XO, and expectations for XO, X-see and Y are created.</Paragraph>
    <Paragraph position="3"> No new exogenous source can satisfy the synchronous conjunction; only an endogenous X.src can. The rule is similar to the notion of an X followed by a Y with an X hole in it (cf. Gazdar, 1982).</Paragraph>
    <Paragraph position="5"> tive clause; other type, s of \[eft-extraposition are handled analogously. Our treatment of relatives is adapted from C'homsky and Lasnik (1977). The movement rule for S is: (seq ($ vl (and Cutup Re/ (or Exog.src PRO-src)) ($ v2 (and Rel Rel.src S))). The rule restricts the first instance of Re/ to arise either from an exogenous relative pronoun such as which or from an endogenously generated (phonologically null) pronoun PRO. The second variable is satisfied when Rei,src simultaneously reactivates a trace of the Rel instance and inserts an NP-tracc into an S.</Paragraph>
    <Paragraph position="6"> It is instructive to consider how phonologically null pronouns are inserted before we discuss how movement occurs by trace insertion. The phrase, \[NP the mouse \[~ PRO=&amp;quot; that ...\]\], illustrates how a relative pronoun PRO is inserted. Figure 5(a) shows the network after parsing the cat. When the complementizer that appears next in the input, PRO-src receives inhibition (marked by downward arrows in Figure 5(b)) from Rel.CompO. Non-exogenous  sources such as PRO-src and Rel.src are activated in contexts in which they are expected and then receive inhibition. Figure 5(c) shows the resulting network after PRO-src has been activated, The inserted pronoun behaves precisely as an input pronoun with respect to subsequent movement.</Paragraph>
    <Paragraph position="7"> The trace generation necessary for movement uses the same insertion mechanism described above. Figures 6(a)(d) illustrate various stages in parsing the phraso, \[/vp the cat \[~&amp;quot; whichi \[$ tl ranll\], in Figure 6(a), after parsing the cat which, synchronous expectations are posted for an S which contains a reactivation of the RelO trace by Rel.</Paragraph>
    <Paragraph position="8"> see. The signal sent to S by Rei.src will be in the form of an NP (through NP-trace).</Paragraph>
    <Paragraph position="9"> Figure 6(b) shows how the input of ran produces inhibition on Rei-src from SI. The inhibition on Rei-src caus~ it to activate (just as in the null pronoun insertion) to try to satisfy the current contextual expectations. Figure 6(c) shows the network after Rel-src has activated to supply the trace. The only remaining problem is that Rel-src is actively inhibiting itself through .~0. 6 When Rel-src activates again, new instances are created for the inhibited nodes as they are re-activated; the uninhibited nodes are simply rebound. The final structure is shown in Figure 6(d).</Paragraph>
    <Paragraph position="10"> it is interesting that the network automatically enforces the restriction that the relative pronoun, complementizer and subject of the embedded sentence cannot all be missing. PRO must be generated before its trace can be inserted as the subject. Furthermore. since expectations are strongest for the first link of a sequence, expectations will be much weaker for the VP in the relative clause (under S under S&amp;quot;) than for the top-level VP under SO. The fact that the device blocks certai'n structures, without explicit weli-formedness constraints, is quite significant. Wherever possible, we would like to account for the complexity of the data through the composite behavior of a universal device and a simple, general grammar. We consider the description of a device which embodies the appropriate principles more parsimonious than a list of complex conditions and filters, and, to the extent that its architecture is independently motivated by proc,'ssink (i.e.. performance) considerations, of greater thcorctical interestf As we have seen, certain interpretations can be suppressed by expectations from elsewhere in the network.</Paragraph>
    <Paragraph position="11"> Furthermore, the occurrence of traces and empty constituents is severely constrained because they must be supplied by endogenous sources, which can only suppurt a sintie constituent at any given time. For NP movement, these two properties of the device, taken together.</Paragraph>
    <Paragraph position="12"> elfectively enforce Ross's Complex NP Constraint (Ross.</Paragraph>
