WO2002097663A1 - Integer programming decoder for machine translation - Google Patents

Integer programming decoder for machine translation Download PDF

Info

Publication number
WO2002097663A1
WO2002097663A1 PCT/US2002/017347 US0217347W WO02097663A1 WO 2002097663 A1 WO2002097663 A1 WO 2002097663A1 US 0217347 W US0217347 W US 0217347W WO 02097663 A1 WO02097663 A1 WO 02097663A1
Authority
WO
WIPO (PCT)
Prior art keywords
translation
machine
operative
cause
nodes
Prior art date
Application number
PCT/US2002/017347
Other languages
French (fr)
Inventor
Kevin Knight
Kenji Yamada
Original Assignee
University Of Southern California
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by University Of Southern California filed Critical University Of Southern California
Publication of WO2002097663A1 publication Critical patent/WO2002097663A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation
    • G06F40/44—Statistical methods, e.g. probability models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation

Definitions

  • Machine translation concerns the automatic translation of natural language sentences from a first language (e.g., French) into another language (e.g., English) .
  • Systems that perform MT techniques are said to "decode" the source language into the target language.
  • One type of MT decoder is the statistical MT decoder.
  • a statistical MT decoder that translates French sentences into English may include a language model (LM) that assigns a probability P(e) to any English string, a translation model (TM) that assigns a probability P(f
  • the decoder may take a previously unseen sentence f and try to find the e that maximizes P(e
  • a "stack decoder” is a type of statistical MT decoder. In a stack decoder, possible translations are organized into a graph structure and then searched until an optimal solution (translation) is found. Although stack decoders tend to produce good results, they do so at a significant cost. Maintaining and searching a large potential solution space is expensive, both computationally and in terms of computer memory.
  • a machine translation (MT) decoder may transform a translation problem into an integer programming problem, such as a Traveling Salesman Problem (TSP) .
  • the decoder may include a graph generator which generates a graph including a number of regions, or cities, corresponding to words in an input source language sentence or phrase. Each region may include a number of nodes, or hotels, corresponding to possible translations of the source language word corresponding to that region.
  • the graph generator may use linguistic constraint information in a translation database to assign distances between hotels.
  • the decoder may invoke an integer program (IP) solver to find a shortest tour on the graph, i.e., solve the TSP.
  • IP integer program
  • the decoder may output a likely decoding which includes the words corresponding to the hotels visited aligned in the order the hotels were visited in the tour.
  • Figure 1 is a block diagram of a machine translation decoder.
  • Figure 2 is a flowchart describing an integer programming decode operation 200.
  • Figure 3 is a salesman graph for a translation problem.
  • Figure 4 illustrates the results of a word alignment operation.
  • Figure 1 illustrates a machine translation (MT) decoder 100 which utilizes a linear integer programming model to translate sentences in a source language (e.g., French) into a target language (e.g., English).
  • the decoder 100 may transform a decoding problem into a linear integer programming problem.
  • a solution to an integer programming problem involves an assignment of variables. Solutions are constrained by inequalities involving linear combinations of variables. An optimal solution is one that respects the constraints and minimizes the value of the objective function, which is also a linear combination of variables .
  • TSP Traveling Salesman Problem
  • the hypothetical situation posed by the TSP concerns a salesman who spends his time visiting a number of cities (or nodes) cyclically. In one tour the salesman visits each city just once, and finishes up where he started.
  • the Traveling Salesman Problem is this: given a finite number of "cities" along with the cost of travel between each pair of them (e.g., distance), find the cheapest (e.g., shortest) way of visiting all the cities and returning to the starting point.
  • TSP TSP
  • IP integer program
  • the decoder may transform a decoding problem into a TSP format and then use an IP solver 105 to generate a translation.
  • Figure 2 is a flowchart describing a decoding operation 200 according to an embodiment .
  • a graph generator 110 may express an MT decoding problem in a TCP format by constructing a salesman graph.
  • Each word in the observed sentence f may be represented as a city 305.
  • City boundaries 310 are shown with bold lines.
  • Each city may be populated with a number of hotels 315 corresponding to likely English word translations (block 210) .
  • the owner of a hotel is the English word inside the rectangle.
  • a third hotel 320 owned by x (e.g., the English word "is") may be built on the border of the two cities (in this case, the cities "CE” and "EST") . More generally, if n cities all have hotels owned by x, 2 n - n - 1 new hotels may be build, one for each non-empty, non-singleton subset of the cities, on various city borders and intersections. An extra city representing the sentence boundary may also be added to the salesman graph and serve as the starting point for the tour.
  • a tour of cities may be defined as a sequence of hotels (starting at the sentence boundary hotel) that visits each city exactly once before returning to the starting point. If a hotel sits on the border between two cities, then staying at that hotel counts as visiting both cities.
  • Each tour of cities corresponds to a potential decoding ⁇ e,a>, where "e" represents the words in the English string and "a" represents the alignment of the words. The owners of the hotels on the tour yield e, while the hotel locations yield a.
  • the distances between hotels may represent various constraints of an integer program. Real-valued (asymmetric) distances may be established between pairs of hotels such that the length of any tour is exactly the negative of log(P(e) • P(a,f
  • the distance assigned to each pair of hotels may be based on a translation model 115, e.g., the IBM Model 4 formula, described in U.S. Patent No. 5,477,451. The IBM Model 4 revolves around the notion of a word alignment over a pair of sentences, such as that shown in Figure .
  • a word alignment assigns a single home (English string position) to each French word. If two French words align to the same English word, then that English word is said to have a fertility of two. Likewise, if an English word remains unaligned-to, then it has fertility zero. Because the destination hotel "not" sits on the border between cities NE and PAS, it corresponds to a partial alignment in which the word "not” has fertility two:
  • NULL-owned hotels may be treated specially. All non-NULL hotels must be visited before any NULL hotels and at most one NULL hotel may be visited on a tour. Since only one NULL hotel is allowed to be visited, the fertility of the NULL word is simply the number of cities that hotel straddles, and the length of f is the number of cities minus one.
  • the tour selection may be cast as an integer programming problem (block 225) .
  • a binary (0/1) integer variable ⁇ ⁇ J may be created for each pair of hotels i and j .
  • the value x 13 equals 1 if and only if travel from hotel i to hotel j is on the itinerary.
  • the objective function is then:
  • Every hotel has either (a) one tour segment coming in and one going out, or (b) no segments in and none out. To put it another way, every hotel must have an equal number of tour segments going in and out:
  • IP solver may be invoked.
  • Exemplary IP solvers include lp_solve, available free of charge at ftp://ftp.ics.ele.tue.nl/pub/lp_solve, and CPLEX, available from ILOG, Inc. of Mountain View, California.
  • Mnemonic names may be assigned to the variables, and ⁇ e,a> extracted from the list of variables and their binary values.
  • the sentence corresponding to the shortest tour may then be output (block 235) .
  • the shortest tour 350 for the graph 300 in Figure 3 corresponds to the optimal decoding: "it is not clear .
  • a second-best decoding can be obtained by adding a new constraint to the integer programming problem to stop the IP solver 105 from choosing the same solution again.

