---
title: "Improving word alignment for low resource languages using"
description: "The paper addresses weak word alignment in statistical MT when little parallel data exists. 46 references, cited by 3 papers here."
authors: ["Meriem Beloucif", "Markus Saers", "Dekai Wu"]
year: 2016
venue: "Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)"
source: "https://aclanthology.org/W16-4507/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/beloucif-2016-improving-word-alignment-low-resource/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/beloucif-2016-improving-word-alignment-low-resource/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/4/) / Improving word alignment for low resource languages using English monolingual SRL

# Improving word alignment for low resource languages using English monolingual SRL

**Authors:** [Meriem Beloucif](https://md.research.elamur.ai/free/en/authors/meriem-beloucif/), Markus Saers and [Dekai Wu](https://md.research.elamur.ai/free/en/authors/dekai-wu/) · **Year:** 2016 · **Venue:** Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6) · **Publisher:** [International Committee on Computational Linguistics (ICCL)](https://md.research.elamur.ai/free/en/publishers/international-committee-on-computational-linguistics-iccl/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W16-4507/) · [PDF](https://aclanthology.org/W16-4507.pdf) · [OpenAlex](https://openalex.org/W2736168741)

**Citations:** 2 citations (OpenAlex, 2026-10-14) · 3 in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper addresses weak word alignment in statistical MT when little parallel data exists. Standard aligners such as GIZA++ (IBM/HMM models) and plain ITG learners depend largely on memorizing frequent patterns, which fails when data is sparse. The authors bias bracketing ITG (BITG) induction with semantic role structure from the English side only. A monolingual English semantic frame parse, together with translation lexicons, adds a penalty to the alignment learning objective. The method therefore needs no SRL tool for the low resource input language. The idea is to bring a semantic signal into the early learning of the translation model, not just into late tuning of log-linear weights against MEANT. The authors tested the method on Chinese, Hausa and Uzbek data from the DARPA LORELEI program, always translating into English. They tuned the penalty weight on Chinese and Hausa and then evaluated on Uzbek. Alignments from the SRL-biased model gave a MOSES system that beat both BITG and GIZA++ alignments on BLEU, METEOR, TER, WER, PER and CDER. This suggests the approach generalizes from modest data.

## Key points
- Training data sizes in sentence pairs:
  - Uzbek: 148,190.
  - Hausa: 76,910.
  - Chinese: 39,953.
  - Development and test sets each have roughly 500–1,500 pairs.
- The baseline is a token-based BITG with a single nonterminal.
  - Lexical rules start from co-occurrence counts.
  - The structural rules start uniform.
  - The proposed model is trained with 10 EM iterations, and alignments are extracted by Viterbi parsing.
  - GIZA++ uses grow-diag-final-and symmetrization.
- Downstream pipeline:
  - MOSES phrase-based SMT.
  - A 4-gram SRILM language model trained on each language's own training data.
  - k-best MIRA tuning.
- A semantic error-penalty weight was swept over 0 to 0.9. A weight of 0.6 gave the best BLEU for both Chinese (17.06 cased) and Hausa (17.44 cased).
- Uzbek-English test results (cased BLEU / TER):

  | Alignment | BLEU | TER |
  |---|---|---|
  | GIZA++ | 16.28 | 82.20 |
  | BITG | 16.85 | 79.75 |
  | Proposed | 17.40 | 79.25 |

  The proposed model also improved METEOR to 41.0.

## Interesting ideas
- Supervise a cross-lingual mapping using structure available only on the well-resourced side: English frames constrain alignment, so the weak language needs no parser of its own.
- Put the meaning-level objective into the actual structure learning instead of only reranking or retuning at the end, since late tuning barely changes what the model has learned.
- Prefer a restricted hypothesis space that still covers the real phenomena; ITG orderings are cited as covering crosslingual frame alternations while excluding most wrong alignments.
