From 1b2bbe20d620e2284e1ce561632c69c8fe5d7435 Mon Sep 17 00:00:00 2001 From: David Hamann Date: Sun, 24 Sep 2017 18:54:16 +0200 Subject: [PATCH] added part-of-speech-tag to word --- proto/stable/rst/dialog/SpeechHypothesis.proto | 72 ++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) diff --git a/proto/stable/rst/dialog/SpeechHypothesis.proto b/proto/stable/rst/dialog/SpeechHypothesis.proto index 087b6ae..fa4cc8c 100644 --- a/proto/stable/rst/dialog/SpeechHypothesis.proto +++ b/proto/stable/rst/dialog/SpeechHypothesis.proto @@ -32,6 +32,78 @@ message SpeechHypothesis { */ optional timing.Interval timestamps = 2; + /** + * Container for part of speech tags as defined by the NEGRA-corpus. + * See here. + * Differences to the NEGRA-corpus are ("$," to "KOMM"), ("$." to "END") and ("$(" to "IPNCT"). + */ + enum PosTag { + ADJA = 1; + ADJD = 2; + ADV = 3; + APPR = 4; + APPRART = 5; + APPO = 6; + APZR = 7; + ART = 8; + CARD = 9; + FM = 10; + ITJ = 11; + ORD = 12; + KOUI = 13; + KOUS = 14; + KON = 15; + KOKOM = 16; + NN = 17; + NE = 18; + PDS = 19; + PDAT = 20; + PIS = 21; + PIAT = 22; + PIDAT = 23; + PPER = 24; + PPOSS = 25; + PPOSAT = 26; + PRELS = 27; + PRELAT = 28; + PRF = 29; + PWS = 30; + PWAT = 31; + PWAV = 32; + PAV = 33; + PTKZU = 34; + PTKNEG = 35; + PTKVZ = 36; + PTKANT = 37; + PTKA = 38; + SGML = 39; + SPELL = 40; + TRUNC = 41; + VVFIN = 42; + VVIMP = 43; + VVINF = 44; + VVIZU = 45; + VVPP = 46; + VAFIN = 47; + VAIMP = 48; + VAINF = 49; + VAPP = 50; + VMFIN = 51; + VMINF = 52; + VMPP = 53; + XY = 54; + KOMM = 55; + END = 56; + IPNCT = 57; + } + + /** + * Part of speech tag for this word. + * See here + * for more information. + */ + optional PosTag part_of_speech_tag = 3; + } /** -- 2.7.4