Abstract

A machine translation (MT) decoder (100) may transform a translation problem into an integer programming problem (200), such as a Traveling Salesman Problem (TSP). The decoder (100) may invoke an integer program (IP) solver to solve the integer programming problem (200) and output a likely decoding based on the solution.

Description

INTEGER PROGRAMMING DECODER FOR MACHINE TRANSLATION
CROSS-REFERENCE TO RELATED APPLICATIONS [0001] This application claims priority to U.S.
Provisional Patent Application Serial No. 60/295,182, filed on May 31, 2001.
ORIGIN OF INVENTION [0002] The research and development described in this application were supported by DARPA-ITO under grant number N66001-00-1-9814. The U.S. Government may have certain rights in the claimed inventions.
BACKGROUND [0003] Machine translation (MT) concerns the automatic translation of natural language sentences from a first language (e.g., French) into another language (e.g., English) . Systems that perform MT techniques are said to "decode" the source language into the target language. [0004] One type of MT decoder is the statistical MT decoder. A statistical MT decoder that translates French sentences into English may include a language model (LM) that assigns a probability P(e) to any English string, a translation model (TM) that assigns a probability P(f |e) to any pair of English and French strings, and a decoder. The decoder may take a previously unseen sentence f and try to find the e that maximizes P(e|f), or equivalently maximizes P(e) • P(f|e).
[0005] A "stack decoder" is a type of statistical MT decoder. In a stack decoder, possible translations are organized into a graph structure and then searched until an optimal solution (translation) is found. Although stack decoders tend to produce good results, they do so at a significant cost. Maintaining and searching a large potential solution space is expensive, both computationally and in terms of computer memory.
SUMMARY [0006] A machine translation (MT) decoder may transform a translation problem into an integer programming problem, such as a Traveling Salesman Problem (TSP) . The decoder may include a graph generator which generates a graph including a number of regions, or cities, corresponding to words in an input source language sentence or phrase. Each region may include a number of nodes, or hotels, corresponding to possible translations of the source language word corresponding to that region. The graph generator may use linguistic constraint information in a translation database to assign distances between hotels.
[0007] The decoder may invoke an integer program (IP) solver to find a shortest tour on the graph, i.e., solve the TSP. The decoder may output a likely decoding which includes the words corresponding to the hotels visited aligned in the order the hotels were visited in the tour.
BRIEF DESCRIPTION OF THE DRAWINGS [0008] Figure 1 is a block diagram of a machine translation decoder.
[0009] Figure 2 is a flowchart describing an integer programming decode operation 200.
[0010] Figure 3 is a salesman graph for a translation problem.
[0011] Figure 4 illustrates the results of a word alignment operation.
DETAILED DESCRIPTION [0012] Figure 1 illustrates a machine translation (MT) decoder 100 which utilizes a linear integer programming model to translate sentences in a source language (e.g., French) into a target language (e.g., English). The decoder 100 may transform a decoding problem into a linear integer programming problem.
[0013] A solution to an integer programming problem involves an assignment of variables. Solutions are constrained by inequalities involving linear combinations of variables. An optimal solution is one that respects the constraints and minimizes the value of the objective function, which is also a linear combination of variables .
[0014] One type of linear integer programming problem is the Traveling Salesman Problem (TSP) . The hypothetical situation posed by the TSP concerns a salesman who spends his time visiting a number of cities (or nodes) cyclically. In one tour the salesman visits each city just once, and finishes up where he started. The Traveling Salesman Problem is this: given a finite number of "cities" along with the cost of travel between each pair of them (e.g., distance), find the cheapest (e.g., shortest) way of visiting all the cities and returning to the starting point.
[0015] Much effort has been dedicated to the TSP, and powerful tools have been developed to solve TSP and other integer programming problems. For example, the Center for Research on Parallel Computation (CRPC) , a National Science Foundation Science and Technology Center established in 1989, has solved the TSP for 13,509 U.S. cities with populations of more than 500 people. Such an integer program (IP) solver may be utilized by the decoder 100 to solve a translation problem posed as a TSP.
[0016] The decoder may transform a decoding problem into a TSP format and then use an IP solver 105 to generate a translation. Figure 2 is a flowchart describing a decoding operation 200 according to an embodiment .
[0017] A graph generator 110 may express an MT decoding problem in a TCP format by constructing a salesman graph. Figure 3 is a salesman graph 300 for the input sentence f = "CE NE EST PAS CLAIR ." (block 205). Each word in the observed sentence f may be represented as a city 305. City boundaries 310 are shown with bold lines. Each city may be populated with a number of hotels 315 corresponding to likely English word translations (block 210) . The owner of a hotel is the English word inside the rectangle. If two cities have hotels with the same owner x, then a third hotel 320 owned by x (e.g., the English word "is") may be built on the border of the two cities (in this case, the cities "CE" and "EST") . More generally, if n cities all have hotels owned by x, 2n - n - 1 new hotels may be build, one for each non-empty, non-singleton subset of the cities, on various city borders and intersections. An extra city representing the sentence boundary may also be added to the salesman graph and serve as the starting point for the tour.