- Tune a single penalty weight on some languages and report the final result on a different, held-out language. This tests whether the setting transfers instead of overfitting to one set.
- Inspect outputs qualitatively for meaning errors that surface metrics hide, such as the baseline calling the male minister "she".

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (back): When translating through the meta-world, Mova's English frames could act as the fixed target that constrains how foreign-language spans are aligned to roles. This would avoid any need for a foreign parser.
- **I2** (learn): Frame-level agreement, such as matching who-did-what-to-whom against silver frames, could become a training signal for the parser itself. It would then do more than filter outputs after training.
- **I3** (tree): Parser search could be restricted to analyses whose subtrees can carry a coherent VerbNet frame, pruning junk attachments while keeping legitimate role reorderings.
- **I4** (learn): Hyperparameters for repair rules or witness voting could be tuned on one genre, such as school tests, and evaluated on another, such as fables, as a transfer check.
- **I5** (back): Generated text could be checked automatically for entity-attribute consistency against the world model, for example by verifying that pronoun gender matches the entity's known properties.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Hong Kong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/hong-kong-university-of-science-and-technology/) — University, Hong Kong, China · 58 works · 23,058 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (4): [🔁 Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) · 958 works · [English](https://md.research.elamur.ai/free/en/topics/english/) · 1,373 works · [🎭 Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · 132 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 165 works

## Cite

Cite as: Meriem Beloucif, Markus Saers and Dekai Wu. 2016. Improving word alignment for low resource languages using English monolingual SRL. Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{beloucif2016improving,
  title = {{Improving word alignment for low resource languages using English monolingual SRL}},
  author = {Meriem Beloucif, Markus Saers and Dekai Wu},
  booktitle = {Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)},
  year = {2016},
  url = {https://aclanthology.org/W16-4507/}
}
```

- [← previous Evaluation Strategies for Computational Construction Grammars](https://md.research.elamur.ai/free/en/papers/marques-2016-evaluation-strategies-computational-construction-grammars/)
- [next → Merged bilingual trees based on Universal Dependencies in Machine Translation](https://md.research.elamur.ai/free/en/papers/marecek-2016-merged-bilingual-trees-based-universal/)
- [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/4/)

## References

46 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Karteek Addanki, Chi-kiu Lo, Markus Saers, and Dekai Wu. LTG vs. ITG coverage of cross-lingual verb frame alternations. In 16th Annual Conference of the European Association for Machine Translation (EAMT-2012), Trento, Italy, May 2012. [find](https://scholar.google.com/scholar?q=Karteek+Addanki%2C+Chi%2Dkiu+Lo%2C+Markus+Saers%2C+and+Dekai+Wu%2E+LTG+vs%2E+ITG+coverage+of+cross%2Dlingual+verb+frame+alternations%2E+In+16th+Annual+Conference+of+the+European+Association+for+Machine+Translation+%28E)
2. Alfred V. Aho and Jeffrey D. Ullman. The Theory of Parsing, Translation, and Compiling. Prentice-Halll, Englewood Cliffs, New Jersey, 1972. [find](https://scholar.google.com/scholar?q=Alfred+V%2E+Aho+and+Jeffrey+D%2E+Ullman%2E+The+Theory+of+Parsing%2C+Translation%2C+and+Compiling%2E+Prentice%2DHalll%2C+Englewood+Cliffs%2C+New+Jersey%2C+1972%2E)
3. Satanjeev Banerjee and Alon Lavie. [METEOR: An automatic metric for MT evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, Ann Arbor, Michigan, June 2005.
