Title: Automatic Rule Learning for ResourceLimited Machine Translation
1Automatic Rule Learning for Resource-Limited
Machine Translation
- Faculty
- Alon Lavie, Jaime Carbonell, Lori Levin,
- Ralf Brown
-
- Students
- Katharina Probst, Erik Peterson,
- Christian Monson, Ariadna Font-Llitjos,
- Rachel Reynolds, Alison Alvarez
2Transfer with Strong Decoding
3Transfer Rule Formalism
SL the old man, TL ha-ish ha-zaqen NPNP
DET ADJ N -gt DET N DET ADJ ( (X1Y1) (X1Y3)
(X2Y4) (X3Y2) ((X1 AGR) 3-SING) ((X1 DEF
DEF) ((X3 AGR) 3-SING) ((X3 COUNT)
) ((Y1 DEF) DEF) ((Y3 DEF) DEF) ((Y2 AGR)
3-SING) ((Y2 GENDER) (Y4 GENDER)) )
- Type information
- Part-of-speech/constituent information
- Alignments
- x-side constraints
- y-side constraints
- xy-constraints,
- e.g. ((Y1 AGR) (X1 AGR))
4The Transfer Engine
5Rule Learning - Overview
- Goal Acquire Syntactic Transfer Rules
- Use available knowledge from the source side
(grammatical structure) - Three steps
- Flat Seed Generation first guesses at transfer
rules flat syntactic structure - Compositionality use previously learned rules to
add hierarchical structure - Seeded Version Space Learning refine rules by
learning appropriate feature constraints
6Flat Seed Rule Generation
7Flat Seed Generation
- Create a transfer rule that is specific to the
sentence pair, but abstracted to the POS level.
No syntactic structure.
8Compositionality
9Compositionality - Overview
- Traverse the c-structure of the English sentence,
add compositional structure for translatable
chunks - Adjust constituent sequences, alignments
- Remove unnecessary constraints, i.e. those that
are contained in the lower-level rule
10Seeded Version Space Learning
11Seeded Version Space Learning Overview
- Goal add appropriate feature constraints to the
acquired rules - Methodology
- Preserve general structural transfer
- Learn specific feature constraints from example
set - Seed rules are grouped into clusters of similar
transfer structure (type, constituent sequences,
alignments) - Each cluster forms a version space a partially
ordered hypothesis space with a specific and a
general boundary - The seed rules in a group form the specific
boundary of a version space - The general boundary is the (implicit) transfer
rule with the same type, constituent sequences,
and alignments, but no feature constraints -
12Seeded Version Space Learning Generalization
- The partial order of the version space
- Definition A transfer rule tr1 is strictly more
general than another transfer rule tr2 if all
f-structures that are satisfied by tr2 are also
satisfied by tr1. - Generalize rules by merging them
- Deletion of constraint
- Raising two value constraints to an agreement
constraint, e.g. - ((x1 num) pl), ((x3 num) pl) ?
- ((x1 num) (x3 num))
13Seeded Version Space Learning
-
-
- NP v det n NP VP
- Group seed rules into version spaces as above.
- Make use of partial order of rules in version
space. Partial order is defined - via the f-structures satisfying the constraints.
- Generalize in the space by repeated merging of
rules - Deletion of constraint
- Moving value constraints to agreement
constraints, e.g. - ((x1 num) pl), ((x3 num) pl) ?
- ((x1 num) (x3 num)
- 4. Check translation power of generalized rules
against sentence pairs
14Seeded Version Space LearningThe Search
- The Seeded Version Space algorithm itself is the
repeated generalization of rules by merging - A merge is successful if the set of sentences
that can correctly be translated with the merged
rule is a superset of the union of sets that can
be translated with the unmerged rules, i.e. check
power of rule - Merge until no more successful merges
15Seeded VSL Some Open Issues
- Three types of constraints
- X-side constrain applicability of rule
- Y-side assist in generation
- X-Y transfer features from SL to TL
- Which of the three types improves translation
performance? - Use rules without features to populate lattice,
decoder will select the best translation - Learn only X-Y constraints, based on list of
universal projecting features - Other notions of version-spaces of feature
constraints - Current feature learning is specific to rules
that have identical transfer components - Important issue during transfer is to
disambiguate among rules that have same SL side
but different TL side can we learn effective
constraints for this?