[0018] A tour of cities may be defined as a sequence of hotels (starting at the sentence boundary hotel) that visits each city exactly once before returning to the starting point. If a hotel sits on the border between two cities, then staying at that hotel counts as visiting both cities. Each tour of cities corresponds to a potential decoding <e,a>, where "e" represents the words in the English string and "a" represents the alignment of the words. The owners of the hotels on the tour yield e, while the hotel locations yield a.
[0019] The distances between hotels may represent various constraints of an integer program. Real-valued (asymmetric) distances may be established between pairs of hotels such that the length of any tour is exactly the negative of log(P(e) • P(a,f | e) ) (block 215). For example, because the logarithm function is monotonic, the shortest tour may correspond to the likeliest decoding. [0020] The distance assigned to each pair of hotels may be based on a translation model 115, e.g., the IBM Model 4 formula, described in U.S. Patent No. 5,477,451. The IBM Model 4 revolves around the notion of a word alignment over a pair of sentences, such as that shown in Figure . A word alignment assigns a single home (English string position) to each French word. If two French words align to the same English word, then that English word is said to have a fertility of two. Likewise, if an English word remains unaligned-to, then it has fertility zero. Because the destination hotel "not" sits on the border between cities NE and PAS, it corresponds to a partial alignment in which the word "not" has fertility two:
... what not ...
/ _A__ / / \ CE NE EST PAS CLAIR .
[0021] Assuming that the price has already been paid for visiting the "what" hotel, then the inter-hotel distance need only account for the partial alignment concerning "not": distance =
-log (bigram(not | what)) //chance of "not" given the previous word was "what" -log(n(2 | not)) //chance that word "not" in English generates two French words
-log(t(NE I not)) - log (t (PAS | not)) //chance that "not" would translate to "ne" and "pas".
-log(dι(+l I class (what) , class (NE) ) )
-log(d>ι(+2 I class (PAS))) //given that "what" translates to the first French word, what is the chance that "not" will translate to the second French word.
These and constraints for different words may be stored in a translation database 120.
[0022] An infinite distance may be assigned in both directions between hotels that are located (even partially) in the same city because travel from one to the other can never be part of a tour. [0023] NULL-owned hotels may be treated specially. All non-NULL hotels must be visited before any NULL hotels and at most one NULL hotel may be visited on a tour. Since only one NULL hotel is allowed to be visited, the fertility of the NULL word is simply the number of cities that hotel straddles, and the length of f is the number of cities minus one.
[0024] The tour selection may be cast as an integer programming problem (block 225) . A binary (0/1) integer variable κ±J may be created for each pair of hotels i and j . The value x13 equals 1 if and only if travel from hotel i to hotel j is on the itinerary. The objective function is then:
minimize : ^ χu •distance^', j)
(■ )
[0025] This minimization may be subject to three classes of constraints. First, every city must be visited exactly once. That means exactly one tour segment must exit each city:
cecities * , / . Λ, IJ
/ located at least / partially in c
[0026] Second, the segments must be linked to one another, i.e., every hotel has either (a) one tour segment coming in and one going out, or (b) no segments in and none out. To put it another way, every hotel must have an equal number of tour segments going in and out:
Figure imgf000010_0001
J J
[0027] Third, to prevent multiple independent sub- tours, require that every proper subset of cities have at least one tour segment leaving it:
Figure imgf000010_0002
[0028] There may be an exponential number of constraints in this third class.
[0029] Once cast as an integer program, the IP solver may be invoked. Exemplary IP solvers include lp_solve, available free of charge at ftp://ftp.ics.ele.tue.nl/pub/lp_solve, and CPLEX, available from ILOG, Inc. of Mountain View, California. [0030] Mnemonic names may be assigned to the variables, and <e,a> extracted from the list of variables and their binary values. The sentence corresponding to the shortest tour may then be output (block 235) . For example, the shortest tour 350 for the graph 300 in Figure 3 corresponds to the optimal decoding: "it is not clear . " A second-best decoding can be obtained by adding a new constraint to the integer programming problem to stop the IP solver 105 from choosing the same solution again.
[0031] A number of embodiments have been described. Nevertheless, it will be understood that various modifications may be made without departing from the spirit and scope of the invention. For example, blocks in the flowchart may be skipped or performed out of order and still produce desirable results. Accordingly, other embodiments are within the scope of the following claims.