4. Meriem Beloucif, Chi kiu Lo, and Dekai Wu. Improving meant based semantically tuned smt. In 11 th International Workshop on spoken Language Translation (IWSLT 2014), 34-41 Lake Tahoe, California, 2014. [find](https://scholar.google.com/scholar?q=Meriem+Beloucif%2C+Chi+kiu+Lo%2C+and+Dekai+Wu%2E+Improving+meant+based+semantically+tuned+smt%2E+In+11+th+International+Workshop+on+spoken+Language+Translation+%28IWSLT+2014%29%2C+34%2D41+Lake+Tahoe%2C+California%2C+2014)
5. Meriem Beloucif, Markus Saers, and Dekai Wu. Improving semantic smt via soft semantic role label constraints on itg alignments. In Machine Translation Summit XV (MT Summit 2015), pages 333–345, Miami, USA, October 2015. [find](https://scholar.google.com/scholar?q=Meriem+Beloucif%2C+Markus+Saers%2C+and+Dekai+Wu%2E+Improving+semantic+smt+via+soft+semantic+role+label+constraints+on+itg+alignments%2E+In+Machine+Translation+Summit+XV+%28MT+Summit+2015%29%2C+pages+333%E2%80%93345%2C+Miami%2C)
6. Phil Blunsom, Trevor Cohn, Chris Dyer, and Miles Osborne. A Gibbs sampler for phrasal synchronous grammar induction. In Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009), pages 782–790, Suntec, Singapore, August 2009. [find](https://scholar.google.com/scholar?q=Phil+Blunsom%2C+Trevor+Cohn%2C+Chris+Dyer%2C+and+Miles+Osborne%2E+A+Gibbs+sampler+for+phrasal+synchronous+grammar+induction%2E+In+Joint+Conference+of+the+47th+Annual+Meeting+of+the+Association+for+Computational)
7. Peter F. Brown, John Cocke, Stephen A. Della Pietra, Vincent J. Della Pietra, Frederik Jelinek, John D. Lafferty, Robert L. Mercer, and Paul S. Roossin. A statistical approach to machine translation. Computational Linguistics, 16(2):79–85, 1990. [↗](https://doi.org/10.5555/92858.92860)
8. Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. The mathematics of machine translation: Parameter estimation. Computational Linguistics, 19(2):263–311, 1993. [find](https://scholar.google.com/scholar?q=Peter+F%2E+Brown%2C+Stephen+A%2E+Della+Pietra%2C+Vincent+J%2E+Della+Pietra%2C+and+Robert+L%2E+Mercer%2E+The+mathematics+of+machine+translation%3A+Parameter+estimation%2E+Computational+Linguistics%2C+19%282%29%3A263%E2%80%93311%2C+1993%2E)
9. Colin Cherry and George Foster. [Batch tuning strategies for statistical machine translation](https://md.research.elamur.ai/free/en/papers/cherry-2012-batch-tuning-strategies-statistical-machine/). In Proceedings of the 2012 Conference of the North American Chapter of the ACL: Human Language Technologies. Association for Computational Linguistics, 2012.
10. Colin Cherry and Dekang Lin. Inversion transduction grammar for joint phrasal translation modeling. In Syntax and Structure in Statistical Translation (SSST), pages 17–24, Rochester, New York, April 2007. [find](https://scholar.google.com/scholar?q=Colin+Cherry+and+Dekang+Lin%2E+Inversion+transduction+grammar+for+joint+phrasal+translation+modeling%2E+In+Syntax+and+Structure+in+Statistical+Translation+%28SSST%29%2C+pages+17%E2%80%9324%2C+Rochester%2C+New+York%2C+April+2)
11. David Chiang. [Hierarchical phrase-based translation](https://md.research.elamur.ai/free/en/papers/chiang-2007-hierarchical-phrase-based-translation/). Computational Linguistics, 33(2):201–228, 2007. [↗](https://doi.org/10.1162/coli.2007.33.2.201)
12. David Chiang. Hope and fear for discriminative training of statistical translation models. The Journal of Machine Learning Research, 13:1159–1187, April 2012. [find](https://scholar.google.com/scholar?q=David+Chiang%2E+Hope+and+fear+for+discriminative+training+of+statistical+translation+models%2E+The+Journal+of+Machine+Learning+Research%2C+13%3A1159%E2%80%931187%2C+April+2012%2E)