16Examples of Learned Rules
17Manual Transfer Rules Example
PASSIVE OF SIMPLE PAST (NO AUX) WITH LIGHT
VERB passive of 43 (7b) VP,28 VPVP V V
V -gt Aux V ( (X1Y2) ((x1 form) root)
((x2 type) c light) ((x2 form) part) ((x2
aspect) perf) ((x3 lexwx) 'jAnA') ((x3
form) part) ((x3 aspect) perf) (x0 x1)
((y1 lex) be) ((y1 tense) past) ((y1 agr
num) (x3 agr num)) ((y1 agr pers) (x3 agr
pers)) ((y2 form) part) )
18Manual Transfer Rules Example
NP PP NP1 NP P Adj N
N1 ke eka aXyAya N
jIvana
NP NP1 PP Adj N
P NP one chapter of N1
N life
NP1 ke NP2 -gt NP2 of NP1 Ex jIvana ke
eka aXyAya life of (one) chapter
gt a chapter of life NP,12 NPNP PP
NP1 -gt NP1 PP ( (X1Y2) (X2Y1) ((x2
lexwx) 'kA') ) NP,13 NPNP NP1 -gt
NP1 ( (X1Y1) ) PP,12 PPPP NP Postp
-gt Prep NP ( (X1Y2) (X2Y1) )
19A Limited Data Scenario for Hindi-to-English
- Put together a scenario with miserly data
resources - Elicited Data corpus 17589 phrases
- Cleaned portion (top 12) of LDC dictionary
2725 Hindi words (23612 translation pairs) - Manually acquired resources during the SLE
- 500 manual bigram translations
- 72 manually written phrase transfer rules
- 105 manually written postposition rules
- 48 manually written time expression rules
- No additional parallel text!!
20Manual Grammar Development
- Covers mostly NPs, PPs and VPs (verb complexes)
- 70 grammar rules, covering basic and recursive
NPs and PPs, verb complexes of main tenses in
Hindi (developed in two weeks)
21Adding a Strong Decoder
- XFER system produces a full lattice
- Edges are scored using word-to-word translation
probabilities, trained from the limited bilingual
data - Decoder uses an English LM (70m words)
- Decoder can also reorder words or phrases (up to
4 positions ahead) - For XFER(strong) , ONLY edges from basic XFER
system are used!
22Testing Conditions
- Tested on section of JHU provided data 258
sentences with four reference translations - SMT system (stand-alone)
- EBMT system (stand-alone)
- XFER system (naïve decoding)
- XFER system with strong decoder
- No grammar rules (baseline)
- Manually developed grammar rules
- Automatically learned grammar rules
- XFERSMT with strong decoder (MEMT)
23Results on JHU Test Set (very miserly training
data)
24Effect of Reordering in the Decoder
25Observations and Lessons (I)
- XFER with strong decoder outperformed SMT even
without any grammar rules in the miserly data
scenario - SMT Trained on elicited phrases that are very
short - SMT has insufficient data to train more
discriminative translation probabilities - XFER takes advantage of Morphology
- Token coverage without morphology 0.6989
- Token coverage with morphology 0.7892
- Manual grammar currently somewhat better than
automatically learned grammar - Learned rules did not yet use version-space
learning - Large room for improvement on learning rules
- Importance of effective well-founded scoring of
learned rules
26Observations and Lessons (II)
- MEMT (XFER and SMT) based on strong decoder
produced best results in the miserly scenario. - Reordering within the decoder provided very
significant score improvements - Much room for more sophisticated grammar rules
- Strong decoder can carry some of the reordering
burden
27Conclusions
- Transfer rules (both manual and learned) offer
significant contributions that can complement
existing data-driven approaches - Also in medium and large data settings?
- Initial steps to development of a statistically
grounded transfer-based MT system with - Rules that are scored based on a well-founded
probability model - Strong and effective decoding that incorporates
the most advanced techniques used in SMT decoding - Working from the opposite end of research on
incorporating models of syntax into standard
SMT systems Knight et al - Our direction makes sense in the limited data
scenario
28Future Directions
- Continued work on automatic rule learning
(especially Seeded Version Space Learning) - Improved leveraging from manual grammar
resources, interaction with bilingual speakers - Developing a well-founded model for assigning
scores (probabilities) to transfer rules - Improving the strong decoder to better fit the
specific characteristics of the XFER model - MEMT with improved
- Combination of output from different translation
engines with different scorings - strong decoding capabilities
29Flat Seed Generation - Example
- The highly qualified applicant did not accept the
offer. - Der äußerst qualifizierte Bewerber nahm das
Angebot nicht an. - ((1,1),(2,2),(3,3),(4,4),(6,8),(7,5),(7,9),(8,6),(
9,7))
SS det adv adj n aux neg v det n -gt det adv
adj n v det n neg vpart (alignments (x1y1)(x2
y2)(x3y3)(x4y4)(x6y8)(x7y5)(x7y9)(x8
y6)(x9y7)) constraints ((x1 def) ) ((x4
agr) 3-sing) ((x5 tense) past) . ((y1
def) ) ((y3 case) nom) ((y4 agr)
3-sing) . )
30Compositionality - Example
SS det adv adj n aux neg v det n -gt det adv
adj n v det n neg vpart (alignments (x1y1)(x2
y2)(x3y3)(x4y4)(x6y8)(x7y5)(x7y9)(x8
y6)(x9y7)) constraints ((x1 def) ) ((x4
agr) 3-sing) ((x5 tense) past) . ((y1
def) ) ((y3 case) nom) ((y4 agr)
3-sing) . )
NPNP det AJDP n -gt det ADJP
n ((x1y1) ((y3 agr) 3-sing) ((x3 agr
3-sing) .)