Claims

1. A method comprising: transforming a translation problem into an integer programming problem; and generating a translation in response to solving the integer programming problem.
2. The method of claim 1, wherein said generating a translation comprises generating a text segment in a target language corresponding to a translation of a text segment in a source language.
3. The method of claim 1, wherein said transforming comprises generating a graph comprising a plurality of regions, each region including one or more nodes.
4. The method of claim 3, further comprising: inputting a text segment including words in a source language, wherein each of said plurality of regions represents a corresponding one of the words in the source language, and wherein the one or more nodes in each of said plurality of regions represent possible translations of the word corresponding to said region.
5. The method of claim 4, further comprising: assigning a distance between each of said nodes, said distance comprising one or more linguistic constraints.
6. The method of claim 5, wherein said generating a translation comprises finding a shortest tour including one node in each of said plurality of regions.
7. The method of claim 6, wherein said graph further comprises a region corresponding to a sentence boundary.
8. The method of claim 7, wherein said tour begins and ends in the region corresponding to the sentence boundary.
9 The method of claim 1, wherein said transforming comprises transforming the translation problem into a traveling salesman problem.
10. Apparatus comprising: a transformation module operative to transform an input text segment in a source language into an integer programming problem ; and an integer program solver operative to solve said integer programming problem.
11. The apparatus of claim 10, further comprising: a database including a plurality of linguistic constraints for a target language and a plurality of words in the target language corresponding to possible translations for a plurality of words in a source language .
12. The apparatus of claim 11, wherein the transformation module comprises a graph generator operative to generate a graph including a plurality of regions and a plurality of nodes, each region corresponding to a word in an input source language text segment and each node corresponding to a possible translation of a word in the input source language, and to assign a distance between nodes based on said plurality of linguistic constraints.
13. The apparatus of claim 12, wherein the integer program solver is operative to find a shortest tour including one node in each of said plurality of regions.
14. The apparatus of claim 13, wherein the integer problem solver is further operative to output a text segment in the target language, said text segment including a plurality of words corresponding to the nodes in the shortest tour.
15. The apparatus of claim 14, wherein the plurality of words are aligned in an order corresponding to an order of nodes visited in the tour.
16. An article comprising a machine-readable medium including machine-executable instructions, the instruction operative to cause the machine to: transform a translation problem into an integer programming problem; and generate a translation in response to solving the integer programming problem.
17. The article of claim 16, wherein the instructions operative to cause the machine to generate a translation include instructions operative to cause the machine to generate a text segment in a target language corresponding to a translation of a text segment in a source language.
18. The article of claim 16, wherein the instructions operative to cause the machine to transform include instructions operative to cause the machine to generate a graph comprising a plurality of regions, each region including one or more nodes.
19. The article of claim 18, further comprising instructions operative to cause the machine to: input a text segment including words in a source language, wherein each of said plurality of regions represents a corresponding one of the words in the source language, and wherein the one or more nodes in each of said plurality of regions represent possible translations of the word corresponding to said region.
20. The article of claim 19, further comprising instructions operative to cause the machine to: assign a distance between each of said nodes, said distance comprising one or more linguistic constraints .
21. The article of claim 20, wherein the instructions operative to cause the machine to generate a translation includes instructions operative to cause the machine to find a shortest tour including one node in each of said plurality of regions .
22. The article of claim 21, wherein said graph further comprises a region corresponding to a sentence boundary.
23. The article of claim 22, wherein said tour begins and ends in the region corresponding to the sentence boundary.
24. The article of claim 16, wherein the instructions operative to cause the machine to transform instructions operative to cause the machine to transform the translation problem into a traveling salesman problem.
PCT/US2002/017347 2001-05-31 2002-05-31 Integer programming decoder for machine translation WO2002097663A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US29518201P 2001-05-31 2001-05-31
US60/295,182 2001-05-31

