<div dir="ltr">Thanks, Tuan!</div><br><div class="gmail_quote"><div dir="ltr">On Tue, Aug 1, 2017 at 4:53 PM Tuấn Anh Lê <<a href="mailto:tuananh.ke@gmail.com">tuananh.ke@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div>Hi Olga,<br><br></div>There is a way to achieve that by selecting a different root (passing -r [rootname] to ace). You can see a list of different roots in the file roots.tdl. For example:<br><br><span style="font-family:monospace,monospace"><b>echo "a big dog" | ace -g erg.dat -1Tf</b><br>SENT: a big dog<br>[ LTOP: h0<br>INDEX: e2 [ e SF: prop-or-ques ]<br>RELS: < [ unknown_rel<0:9> LBL: h1 ARG0: e2 ARG: x4 [ x PERS: 3 NUM: sg IND: + ] ]<br> [ _a_q_rel<0:1> LBL: h5 ARG0: x4 RSTR: h6 BODY: h7 ]<br> [ "_big_a_1_rel"<2:5> LBL: h8 ARG0: e9 [ e SF: prop TENSE: untensed MOOD: indicative PROG: bool PERF: - ] ARG1: x4 ]<br> [ "_dog_n_1_rel"<6:9> LBL: h8 ARG0: x4 ] ><br>HCONS: < h0 qeq h1 h6 qeq h8 ><br>ICONS: < > ]<br>NOTE: 1 readings, added 611 / 61 edges to chart (26 fully instantiated, 34 actives used, 19 passives used) RAM: 1120k<br><br><br>NOTE: parsed 1 / 1 sentences, avg 1120k, time 0.00606s<br><br><b>echo "a big dog" | ace -g erg.dat -1Tf <span style="color:rgb(255,0,0)">-r root_spoken_frag</span></b><br>SENT: a big dog<br>[ LTOP: h0<br>INDEX: e2 [ e SF: prop-or-ques ]<br>RELS: < [ unknown_rel<0:9> LBL: h1 ARG0: e2 ARG: x4 [ x PERS: 3 NUM: sg IND: + ] ]<br> [ _a_q_rel<0:1> LBL: h5 ARG0: x4 RSTR: h6 BODY: h7 ]<br> [ "_big_a_1_rel"<2:5> LBL: h8 ARG0: e9 [ e SF: prop TENSE: untensed MOOD: indicative PROG: bool PERF: - ] ARG1: x4 ]<br> [ "_dog_n_1_rel"<6:9> LBL: h8 ARG0: x4 ] ><br>HCONS: < h0 qeq h1 h6 qeq h8 ><br>ICONS: < > ]<br>NOTE: 1 readings, added 611 / 61 edges to chart (26 fully instantiated, 34 actives used, 19 passives used) RAM: 1120k<br><br><br>NOTE: parsed 1 / 1 sentences, avg 1120k, time 0.00567s<br><br><b>echo "a big dog" | ace -g erg.dat -1Tf <span style="color:rgb(255,0,0)">-r root_informal</span></b><br>NOTE: 0 readings, added 611 / 61 edges to chart (26 fully instantiated, 34 actives used, 19 passives used) RAM: 1093k<br>SKIP: a big dog<br><br><br>NOTE: parsed 0 / 1 sentences, avg 1093k, time 0.00576s</span><br><br></div>Hope this helps :)<br><div><br></div></div><div class="gmail_extra"></div><div class="gmail_extra"><br><div class="gmail_quote">On 2 August 2017 at 06:01, Olga Zamaraeva <span dir="ltr"><<a href="mailto:olzama@uw.edu" target="_blank">olzama@uw.edu</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">It appears that by default, fragments are on when I am parsing with ACE + ERG. Is there a way to disable that? I would like to only use fragments when there are no non-fragments results.<div><br></div><div>I see in the config file for ERG: "fragment-only rules" but that does not seems to be the flag I am looking for?</div><div><br></div><div>Thanks!</div><span class="m_-2598620150278225697HOEnZb"><font color="#888888"><div>Olga</div></font></span></div>
</blockquote></div><br><br clear="all"><br></div><div class="gmail_extra">-- <br><div class="m_-2598620150278225697gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><span style="font-size:small">Yours,</span><br style="font-size:small"><span style="font-size:small">-- </span><br style="font-size:small"><div style="font-size:small"><div dir="ltr">Tuan Anh Le</div></div></div></div></div></div>
</div></blockquote></div>