13. Adrià De Gispert, Deepa Gupta, Maja Popovic, Patrik Lambert, Jose B.Marino, Marcello Federico, Hermann Ney, and Rafael Banchs. Improving statistical word alignment with morpho-syntactic transformations. In Advances in Natural Language Processing, pages 368–379, 2006. [find](https://scholar.google.com/scholar?q=Adri%C3%A0+De+Gispert%2C+Deepa+Gupta%2C+Maja+Popovic%2C+Patrik+Lambert%2C+Jose+B%2EMarino%2C+Marcello+Federico%2C+Hermann+Ney%2C+and+Rafael+Banchs%2E+Improving+statistical+word+alignment+with+morpho%2Dsyntactic+transformation)
14. George Doddington. Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In The second international conference on Human Language Technology Research (HLT ’02), San Diego, California, 2002. [find](https://scholar.google.com/scholar?q=George+Doddington%2E+Automatic+evaluation+of+machine+translation+quality+using+n%2Dgram+co%2Doccurrence+statistics%2E+In+The+second+international+conference+on+Human+Language+Technology+Research+%28HLT+%E2%80%9902%29%2C+Sa)
15. Chris Dyer, Jonathan Clark, Alon Lavie, and Noah A.Smith. Unsupervised word alignment with arbitrary features. In 49th Annual Meeting of the Association for Computational Linguistics, 2011. [find](https://scholar.google.com/scholar?q=Chris+Dyer%2C+Jonathan+Clark%2C+Alon+Lavie%2C+and+Noah+A%2ESmith%2E+Unsupervised+word+alignment+with+arbitrary+features%2E+In+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+2011%2E)
16. Daniel Gildea and Daniel Jurafsky. [Automatic labeling of semantic roles](https://md.research.elamur.ai/free/en/papers/gildea-2002-automatic-labeling-semantic-roles/). Computational Linguistics, 28(3):245–288, 2002. [↗](https://doi.org/10.1162/089120102760275983)
17. Aria Haghighi, John Blitzer, John DeNero, and Dan Klein. [Better word alignments with supervised ITG models](https://md.research.elamur.ai/free/en/papers/haghighi-2009-better-word-alignments-supervised-itg/). In Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009), pages 923–931, Suntec, Singapore, August 2009.
18. Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. Moses: Open source toolkit for statistical machine translation. In Interactive Poster and Demonstration Sessions of the 45th Annual Meeting of the Association for Computational Linguistics (ACL 2007), pages 177–180, Prague, Czech Republic, June 2007. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2C+Hieu+Hoang%2C+Alexandra+Birch%2C+Chris+Callison%2DBurch%2C+Marcello+Federico%2C+Nicola+Bertoldi%2C+Brooke+Cowan%2C+Wade+Shen%2C+Christine+Moran%2C+Richard+Zens%2C+Chris+Dyer%2C+Ondrej+Bojar%2C+Alexandra+Consta)
19. Gregor Leusch, Nicola Ueffing, and Hermann Ney. [CDer: Efficient MT evaluation using block movements](https://md.research.elamur.ai/free/en/papers/leusch-2006-cder-efficient-mt-evaluation-block/). In 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2006), 2006.
20. Philip M. Lewis and Richard E. Stearns. Syntax-directed transduction. Journal of the Association for Computing Machinery, 15(3):465–488, 1968. [↗](https://doi.org/10.1145/321466.321477)
21. Chi-kiu Lo and Dekai Wu. [MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility based on semantic roles](https://md.research.elamur.ai/free/en/papers/lo-2011-meant-inexpensive-high-accuracy-semi/). In 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL HLT 2011), 2011.