Publications (1)

Publication Number Publication Date
WO2002097663A1 true WO2002097663A1 (en) 2002-12-05

Family

ID=23136586

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2002/017347 WO2002097663A1 (en) 2001-05-31 2002-05-31 Integer programming decoder for machine translation

Country Status (2)

Country Link
US (2) US7177792B2 (en)
WO (1) WO2002097663A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011028754A (en) * 2009-07-27 2011-02-10 Xerox Corp Phrase-based statistical machine translation as generalized traveling sales person problem

Families Citing this family (66)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060116865A1 (en) 1999-09-17 2006-06-01 Www.Uniscape.Com E-services translation utilizing machine translation and translation memory
US7904595B2 (en) 2001-01-18 2011-03-08 Sdl International America Incorporated Globalization management system and method therefor
US7177792B2 (en) * 2001-05-31 2007-02-13 University Of Southern California Integer programming decoder for machine translation
US8214196B2 (en) 2001-07-03 2012-07-03 University Of Southern California Syntax-based statistical translation model
WO2004001623A2 (en) 2002-03-26 2003-12-31 University Of Southern California Constructing a translation lexicon from comparable, non-parallel corpora
US8548794B2 (en) 2003-07-02 2013-10-01 University Of Southern California Statistical noun phrase translation
US7711545B2 (en) * 2003-07-02 2010-05-04 Language Weaver, Inc. Empirical methods for splitting compound words with application to machine translation
WO2005089340A2 (en) * 2004-03-15 2005-09-29 University Of Southern California Training tree transducers
US8296127B2 (en) * 2004-03-23 2012-10-23 University Of Southern California Discovery of parallel text portions in comparable collections of corpora and training using comparable texts
US8666725B2 (en) 2004-04-16 2014-03-04 University Of Southern California Selection and use of nonstatistical translation components in a statistical machine translation framework
US7936861B2 (en) 2004-07-23 2011-05-03 At&T Intellectual Property I, L.P. Announcement system and method of use
US7580837B2 (en) 2004-08-12 2009-08-25 At&T Intellectual Property I, L.P. System and method for targeted tuning module of a speech recognition system
US20060050865A1 (en) * 2004-09-07 2006-03-09 Sbc Knowledge Ventures, Lp System and method for adapting the level of instructional detail provided through a user interface
JP5452868B2 (en) 2004-10-12 2014-03-26 ユニヴァーシティー オブ サザン カリフォルニア Training for text-to-text applications that use string-to-tree conversion for training and decoding
US7657005B2 (en) 2004-11-02 2010-02-02 At&T Intellectual Property I, L.P. System and method for identifying telephone callers
US7242751B2 (en) 2004-12-06 2007-07-10 Sbc Knowledge Ventures, L.P. System and method for speech recognition-enabled automatic call routing
US7864942B2 (en) * 2004-12-06 2011-01-04 At&T Intellectual Property I, L.P. System and method for routing calls
US7751551B2 (en) 2005-01-10 2010-07-06 At&T Intellectual Property I, L.P. System and method for speech-enabled call routing
US7627096B2 (en) * 2005-01-14 2009-12-01 At&T Intellectual Property I, L.P. System and method for independently recognizing and selecting actions and objects in a speech recognition system
US7450698B2 (en) * 2005-01-14 2008-11-11 At&T Intellectual Property 1, L.P. System and method of utilizing a hybrid semantic model for speech recognition
US7627109B2 (en) 2005-02-04 2009-12-01 At&T Intellectual Property I, Lp Call center system for multiple transaction selections
US8005204B2 (en) 2005-06-03 2011-08-23 At&T Intellectual Property I, L.P. Call routing system and method of using the same
US7657020B2 (en) * 2005-06-03 2010-02-02 At&T Intellectual Property I, Lp Call routing system and method of using the same
US8886517B2 (en) 2005-06-17 2014-11-11 Language Weaver, Inc. Trust scoring for language translation systems
US8676563B2 (en) 2009-10-01 2014-03-18 Language Weaver, Inc. Providing human-generated and machine-generated trusted translations
US7974833B2 (en) 2005-06-21 2011-07-05 Language Weaver, Inc. Weighted system of expressing language information using a compact notation
US20070010989A1 (en) * 2005-07-07 2007-01-11 International Business Machines Corporation Decoding procedure for statistical machine translation
US7389222B1 (en) 2005-08-02 2008-06-17 Language Weaver, Inc. Task parallelization in a text-to-text system
US7813918B2 (en) * 2005-08-03 2010-10-12 Language Weaver, Inc. Identifying documents which form translated pairs, within a document collection
US7624020B2 (en) * 2005-09-09 2009-11-24 Language Weaver, Inc. Adapter for allowing both online and offline training of a text to text system
US10319252B2 (en) 2005-11-09 2019-06-11 Sdl Inc. Language capability assessment and training apparatus and techniques
US8943080B2 (en) 2006-04-07 2015-01-27 University Of Southern California Systems and methods for identifying parallel documents and sentence fragments in multilingual document collections