    <Paragraph position="13"> 1967), which states that, &amp;quot;No element contained in a 6. Another ,~sy o4&amp;quot; rut*inS thi,J iJ that the noa~ynchroetM:ity of the two vanaMea in the I~ttern hat ~ viohtted. The wdt-inhibittoa of * murcg ocgtwt in othcnr conteat~ in the APN ft'tnM:lmek eve* for egolgno~t toMt~eL Is net,aerita that contai* leJ't.rm;urtiv* cyr.t~ or ,endmSl~tm tttaghn~nta (e.S.. PP lUaghfl~'ltt), tett-iahibltioa Call Ifiu naturally U the t~ult at nemum~ me-de~rmiaim~ ae.tctivatioe of * ~\[-inhil~t~ mum d'egUvety Ixorgtva the aea-tyarJumigity ~ pmuwnt.</Paragraph>
    <Paragraph position="14"> ?. 1&amp;quot;I~ work 4 Margin (1980) iain tJ~tm~&amp;l~t.</Paragraph>
    <Paragraph position="15"> sentence dominated by an NP with a lexLcal head noun may be moved out of that NP by a transformation.&amp;quot; To see why this constraint is enforced, consider the two kinds of sentences that an NP with a lexical head noun might dominate. If the embedded sentence is a relative clause, as in. \[pip the rat \[~&amp;quot; whichl \[$ the cat \[~&amp;quot; whichj \[S fj chased/I\]\] likes fish\]J\], then Rel.src cannot support both traces. If the embedded sentence is a noun complement (not shown in Figure 4). as in. \[NP the rat \[~&amp;quot; whichi \[S he read a report \[~&amp;quot; that \[$ the cat chased fl\]\]\]\]\], then there is only one trace in the intended interpretation, but there is nondeterminlsm during parsing between the noun complement and the relative clause interpretation. The interference eausC/,, the trace to be bound to the innermost relative pronoun in the relative clause interpretation.' Thus, the combined properties of the device and grammar consistently block those structures which violate the Complex NP Constraint. Our preliminary findings for other types of movement (e.g., Subject-auxiliary Inversion, Wh-movement, and Raising) indicate that they also have natural APN explanations.</Paragraph>
    <Paragraph position="16"> 4. IMPLF.aMENTATION 8ml Fu'ruRg DIMF.CrlONS Although the re.torch described in this summary is primarily of a theoretic nature, the basic ideas involved in using APNs for recognition and generation are being implemented and tested in Zetalisp on a Symbolics Lisp Machine. We have also hand-simulated data on movement from the literature to design the theory and algorithms presented in this paper. We are currently designing networks for a broad coverage syntactic grammar of English and for additional, cascaded levels for NP role mapping and case frames. The model has aLso been adapted as a general, context-driven problem solver, although more work remains to be done.</Paragraph>
    <Paragraph position="17"> We are considering ways of integrating iterative relaxation techniques with the rule-based framework of APNs.</Paragraph>
    <Paragraph position="18"> This is particularly necessary in helping the network to identify expectation coalitions. In Figure 5(a), for exampie. there should be virtually no expectations for Rel-src, since it cannot satisfy any of the dominating synchronous conjunctions. Some type of non-activating feedback from the sources seems to be necessary.</Paragraph>
    <Paragraph position="19"> S. SUI~ARY Recent linguistic theories have attempted to induce general principles (e.g., CNPC. Subjacency, and the Structure Preserving Hypothesis) from the detailed structural descriptions of earlier transformational theories (Chomsky, 1981), Our research can be viewed as an attempt tu induce the machine that embodies theae principles. In this paper, we have described a class of candidate machine~, called active production networks, and outlined how they handle movement as a natural way in which machine and grammar interact.</Paragraph>
    <Paragraph position="20"> The APN framework was initially developed as a plausible cognitive model for language processing, which would have real-time processing behavior, and extensive 8. Uhle tO r~-.~,-~.--i C/oeskJs~ttmsJ wb~t rg~lto tO e.lp~t~om q~t~nfftb~ tJr*~ tm heud ia s ~.tr tlmt ~ nemmtg.  contextual processing and learning capabilities based on a formal notion of expectations. That movement also seems naturally expressible in a way that is consistent with current linguistic theories is quite intriguing.</Paragraph>
  </Section>
class="xml-element"></Paper>