1. A computer readable medium including instructions readable by a computer which, when implemented execute a method to perform language processing for recognizing language and providing an output signal indicative thereof, the method comprising:
receiving an input signal indicative of language;
accessing a unified language model to recognize the language and predict non-terminal tokens contained therein, the unified language model comprising a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals, and a N-gram language model having the non-terminal tokens; and
generating hypotheses for the language by exploring each of the terminals in the unified language model associated with the non-terminal tokens predicted based on a probability value for each terminal, wherein at least one terminal has a different probability value than one other terminal in the same context-free grammar.
2. The computer readable medium of claim 1 wherein each of the terminals of the plurality of context-free grammars include a probability value, and wherein the method further comprises calculating a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
3. The computer readable medium of claim 2 and further comprising:
assigning probability values of at least some of the terminals of the context-free grammars from a terminal-based language model and normalizing said values using the set of terminals constrained by the context-free grammars.
4. The computer readable medium of claim 1 and further comprising:
providing an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
5. A language processing system comprising:
a unified language model comprising:
a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals; and
a N-gram language model having the non-terminal tokens; and
a language processing module capable of receiving an input signal indicative of language and accessing the unified language model to recognize the language and predict non-terminal tokens contained therein, the language processing module further adapted to generate hypotheses for the language by exploring each of the terminals in the unified language model associated with the non-terminal tokens predicted based on a probability value for each terminal, wherein at least one terminal has a different probability value than one other terminal in the same context-free grammar.
6. The system of claim 5 wherein each of the terminals of the plurality of context-free grammars include a probability value, and wherein the language processing module is further adapted to calculate a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
7. The system of claim 5 wherein the language processing module is further adapted to assign probability values of at least some of the terminals of the context-free grammars from a terminal-based language model and normalize said values using the set of terminals constrained by the context-free grammars.
8. The system of claim 5 wherein the language processing module is further adapted to provide an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
9. A method to perform language processing comprising:
receiving an input signal indicative of language;
accessing a unified language model to recognize the language and predict non-terminal tokens contained therein, the unified language model comprising a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals wherein each of the terminals of the plurality of context-free grammars include a probability value, and a N-gram language model having the non-terminal tokens;
assigning probability values of at least some of the terminals of the context-free grammars from a terminal-based language model, wherein at least one terminal has a probability value different than one other terminal in the same context-free grammar and normalizing said values using the set of terminals constrained by the context-free grammars;
generating hypotheses for the language as a function of words in the unified language model corresponding to the non-terminal tokens predicted; and
calculating a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
10. The method of claim 9 and further comprising:
providing an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
11. A language processing system comprising:
a unified language model comprising:
a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals, wherein each of the terminals of the plurality of context-free grammars include a probability value; and
a N-gram language model having the non-terminal tokens; and
a language processing module capable of receiving an input signal indicative of language and accessing the unified language model to recognize the language and predict non-terminal tokens contained therein, the language processing module further adapted to assign probability values of at least some of the terminals of the context-free grammars from a terminal-based language model, wherein at least one terminal has a probability value different than one other terminal in the same context-free grammar and normalize said values using the set of terminals constrained by the context-free grammars, and adapted to generate hypotheses for the language as a function of words in the unified language model corresponding to the non-terminal tokens predicted and calculate a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
12. The system of claim 11 wherein the language processing module is further adapted to provide an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
13. A computer readable medium having instructions to process information, the instructions comprising:
a unified language model comprising:
a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals, wherein each of the terminals include a probability value assigned by using non-uniform probability values derived from a terminal based language model and normalizing said values using the set of terminals constrained by the plurality of context-free grammars; and
a N-gram language model having the non-terminal tokens; and
a language processing module capable of receiving an input signal indicative of language and accessing the unified language model to recognize the language and predict non-terminal tokens contained therein, the language processing module further generating hypotheses for the received language as a function of words in the unified language model corresponding to the non-terminal tokens predicted and calculating a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
14. The computer readable medium of claim 3 wherein the language processing module provides an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
15. A method to perform language processing comprising:
receiving an input signal indicative of language;
accessing a unified language model to recognize the language and predict non-terminal tokens contained therein, the unified language model comprising a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals, wherein each of the terminals include a probability value assigned by using non-uniform probability values derived from a terminal based language model, said values being normalized using the set of terminals constrained by the plurality of context-free grammars, and a N-gram language model having the non-terminal tokens; and
generating hypotheses for the received language as a function of words in the unified language model corresponding to the non-terminal tokens predicted and calculating a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
16. The method of claim 15 and further comprising:
providing an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
17. A computer readable medium including instructions readable by a computer which, when implemented execute a method to perform language processing for recognizing language and providing an output signal indicative thereof, the method comprising:
receiving an input signal indicative of language;
accessing a unified language model to recognize the language and predict non-terminal tokens contained therein, the unified language model comprising a plurality of context-free grammars comprising non-terminal tokens representing semantic or syntactic concepts and terminals, wherein each of the terminals include a probability value assigned by using non-uniform probability values derived from a terminal based language model, said values being normalized using the set of terminals constrained by the plurality of context-free grammars, and a N-gram language model having the non-terminal tokens; and
generating hypotheses for the received language as a function of words in the unified language model corresponding to the non-terminal tokens predicted and calculating a language model score for each of the hypotheses using the associated probability value for each terminal present therein and obtained from the plurality of context-free grammars.