US20080027900A1 (en) * 2006-07-12 2008-01-31 International Business Machines Corporation Method and system for optimal selection of targets based on business rules and resource availability
US8886518B1 (en) 2006-08-07 2014-11-11 Language Weaver, Inc. System and method for capitalizing machine translated text
US8433556B2 (en) 2006-11-02 2013-04-30 University Of Southern California Semi-supervised training for statistical word alignment
US9122674B1 (en) 2006-12-15 2015-09-01 Language Weaver, Inc. Use of annotations in statistical machine translation
US8468149B1 (en) 2007-01-26 2013-06-18 Language Weaver, Inc. Multi-lingual online community
US8615389B1 (en) 2007-03-16 2013-12-24 Language Weaver, Inc. Generation and exploitation of an approximate language model
US8831928B2 (en) 2007-04-04 2014-09-09 Language Weaver, Inc. Customizable machine translation service
US8825466B1 (en) 2007-06-08 2014-09-02 Language Weaver, Inc. Modification of annotated bilingual segment pairs in syntax-based machine translation
US8209164B2 (en) * 2007-11-21 2012-06-26 University Of Washington Use of lexical translations for facilitating searches
US8990064B2 (en) 2009-07-28 2015-03-24 Language Weaver, Inc. Translating documents based on content
US8380486B2 (en) 2009-10-01 2013-02-19 Language Weaver, Inc. Providing machine-generated translations and corresponding trust levels
US10417646B2 (en) 2010-03-09 2019-09-17 Sdl Inc. Predicting the cost associated with translating textual content
US10657540B2 (en) 2011-01-29 2020-05-19 Sdl Netherlands B.V. Systems, methods, and media for web content management
US9547626B2 (en) 2011-01-29 2017-01-17 Sdl Plc Systems, methods, and media for managing ambient adaptability of web applications and web services
US10580015B2 (en) 2011-02-25 2020-03-03 Sdl Netherlands B.V. Systems, methods, and media for executing and optimizing online marketing initiatives
US10140320B2 (en) 2011-02-28 2018-11-27 Sdl Inc. Systems, methods, and media for generating analytical data
US11003838B2 (en) 2011-04-18 2021-05-11 Sdl Inc. Systems and methods for monitoring post translation editing
US8694303B2 (en) 2011-06-15 2014-04-08 Language Weaver, Inc. Systems and methods for tuning parameters in statistical machine translation
US9984054B2 (en) 2011-08-24 2018-05-29 Sdl Inc. Web interface including the review and manipulation of a web document and utilizing permission based control
US8886515B2 (en) 2011-10-19 2014-11-11 Language Weaver, Inc. Systems and methods for enhancing machine translation post edit review processes
US8942973B2 (en) 2012-03-09 2015-01-27 Language Weaver, Inc. Content page URL translation
US9773270B2 (en) 2012-05-11 2017-09-26 Fredhopper B.V. Method and system for recommending products based on a ranking cocktail
US10261994B2 (en) 2012-05-25 2019-04-16 Sdl Inc. Method and system for automatic management of reputation of translators
US11308528B2 (en) 2012-09-14 2022-04-19 Sdl Netherlands B.V. Blueprinting of multimedia assets
US10452740B2 (en) 2012-09-14 2019-10-22 Sdl Netherlands B.V. External content libraries
US11386186B2 (en) 2012-09-14 2022-07-12 Sdl Netherlands B.V. External content library connector systems and methods
US9916306B2 (en) 2012-10-19 2018-03-13 Sdl Inc. Statistical linguistic analysis of source content
US9152622B2 (en) 2012-11-26 2015-10-06 Language Weaver, Inc. Personalized machine translation via online adaptation
US9213694B2 (en) 2013-10-10 2015-12-15 Language Weaver, Inc. Efficient online domain adaptation
US10614167B2 (en) 2015-10-30 2020-04-07 Sdl Plc Translation review workflow systems and methods
RU2617329C1 (en) * 2016-03-21 2017-04-24 федеральное государственное автономное образовательное учреждение высшего профессионального образования "Национальный исследовательский ядерный университет МИФИ" (НИЯУ МИФИ) Group structure counter with variable module
US10635863B2 (en) 2017-10-30 2020-04-28 Sdl Inc. Fragment recall and adaptive automated translation
US10817676B2 (en) 2017-12-27 2020-10-27 Sdl Inc. Intelligent routing services and systems
US11256867B2 (en) 2018-10-09 2022-02-22 Sdl Inc. Systems and methods of machine learning for digital assets and message creation

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5477451A (en) * 1991-07-25 1995-12-19 International Business Machines Corp. Method and system for natural language translation
US5867811A (en) * 1993-06-18 1999-02-02 Canon Research Centre Europe Ltd. Method, an apparatus, a system, a storage device, and a computer readable medium using a bilingual database including aligned corpora
US5987404A (en) * 1996-01-29 1999-11-16 International Business Machines Corporation Statistical natural language understanding using hidden clumpings
US6031984A (en) * 1998-03-09 2000-02-29 I2 Technologies, Inc. Method and apparatus for optimizing constraint models
US6182014B1 (en) * 1998-11-20 2001-01-30 Schlumberger Technology Corporation Method and system for optimizing logistical operations in land seismic surveys