22. Chi-kiu Lo and Dekai Wu. Unsupervised vs. supervised weight estimation for semantic MT evaluation metrics. In Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-6), 2012. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo+and+Dekai+Wu%2E+Unsupervised+vs%2E+supervised+weight+estimation+for+semantic+MT+evaluation+metrics%2E+In+Sixth+Workshop+on+Syntax%2C+Semantics+and+Structure+in+Statistical+Translation+%28SSST%2D6%29%2C+201)
23. Chi-kiu Lo and Dekai Wu. Can informal genres be better translated by tuning on automatic semantic metrics? In 14th Machine Translation Summit (MT Summit XIV), 2013. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo+and+Dekai+Wu%2E+Can+informal+genres+be+better+translated+by+tuning+on+automatic+semantic+metrics%3F+In+14th+Machine+Translation+Summit+%28MT+Summit+XIV%29%2C+2013%2E)
24. Chi-kiu Lo and Dekai Wu. MEANT at WMT 2013: A tunable, accurate yet inexpensive semantic frame based mt evaluation metric. In 8th Workshop on Statistical Machine Translation (WMT 2013), 2013. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo+and+Dekai+Wu%2E+MEANT+at+WMT+2013%3A+A+tunable%2C+accurate+yet+inexpensive+semantic+frame+based+mt+evaluation+metric%2E+In+8th+Workshop+on+Statistical+Machine+Translation+%28WMT+2013%29%2C+2013%2E)
25. Chi-kiu Lo, Anand Karthik Tumuluru, and Dekai Wu. Fully automatic semantic MT evaluation. In 7th Workshop on Statistical Machine Translation (WMT 2012), 2012. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo%2C+Anand+Karthik+Tumuluru%2C+and+Dekai+Wu%2E+Fully+automatic+semantic+MT+evaluation%2E+In+7th+Workshop+on+Statistical+Machine+Translation+%28WMT+2012%29%2C+2012%2E)
26. Chi-kiu Lo, Karteek Addanki, Markus Saers, and Dekai Wu. Improving machine translation by training against an automatic semantic frame based evaluation metric. In 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), 2013. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo%2C+Karteek+Addanki%2C+Markus+Saers%2C+and+Dekai+Wu%2E+Improving+machine+translation+by+training+against+an+automatic+semantic+frame+based+evaluation+metric%2E+In+51st+Annual+Meeting+of+the+Associatio)
27. Chi-kiu Lo, Meriem Beloucif, and Dekai Wu. Improving machine translation into Chinese by tuning against Chinese MEANT. In International Workshop on Spoken Language Translation (IWSLT 2013), 2013. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo%2C+Meriem+Beloucif%2C+and+Dekai+Wu%2E+Improving+machine+translation+into+Chinese+by+tuning+against+Chinese+MEANT%2E+In+International+Workshop+on+Spoken+Language+Translation+%28IWSLT+2013%29%2C+2013%2E)
28. Jeff Ma, Spyros Matsoukas, and Richard Schwartz. Improving low-resource statistical machine translation with a novel semantic word clustering algorithm. In Proceedings of the MT Summit XIII, 2011. [find](https://scholar.google.com/scholar?q=Jeff+Ma%2C+Spyros+Matsoukas%2C+and+Richard+Schwartz%2E+Improving+low%2Dresource+statistical+machine+translation+with+a+novel+semantic+word+clustering+algorithm%2E+In+Proceedings+of+the+MT+Summit+XIII%2C+2011%2E)
29. Matouš Macháček and Ondřej Bojar. Results of the WMT13 metrics shared task. In Eighth Workshop on Statistical Machine Translation (WMT 2013), Sofia, Bulgaria, August 2013. [find](https://scholar.google.com/scholar?q=Matou%C5%A1+Mach%C3%A1%C4%8Dek+and+Ond%C5%99ej+Bojar%2E+Results+of+the+WMT13+metrics+shared+task%2E+In+Eighth+Workshop+on+Statistical+Machine+Translation+%28WMT+2013%29%2C+Sofia%2C+Bulgaria%2C+August+2013%2E)
30. Graham Neubig, Taro Watanabe, Eiichiro Sumita, Shinsuke Mori, and Tatsuya Kawahara. An unsupervised model for joint phrase alignment and extraction. In 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL HLT 2011), pages 632–641, Portland, Oregon, June 2011. [find](https://scholar.google.com/scholar?q=Graham+Neubig%2C+Taro+Watanabe%2C+Eiichiro+Sumita%2C+Shinsuke+Mori%2C+and+Tatsuya+Kawahara%2E+An+unsupervised+model+for+joint+phrase+alignment+and+extraction%2E+In+49th+Annual+Meeting+of+the+Association+for+Compu)
