<div dir="ltr">This change to lfr.tdl looked promising (`svn diff -r22903:25380 lfr.tdl`):<div><br></div><div><div> proper_ne+name_lfr := lexical_filtering_rule &</div><div> [ +CONTEXT < [ SYNSEM [ PHON.ONSET con_or_voc,</div><div>- LOCAL [ CAT.HEAD noun,</div><div>+ LOCAL [ CAT [ HEAD noun,</div><div>+<span class="gmail-m_8532522051751971272gmail-Apple-tab-span" style="white-space:pre-wrap"> </span> VAL.COMPS *olist* ],</div><div> CONJ cnil ],</div><div>- LKEYS.KEYREL.PRED abstr_named_rel ] ] >,</div><div>+ LKEYS.KEYREL.PRED abstr_named_rel ],</div><div>+ ORTH.LD #ld ] >,</div><div> +INPUT < [ SYNSEM [ PHON.ONSET unk_onset,</div><div>- LKEYS.KEYREL.PRED named_rel ] ] >,</div><div>+ LKEYS.KEYREL.PRED named_rel ],</div><div>+ ORTH.LD #ld ] >,</div><div> +OUTPUT < >,</div><div> +POSITION "I1@C1" ].</div></div><div><br></div><div>But just reverting this change was not enough:</div><div><br></div><div><div>$ echo "Ubuntu is dropping Unity." | ace -g erg.dat -Tq1 2>/dev/null | ace -g erg.dat -e 2>/dev/null</div><div>Unity, _generic_proper_ne_ is dropping.</div><div>_generic_proper_ne_ is dropping unity.</div></div><div><br></div><div>Are there any other relevant files/types regarding generic named entities and generation?</div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Mar 10, 2017 at 4:54 PM, Francis Bond <span dir="ltr"><<a href="mailto:bond@ieee.org" target="_blank">bond@ieee.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">G'day,<div><br></div><div>we have found what looks like a regression in the newest ERG.</div><div><br></div><div>For my tried and trusty ERG (trunk: Revision: 22903) I can parse and the generate an unknown name:</div><div><br></div><div>echo "Kuririnrinrin!" | ace -g /home/bond/svn/erg/erg.dat -Tf | ace -e -g /home/bond/svn/erg/erg.dat<br></div><div><div>NOTE: 1 readings, added 78 / 4 edges to chart (4 fully instantiated, 3 actives used, 2 passives used)<span class="m_2279375582622889023gmail-Apple-tab-span" style="white-space:pre-wrap"> </span>RAM: 285k</div><div>NOTE: parsed 1 / 1 sentences, avg 285k, time 0.00556s</div><div>Kuririnrinrin.</div><div>NOTE: 15 passive, 163 active edges in final generation chart; built 15 passives total. [1 results]</div><div>NOTE: generated 1 / 1 sentences, avg 432k, time 0.00410s</div></div><div><br></div><div>For a newer ERG (Revision: 25380), I just get "_generic_proper_ne_":</div><div><br></div><div><div>echo "Kuririnrinrin!" | ace -g ~/grammars/erg/erg-2017-03-10.<wbr>dat -T | ace -g ~/grammars/erg/erg-2017-03-10.<wbr>dat -e</div><div>NOTE: 1 readings, added 79 / 4 edges to chart (5 fully instantiated, 2 actives used, 2 passives used)<span class="m_2279375582622889023gmail-Apple-tab-span" style="white-space:pre-wrap"> </span>RAM: 213k</div><div>NOTE: parsed 1 / 1 sentences, avg 213k, time 0.00320s</div><div>_generic_proper_ne_.</div><div>NOTE: 16 passive, 168 active edges in final generation chart; built 16 passives total. [3 results]<br></div><div>NOTE: generated 1 / 1 sentences, avg 491k, time 0.00555s</div></div><div><br></div><div>ace is the same version in both cases (0.9.24).</div><div><br clear="all"><div>Any idea how to regain the old behavior?</div><span class="HOEnZb"><font color="#888888"><div><br></div>-- <br><div class="m_2279375582622889023gmail_signature">Francis Bond <<a href="http://www3.ntu.edu.sg/home/fcbond/" target="_blank">http://www3.ntu.edu.sg/home/<wbr>fcbond/</a>><br>Division of Linguistics and Multilingual Studies<br>Nanyang Technological University<br></div> </font></span></div></div> </blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr">Michael Wayne Goodman<div>Ph.D. Candidate, UW Linguistics</div></div></div> </div>