SS NP aux neg v det n -gt NP v det n neg
vpart (alignments (x1y1)(x3y5)(x4y2)(x4
y6)(x5y3)(x6y4) constraints ((x2 tense)
past) . ((y1 def) ) ((y1 case) nom) .
)
31Seeded Version Space Learning Example
SS NP aux neg v det n -gt NP v det n neg
vpart (alignments (x1y1)(x3y5)(x4y2)(x4
y6)(x5y3)(x6y4) constraints ((x2 tense)
past) . ((y1 def) ) ((y1 case) nom)
((y1 agr) 3-sing) ) ((y3 agr) 3-sing)
((y4 agr) 3-sing) )
SS NP aux neg v det n -gt NP n det n neg
vpart ( alignments (x1y1)(x3y5) (x4y2)(x
4y6) (x5y3)(x6y4) constraints ((x2
tense) past) ((y1 def) ) ((y1 case)
nom) ((y4 agr) (y3 agr)) )
SS NP aux neg v det n -gt NP v det n neg
vpart (alignments (x1y1)(x3y5)(x4y2)(x4
y6)(x5y3)(x6y4) constraints ((x2 tense)
past) ((y1 def) ) ((y1 case) nom) ((y1
agr) 3-plu) ((y3 agr) 3-plu) ((y4 agr)
3-plu) )
32Preliminary Evaluation
- English to German
- Corpus of 141 ADJPs, simple NPs and sentences
- 10-fold cross-validation experiment
- Goals
- Do we learn useful transfer rules?
- Does Compositionality improve generalization?
- Does VS-learning improve generalization?
33Summary of Results
- Average translation accuracy on cross-validation
test set was 62 - Without VS-learning 43
- Without Compositionality 57
- Average number of VSs 24
- Average number of sents per VS 3.8
- Average number of merges per VS 1.6
- Percent of compositional rules 34
34Conclusions
- New paradigm for learning transfer rules from
pre-designed elicitation corpus - Geared toward languages with very limited
resources - Preliminary experiments validate approach
compositionality and VS-learning improve
generalization
35Future Work
- Larger, more diverse elicitation corpus
- Additional languages (Mapudungun)
- Less information on TL side
- Reverse translation direction
- Refine the various algorithms
- Operators for VS generalization
- Generalization VS search
- Layers for compositionality
- User interactive verification
36Why Machine Translation for Minority and
Indigenous Languages?
- Commercial MT economically feasible for only a
handful of major languages with large resources
(corpora, human developers) - Is there hope for MT for languages with limited
resources? - Benefits include
- Better government access to indigenous
communities (Epidemics, crop failures, etc.) - Better indigenous communities participation in
information-rich activities (health care,
education, government) without giving up their
languages. - Language preservation
- Civilian and military applications (disaster
relief)
37MT for Minority and Indigenous Languages
Challenges
- Minimal amount of parallel text
- Possibly competing standards for
orthography/spelling - Often relatively few trained linguists
- Access to native informants possible
- Need to minimize development time and cost
38Transfer Rule Formalism (II)
SL the old man, TL ha-ish ha-zaqen NPNP
DET ADJ N -gt DET N DET ADJ ( (X1Y1) (X1Y3)
(X2Y4) (X3Y2) ((X1 AGR) 3-SING) ((X1 DEF
DEF) ((X3 AGR) 3-SING) ((X3 COUNT)
) ((Y1 DEF) DEF) ((Y3 DEF) DEF) ((Y2 AGR)
3-SING) ((Y2 GENDER) (Y4 GENDER)) )
- Value constraints
-
- Agreement constraints