31. Sonja Nießen, Franz Josef Och, Gregor Leusch, and Hermann Ney. A evaluation tool for machine translation: Fast evaluation for MT research. In The Second International Conference on Language Resources and Evaluation (LREC 2000), 2000. [find](https://scholar.google.com/scholar?q=Sonja+Nie%C3%9Fen%2C+Franz+Josef+Och%2C+Gregor+Leusch%2C+and+Hermann+Ney%2E+A+evaluation+tool+for+machine+translation%3A+Fast+evaluation+for+MT+research%2E+In+The+Second+International+Conference+on+Language+Resources+)
32. Franz Josef Och and Hermann Ney. [Improved statistical alignment models](https://md.research.elamur.ai/free/en/papers/och-2000-improved-statistical-alignment-models/). In The 38th Annual Meeting of the Association for Computational Linguistics (ACL 2000), pages 440–447, Hong Kong, October 2000.
33. Martha Palmer, Daniel Gildea, and Paul Kingsbury. [The proposition bank: an annotated corpus of semantic roles](https://md.research.elamur.ai/free/en/papers/palmer-2005-proposition-bank-annotated-corpus-semantic/). Computational Linguistics, 31(1):71–106, 2005. [↗](https://doi.org/10.1162/0891201053630264)
34. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. [BLEU: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In 40th Annual Meeting of the Association for Computational Linguistics (ACL-02), pages 311–318, Philadelphia, Pennsylvania, July 2002.
35. Sameer Pradhan, Wayne Ward, Kadri Hacioglu, James H. Martin, and Dan Jurafsky. [Shallow semantic parsing using support vector machines](https://md.research.elamur.ai/free/en/papers/pradhan-2004-shallow-semantic-parsing-support-vector/). In Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2004), 2004.
36. Markus Saers and Dekai Wu. Improving phrase-based translation via word alignments from stochastic inversion transduction grammars. In Third Workshop on Syntax and Structure in Statistical Translation (SSST-3), pages 28–36, Boulder, Colorado, June 2009. [find](https://scholar.google.com/scholar?q=Markus+Saers+and+Dekai+Wu%2E+Improving+phrase%2Dbased+translation+via+word+alignments+from+stochastic+inversion+transduction+grammars%2E+In+Third+Workshop+on+Syntax+and+Structure+in+Statistical+Translation+)
37. Markus Saers, Joakim Nivre, and Dekai Wu. Learning stochastic bracketing inversion transduction grammars with a cubic time biparsing algorithm. In 11th International Conference on Parsing Technologies (IWPT’09), pages 29–32, Paris, France, October 2009. [find](https://scholar.google.com/scholar?q=Markus+Saers%2C+Joakim+Nivre%2C+and+Dekai+Wu%2E+Learning+stochastic+bracketing+inversion+transduction+grammars+with+a+cubic+time+biparsing+algorithm%2E+In+11th+International+Conference+on+Parsing+Technologies)
38. Markus Saers, Joakim Nivre, and Dekai Wu. Word alignment with stochastic bracketing linear inversion transduction grammar. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL HLT 2010), pages 341– 344, Los Angeles, California, June 2010. [find](https://scholar.google.com/scholar?q=Markus+Saers%2C+Joakim+Nivre%2C+and+Dekai+Wu%2E+Word+alignment+with+stochastic+bracketing+linear+inversion+transduction+grammar%2E+In+Human+Language+Technologies%3A+The+2010+Annual+Conference+of+the+North+Ameri)
39. Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul. [A study of translation edit rate with targeted human annotation](https://md.research.elamur.ai/free/en/papers/snover-2006-study-translation-edit-rate-targeted/). In 7th Biennial Conference Association for Machine Translation in the Americas (AMTA 2006), pages 223–231, Cambridge, Massachusetts, August 2006.