Family Cites Families (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS57201958A (en) * 1981-06-05 1982-12-10 Hitachi Ltd Device and method for interpretation between natural languages
JPS58201175A (en) * 1982-05-20 1983-11-22 Kokusai Denshin Denwa Co Ltd <Kdd> Machine translation system
JPS61217871A (en) * 1985-03-25 1986-09-27 Toshiba Corp Translation processor
DE3616751A1 (en) * 1985-05-20 1986-11-20 Sharp K.K., Osaka TRANSLATION SYSTEM
JPH083815B2 (en) * 1985-10-25 1996-01-17 株式会社日立製作所 Natural language co-occurrence relation dictionary maintenance method
US5146405A (en) * 1988-02-05 1992-09-08 At&T Bell Laboratories Methods for part-of-speech determination and usage
JPH0242572A (en) * 1988-08-03 1990-02-13 Hitachi Ltd Preparation/maintenance method for co-occurrence relation dictionary
JPH02301869A (en) * 1989-05-17 1990-12-13 Hitachi Ltd Method for maintaining and supporting natural language processing system
US5212730A (en) * 1991-07-01 1993-05-18 Texas Instruments Incorporated Voice recognition of proper names using text-derived recognition models
US5267156A (en) * 1991-12-05 1993-11-30 International Business Machines Corporation Method for constructing a knowledge base, knowledge base system, machine translation method and system therefor
GB9209346D0 (en) * 1992-04-30 1992-06-17 Sharp Kk Machine translation system
US6278967B1 (en) * 1992-08-31 2001-08-21 Logovista Corporation Automated system for generating natural language translations that are domain-specific, grammar rule-based, and/or based on part-of-speech analysis
US5432948A (en) * 1993-04-26 1995-07-11 Taligent, Inc. Object-oriented rule-based text input transliteration system
US5510981A (en) * 1993-10-28 1996-04-23 International Business Machines Corporation Language translation apparatus and method using context-based translation models
US6304841B1 (en) * 1993-10-28 2001-10-16 International Business Machines Corporation Automatic construction of conditional exponential models from elementary features
US6064819A (en) * 1993-12-08 2000-05-16 Imec Control flow and memory management optimization
JP3377290B2 (en) * 1994-04-27 2003-02-17 シャープ株式会社 Machine translation device with idiom processing function
JP2855409B2 (en) * 1994-11-17 1999-02-10 日本アイ・ビー・エム株式会社 Natural language processing method and system
GB2295470A (en) * 1994-11-28 1996-05-29 Sharp Kk Machine translation system
CA2170669A1 (en) * 1995-03-24 1996-09-25 Fernando Carlos Neves Pereira Grapheme-to phoneme conversion with weighted finite-state transducers
EP0834139A4 (en) * 1995-06-07 1998-08-05 Int Language Engineering Corp Machine assisted translation tools
US5903858A (en) * 1995-06-23 1999-05-11 Saraki; Masashi Translation machine for editing a original text by rewriting the same and translating the rewrote one
JPH09259127A (en) * 1996-03-21 1997-10-03 Sharp Corp Translation device
US5870706A (en) * 1996-04-10 1999-02-09 Lucent Technologies, Inc. Method and apparatus for an improved language recognition system
US6161083A (en) * 1996-05-02 2000-12-12 Sony Corporation Example-based translation method and system which calculates word similarity degrees, a priori probability, and transformation probability to determine the best example for translation
JP3579204B2 (en) * 1997-01-17 2004-10-20 富士通株式会社 Document summarizing apparatus and method
US5991710A (en) * 1997-05-20 1999-11-23 International Business Machines Corporation Statistical translation system with features based on phrases or groups of words
US6415250B1 (en) * 1997-06-18 2002-07-02 Novell, Inc. System and method for identifying language using morphologically-based techniques
US6032111A (en) * 1997-06-23 2000-02-29 At&T Corp. Method and apparatus for compiling context-dependent rewrite rules and input strings
DE69837979T2 (en) * 1997-06-27 2008-03-06 International Business Machines Corp. System for extracting multilingual terminology
JPH11143877A (en) * 1997-10-22 1999-05-28 Internatl Business Mach Corp <Ibm> Compression method, method for compressing entry index data and machine translation system
GB2337611A (en) * 1998-05-20 1999-11-24 Sharp Kk Multilingual document retrieval system
GB2338089A (en) * 1998-06-02 1999-12-08 Sharp Kk Indexing method
US6092034A (en) * 1998-07-27 2000-07-18 International Business Machines Corporation Statistical translation system and method for fast sense disambiguation and translation of large corpora using fertility models and sense models
US6285978B1 (en) * 1998-09-24 2001-09-04 International Business Machines Corporation System and method for estimating accuracy of an automatic natural language translation
JP2000132550A (en) * 1998-10-26 2000-05-12 Matsushita Electric Ind Co Ltd Chinese generating device for machine translation
US6460015B1 (en) * 1998-12-15 2002-10-01 International Business Machines Corporation Method, system and computer program product for automatic character transliteration in a text string object
US6223150B1 (en) * 1999-01-29 2001-04-24 Sony Corporation Method and apparatus for parsing in a spoken language translation system
WO2000062193A1 (en) * 1999-04-08 2000-10-19 Kent Ridge Digital Labs System for chinese tokenization and named entity recognition
US6393389B1 (en) * 1999-09-23 2002-05-21 Xerox Corporation Using ranked translation choices to obtain sequences indicating meaning of multi-token expressions
US6904402B1 (en) * 1999-11-05 2005-06-07 Microsoft Corporation System and iterative method for lexicon, segmentation and language model joint optimization
US6782356B1 (en) * 2000-10-03 2004-08-24 Hewlett-Packard Development Company, L.P. Hierarchical language chunking translation table
US7113903B1 (en) * 2001-01-30 2006-09-26 At&T Corp. Method and apparatus for providing stochastic finite-state machine translation
US7107215B2 (en) * 2001-04-16 2006-09-12 Sakhr Software Company Determining a compact model to transcribe the arabic language acoustically in a well defined basic phonetic study
US7177792B2 (en) * 2001-05-31 2007-02-13 University Of Southern California Integer programming decoder for machine translation
US7191115B2 (en) * 2001-06-20 2007-03-13 Microsoft Corporation Statistical method and apparatus for learning translation relationships among words
US6810374B2 (en) * 2001-07-23 2004-10-26 Pilwon Kang Korean romanization system
ES2343786T3 (en) * 2002-03-27 2010-08-10 University Of Southern California PROBABILITY MODEL OF UNION BASED ON PHRASES FOR STATISTICAL AUTOMATIC TRANSLATION.