18. The computer readable medium of claim 17 and further comprising:
providing an output signal indicative of the language and at least some of the semantic or syntactic concepts contained therein.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A product comprising:
a dust collection device for a sanding tool comprising a bag having a sidewall with an inner surface and a coupler attached to the bag;
the sidewall comprising at least one filter layer and an outer support layer;
a sleeve having an outer surface, a sleeve sidewall with an inner surface, a first open end, a second open end, a first gap having a first gap area with an air flow path located at the first open end between the sleeve first open end and both the coupler and the inner surface of the bag and a second gap having a second gap area with an air flow path located at the second open end between the sleeve second open end and the inner surface of the bag; the sleeve constructed from a porous air permeable material; and
the first open end positioned surrounding the coupler to direct incoming air through the sleeve and the sleeve apportioning more airflow through the first gap and the second gap as the permeability of the sleeve is reduced, and the sleeve is sized and positioned within the bag such that an air flow bypass volume is present between the outer surface and the inner surface.
2. The product of claim 1 wherein the sidewall comprises a first filter layer, a second filter layer, and the outer support layer.
3. The product of claim 2 wherein the first filter layer comprises electrostatically charged electret fibers.
4. The product of claim 3 wherein the second filter layer comprises a melt blown microfiber web.
5. The product of claim 2 wherein the second filter layer comprises a melt blown microfiber web.
6. The product of claim 2, 3, 4, or 5 comprising the first filter layer having a total pressure drop at a flow rate of 85 litersmin between about 1.0 to about 4.0 mm H2O, and the first filter layer having a total basis weight between about 100 to about 300 gramsm2; and the second filter layer having a total pressure drop at a flow rate of 85 litersmin between about 10 to about 18 mm H20, and the second filter layer having a total basis weight between about 25 to about 75 gramsm2.
7. The product of claim 2, 3, 4, or 5 comprising the first filter layer having a total pressure drop at a flow rate of 85 litersmin between about 0.1 to about 4.0 mm H2O, and the first filter layer having a total basis weight between about 50 to about 450 gramsm2; and the second filter layer having a total pressure drop at a flow rate of 85 litersmin between about 5.5 to about 20 mm H20, and the second filter layer having a total basis weight between about 15 to about 75 gramsm2.
8. The product of claim 1 wherein the sleeve comprises a nonwoven material.
9. The product of claim 1 wherein the sleeve comprises a pleated material.
10. The product of claim 1 wherein the sleeve sidewall comprises a total pressure drop at a flow rate of 85 litersmin between about 0.05 mm H2O to about 5.0 mm H2O.
11. The product of claim 10 wherein the sleeve sidewall comprises a total pressure drop at a flow rate of 85 litersmin between about 0.15 mm H2O to about 0.8 mm H2O.
12. The product of claim 1 wherein the sleeve sidewall comprises a total basis weight between about 10 to about 400 gramsm2.
13. The product of claim 12 wherein the sleeve sidewall comprises a total basis weight between about 40 to about 250 gramsm2.
14. The product of claim 1 wherein the first gap area plus the second gap area is between about 5 cm2 to about 160 cm2.
15. The product of claim 1 wherein the first gap area plus the second gap area is between about 1 cm2 to about 1240 cm2.
16. The product of claim 1 wherein the first gap area plus the second gap area is between about 5 cm2 to about 600 cm2.
17. The product of claim 1 wherein the first gap area plus the second gap area is between about 75 cm2 to about 90 cm2.
18. The product of claim 1 wherein the first gap area plus the second gap area is between about 75 cm2 to about 400 cm2.
19. The product of claim 1 wherein the bag has an area, AB, and the sleeve has an area, AS, and an Area Ratio ASAB is between about 0.2 to about 0.8.
20. The product of claim 19 wherein the Area Ratio ASAB is between about 0.4 to about 0.6.
21. The product of claim 1 wherein the coupler comprises a barbed first end, a flange, and a ribbed second end, and the flange is attached to the sidewall such that the ribbed second end resides inside of the first end of the sleeve.