40. Theerawat Songyot and David Chiang. Improving word alignment using word similarity. In 52nd Annual Meeting of the Association for Computational Linguistics, 2014. [find](https://scholar.google.com/scholar?q=Theerawat+Songyot+and+David+Chiang%2E+Improving+word+alignment+using+word+similarity%2E+In+52nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+2014%2E)
41. Andreas Stolcke. SRILM – an extensible language modeling toolkit. In 7th International Conference on Spoken Language Processing (ICSLP2002 - INTERSPEECH 2002), pages 901–904, Denver, Colorado, September 2002. [find](https://scholar.google.com/scholar?q=Andreas+Stolcke%2E+SRILM+%E2%80%93+an+extensible+language+modeling+toolkit%2E+In+7th+International+Conference+on+Spoken+Language+Processing+%28ICSLP2002+%2D+INTERSPEECH+2002%29%2C+pages+901%E2%80%93904%2C+Denver%2C+Colorado%2C+Septemb)
42. Stephan Vogel, Hermann Ney, and Christoph Tillmann. HMM-based word alignment in statistical translation. In The 16th International Conference on Computational linguistics (COLING-96), volume 2, pages 836–841, 1996. [find](https://scholar.google.com/scholar?q=Stephan+Vogel%2C+Hermann+Ney%2C+and+Christoph+Tillmann%2E+HMM%2Dbased+word+alignment+in+statistical+translation%2E+In+The+16th+International+Conference+on+Computational+linguistics+%28COLING%2D96%29%2C+volume+2%2C+pages+)
43. Dekai Wu. Trainable coarse bilingual grammars for parallel text bracketing. In Third Annual Workshop on Very Large Corpora (WVLC-3), pages 69–81, Cambridge, Massachusetts, June 1995. [find](https://scholar.google.com/scholar?q=Dekai+Wu%2E+Trainable+coarse+bilingual+grammars+for+parallel+text+bracketing%2E+In+Third+Annual+Workshop+on+Very+Large+Corpora+%28WVLC%2D3%29%2C+pages+69%E2%80%9381%2C+Cambridge%2C+Massachusetts%2C+June+1995%2E)
44. Dekai Wu. [Stochastic inversion transduction grammars and bilingual parsing of parallel corpora](https://md.research.elamur.ai/free/en/papers/wu-1997-stochastic-inversion-transduction-grammars-bilingual/). Computational Linguistics, 23(3):377–403, 1997.
45. Richard Zens and Hermann Ney. A comparative study on reordering constraints in statistical machine translation. In 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003), pages 144–151, Stroudsburg, Pennsylvania, 2003. [find](https://scholar.google.com/scholar?q=Richard+Zens+and+Hermann+Ney%2E+A+comparative+study+on+reordering+constraints+in+statistical+machine+translation%2E+In+41st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%2D2003%29%2C+page)
46. Hao Zhang and Daniel Gildea. Stochastic lexicalized inversion transduction grammar for alignment. In 43rd Annual Meeting of the Association for Computational Linguistics (ACL-05), pages 475–482, Ann Arbor, Michigan, June 2005. [find](https://scholar.google.com/scholar?q=Hao+Zhang+and+Daniel+Gildea%2E+Stochastic+lexicalized+inversion+transduction+grammar+for+alignment%2E+In+43rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%2D05%29%2C+pages+475%E2%80%93482%2C+Ann+A)

*Updated 24 October 2026*