J97-3002 needed . Previous approaches to phrasal matching employ arbitrary heuristic functions
P12-2024 proach , however , still rely on phrasal matching techniques that disregard relevant
W13-2117 al. , 2011 ) which consists of phrasal matching at the level on ngrams ( 1 to
N13-1018 al. , 2011 ) which consists of phrasal matching at the level on ngrams ( 1 to
S12-1105 decisions are assigned combining phrasal matching scores calculated for each level
J97-3002 constituent structure . Manual phrasal matching is feasible only for small corpora
W12-3122 Mehdad et al. , 2011 ) , with a phrasal matching algorithm that takes advantage
P11-1134 matched at each level ( n ) . The phrasal matching score for each n-gram level is
P11-1134 decisions are estimated by combining phrasal matching scores ( Score , , , ) calculated
P11-1134 of 3.2 words per phrase . 3.2 Phrasal Matching Method In order to maximize the
P11-1134 inference . We experiment with a phrasal matching method in order to : i ) build
P11-1134 : Mn coren = Nn To combine the phrasal matching scores obtained at each n-gram
D13-1008 Levenshtein distance ) . We also perform phrasal matchings , such as ikwn to i know . To
W11-0144 domain-specific canned lexical or phrasal matching ( Buf3 et al. , 2010 ) . Our
W97-1311 morphological analysis , performs phrasal matching against lists of proper names
C96-1071 hological ana - lysis , Imrtbrms phrasal matching against lists of proper names
C04-1155 subtrees it dominated . In many phrasal matching ap - proaches , such as constituency-oriented
J97-3002 constraints are implicit in many phrasal matching approaches , both constituency-oriented
W99-0211 the raw input text , performs phrasal matching against lists of proper names
hide detail