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5477451A (en) * 1991-07-25 1995-12-19 International Business Machines Corp. Method and system for natural language translation
US5867811A (en) * 1993-06-18 1999-02-02 Canon Research Centre Europe Ltd. Method, an apparatus, a system, a storage device, and a computer readable medium using a bilingual database including aligned corpora
US5987404A (en) * 1996-01-29 1999-11-16 International Business Machines Corporation Statistical natural language understanding using hidden clumpings
US6031984A (en) * 1998-03-09 2000-02-29 I2 Technologies, Inc. Method and apparatus for optimizing constraint models
US6182014B1 (en) * 1998-11-20 2001-01-30 Schlumberger Technology Corporation Method and system for optimizing logistical operations in land seismic surveys

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011028754A (en) * 2009-07-27 2011-02-10 Xerox Corp Phrase-based statistical machine translation as generalized traveling sales person problem

Also Published As

Publication number Publication date
US20060195312A1 (en) 2006-08-31
US7177792B2 (en) 2007-02-13
US20020188438A1 (en) 2002-12-12

Similar Documents

Publication Publication Date Title
US7177792B2 (en) Integer programming decoder for machine translation
ES2228408T3 (en) METHOD AND ANALYZING APPLIANCE OF THE NATURAL LANGUAGE.
US5987404A (en) Statistical natural language understanding using hidden clumpings
CN110399162A (en) A kind of source code annotation automatic generation method
JP2005115922A (en) Method and apparatus for identifying semantic structure from text
WO2006133538A1 (en) System and method for ranking web content
Le et al. Improving sequence to sequence neural machine translation by utilizing syntactic dependency information
CN103189860A (en) Machine translation device and machine translation method in which a syntax conversion model and a vocabulary conversion model are combined
CN110287336A (en) A kind of tourist&#39;s portrait construction method recommended towards tourist attractions
Goldberg et al. A single generative model for joint morphological segmentation and syntactic parsing
Yang et al. xMoCo: Cross momentum contrastive learning for open-domain question answering
Giegerich Introduction to stochastic context free grammars
JP5980520B2 (en) Method and apparatus for efficiently processing a query
Jhunjhunwala et al. Multi-action dialog policy learning with interactive human teaching
Schneck et al. Accelerating traffic assignment with customizable contraction hierarchies
CN113343692B (en) Search intention recognition method, model training method, device, medium and equipment
CN114913938A (en) Small molecule generation method, equipment and medium based on pharmacophore model
CN101470701A (en) Text analyzer supporting semantic rule based on finite state machine and method thereof
US8583460B2 (en) Pricing tickets based on constructing tables of pricing units for sub-portions of a ticket
Hockenmaier et al. Routes are trees: the parsing perspective on protein folding
Köppl Non-overlapping LZ77 factorization and LZ78 substring compression queries with suffix trees
Tsujii Computational linguistics and natural language processing
Maqbool et al. Zero-label anaphora resolution for off-script user queries in goal-oriented dialog systems
CN110188355A (en) A kind of segmenting method based on WFST technology, system, equipment and medium
Zollmann Learning multiple-nonterminal synchronous grammars for statistical machine translation

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG US UZ VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
REG Reference to national code

Ref country code: DE

Ref legal event code: 8642

122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP