Nakagawa, S. 1987 Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of ContextFree Grammar'. Proc. ICASSP 87, Dallas (Texas), VoL 2: 829-832.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....bottom up, etc. I Int:roduction It is often necessary in practical situations to attempt parsing an incorrect o incomplete input. This may take many forms: e.g. missing or spurious words, misspelled or misunderstood or otherwise unkuown words [28] missing or unidentified word bound aries [22,27]. Specific techniques may be developed to deal with these situations according to the requirements of the application area (e.g. natural language processing, programtinting language parsing, rea . timc or off line processing) The comlext fi.ee (CF) parsing of a sentence with unknown words has ....

Nakagawa, S. 1987 Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of ContextFree Grammar'. Proc. ICASSP 87, Dallas (Texas), VoL 2: 829-832.

.... play a central role in integrating low level word models with higher level language models (Ney 1992) as well as in non finite state acoustic and phonotactic modeling (Lari Young 1991) In some work, context free grammars are combined with scoring functions that are not strictly probabilistic (Nakagawa 1987), or they are used with context sensitive and or semantic probabilities (Magerman Marcus 1991; Magerman Weir 1992; Jones Eisner 1992; Briscoe Carroll 1993) Although clearly not a perfect model of natural language, stochastic context free grammars (SCFGs) are superior to non probabilistic ....

....exact) solution to the computation of the various SCFG probabilities. 6.4 Other related work The literature on Earley based probabilistic parsers is sparse, presumably because of the precedent set by the Inside Outside algorithm, which is more naturally formulated as a bottom up algorithm. Both Nakagawa (1987) and Paseler (1988) use a non probabilistic Earley parser augmented with word match scoring. Though not truly probabilistic, these algorithms are similar to the Viterbi version described here, in that they find a parse that optimizes the accumulated matching scores 17 The identity of this ....

Nakagawa, Sei-ichi. 1987. Spoken sentence recognition by time-synchronous parsing algorithm of context-free grammar. In Proceedings IEEE Conference on Acoustics, Speech and Signal Processing , volume 2, 829--832, Dallas, Texas.

.... play a central role in integrating low level word models with higherlevel language models (Ney 1992) as well as in non finite state acoustic and phonotactic modeling (Lari Young 1991) In some work, context free grammars are combined with scoring functions that are not strictly probabilistic (Nakagawa 1987), or they are used with context sensitive and or semantic probabilities (Magerman Marcus 1991; Magerman Weir 1992; Jones Eisner 1992a; Briscoe Carroll 1993) Although clearly not a perfect model of natural language, stochastic context free grammars (SCFGs) are superior to ....

....for computing prefix probabilities. Magerman Marcus (1991) are interested primarily in scoring functions to guide a parser efficiently to the most promising parses. They use Earley style top down prediction only to suggest worthwhile parses, not to compute precise probabilities. 24 Both Nakagawa (1987) and Paseler (1988) use a non probabilistic Earley parser augmented with word match scoring. Though not truly probabilistic, these algorithms are similar to the Viterbi version described here, in that they find a parse that optimizes the accumulated matching scores (without regard to rule ....

NAKAGAWA, SEI-ICHI. 1987. Spoken sentence recognition by time-synchronous parsing algorithm of contextfree grammar. In Proceedings IEEE Conference on Acoustics, Speech and Signal Processing, volume 2, 829--832, Dallas, Texas.

....contextual distinctions. This effect is particularly visible when parsing incomplete sentences [16] Efficiency loss with increased look ahead is mainly due to state splitting [6] This should favor LALR techniques over LR ones. However, in the case of incomplete sentences or word lattice parsing [21, 30], and more generally in so called robust parsing, loss of efficiency and sharing may be due to the (actually ambiguous) look ahead itself. 13 Our results do not take into account a newly found optimization of PDT interpretation that applies to all and only to bottomup PDTs. This should make ....

.... and extensions still remain to be made: improved dynamic programming interpretation of bottom up parsers, more extensive experimental measurements with a variety of languages and parsing schemata, or generalization of this approach to more complex situations, such as word lattice parsing [21, 30], or even handling of secondary language features. Early research in that latter direction is promising: our framework and the corresponding paradigm for parser construction have been extended to full first order Horn clauses [17, 18] and are hence applicable to unification based grammatical ....

Nakagawa, S. 1987 Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of Context-Free Grammar. Proc. ICASSP 87, Dallas (Texas), Vol. 2 : 829-832.

....bottom up, etc. 1 Introduction It is often necessary in practical situations to attempt parsing an incorrect or incomplete input. This may take many forms: e.g. missing or spurious words, misspelled or misunderstood or otherwise unknown words [28] missing or unidentified word boundaries [22, 27]. Specific techniques may be developed to deal with these situations according to the requirements of the application area (e.g. natural language processing, programming language parsing, real time or off line processing) The context free (CF) parsing of a sentence with unknown words has been ....

....that created by cyclic grammars, i.e. grammars where a nonterminal may derive onto itself without producing any terminal. This explains why techniques limited to non cyclic grammars cannot deal with this problem. It may be noted that the problem is different from that of parsing in a word lattice [22, 27] since all possible path in the lattice have a known bounded length, even when the lattice contains separated unknown words. However the technique presented here combines well with word lattice parsing. The ability to parse unknown subsequences may be useful to parse badly transmitted sentences, ....

Nakagawa, S. 1987 Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of Context-Free Grammar. Proc. ICASSP 87, Dallas (Texas), Vol. 2 : 829-832.

....is 80 and 99 , respectively. 1 INTRODUCTION There have been many speech recognition systems which use syntactic information to improve recognition accuracy. For example, statistical language modeling such as a bigram or a trigram [1, 2, 3] nite state grammars [4, 5] and context free grammars [6, 7]. This paper proposes a new method for parsing speech data directly without any intervening structure such as a phoneme lattice. This method uses generalized LR parsing [8] and HMM phone veri ers. Generalized LR parsing is a kind of LR parsing [9] originally developed for programming languages ....

S.Nakagawa: \Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of ContextFree Grammar", ICASSP 87 (April 1987)

No context found.

NAKAGAWA,SEI-ICHI. 1987. Spoken sentence recognition by time-synchronous parsing algorithm of contextfree grammar. In Proceedings IEEE Conference on Acoustics, Speech and Signal Processing, volume 2, 829--832, Dallas, Texas.

No context found.

Nakagawa, S. 1987 Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of Context-Free Grammar. Proc. ICASSP 87, Dallas (Texas), Vol. 2 : 829-832.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC