MaltParser Dependency Parser

Illuminating Syntax: The Vital Role of MaltParser in Dependency Parsing 

MaltParser has emerged as one of the most widely used dependency parsing frameworks, playing a pivotal role in advancing dependency-based syntactic analysis in natural language processing. As an open-source transition-based parsing system implemented in Java, MaltParser exemplifies the success of applying machine learning techniques to complex linguistic tasks.

At its core, MaltParser aims to determine the syntactic structure of sentences by analyzing the grammatical relationships between words. It does this through a two-phase parsing approach, first applying heuristic rules to generate an initial parse of the sentence before using a dependency grammar and set of relations to search for the most likely final parse. This transition-based technique models the parse as a sequence of actions that incrementally build a full dependency parse tree.

To guide its search, MaltParser uses a rich set of features extracted from the sentence, including the words, part-of-speech tags, context, and history of past parsing actions. The parser uses a scoring function to rank alternative parses, selecting the highest scoring tree as the end result. This output parse explicitly represents dependencies between words through labeled arcs connecting the tokens.

Researchers have leveraged MaltParser’s configurable machine learning components to train custom models for over 40 languages. As an illustration, one study optimized a parser for Lithuanian using rich morphological features to capture its complex inflections. Another explored augmenting MaltParser for Korean with full lexical information to improve accuracy. Such adaptations demonstrate the framework’s extensibility.

MaltParser’s syntactic parsing capabilities enable higher-level NLP applications. For instance, one system extracted biographical relationships from text using MaltParser to provide input dependency structures. Others have employed the parser to preprocess historical texts to identify verb clauses despite language variation or support concept location in source code. Analyzing the parliamentary proceedings of the European Parliament, researchers used multilingual MaltParser-based parsers to extract rhetorical relations.

Active research also continues on improving MaltParser itself. Recent work has developed enhanced transition systems, studied the impact of different training corpora, and experimented with new features. Error analysis has even used MaltParser to parse gold treebanks and detect anomalies. On the applied side, researchers have visualized MaltParser’s transition sequences to make the parsing process more transparent.

In driving forward dependency-based approaches to syntactic parsing, MaltParser has demonstrated the ability of machine learning techniques to capture complex linguistic phenomena. Its flexible, extensible architecture has supported practical parsing solutions for real-world NLP tasks across languages and domains. For both researchers advancing parsing algorithms and practitioners handling linguistic data, MaltParser remains an indispensable tool.

Resources:

Wikipedia:

See also:

APP (Apple Pie Parser) | Best Natural Language Parsing Videos | CCG Parsers 2011 | CFG (Context-free Grammar) Parsers | Chart Parsers & Dialog Systems | Grammar Parsers & Dialog Systems | Grammar Parsing & Natural Language Generation | HPSG Parsers | LALR Parser | Ontology Parsers | Parsing Algorithms & Dialog Systems | PCFG (Probabilistic Context Free Grammar) & Dialog Systems | Sentence Parsers & Dialog Systems

  • Abbas, Q. (2014). Exploiting Language Variants Via Grammar Parsing Having Morphologically Rich Information. In LT4CloseLang 2014 (pp. 36–46).
  • Abebe, S. L., Alicante, A., & Corazza, A. (2013). Supporting concept location through identifier parsing and ontology extraction. Journal of Systems and Software, 86(10), 2519-2533.
  • Agarwal, R., Ambati, B. R., & Sharma, D. M. (2012). A hybrid approach to error detection in a treebank and its impact on manual validation time. In Linguistic Issues in Language Technology (Vol. 8, pp. 1-8).
  • Alabbas, M., & Ramsay, A. (2012, December). Combining black-box taggers and parsers for modern standard Arabic. In Computer Science and Information Technology (CSIT), 2012 5th International Conference on (pp. 248-253). IEEE.
  • Alicante, A. (2013). Barrier and syntactic features for information retrieval (Doctoral dissertation).
  • Annamaneni, N., & Bhat, R. A. (2013). Ensembling dependency parsers for treebank error detection. In The Twelfth Workshop on Treebanks and Linguistic Theories (TLT12).
  • Anthonymuthu, A. S., Georgescu, V., & Kurohashi, S. (2014). An ensemble model for semantic role labeling. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (pp. 1063-1072).
  • Arora, A., Agarwal, R., Joshi, S., & Singla, P. (2015). Learning to annotate: Modular active learning for corpus construction. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 1482-1491).
  • Ballesteros, M. (2013). Análisis, optimización, mejora y aplicación del análisis de dependencias (Doctoral dissertation, Universidad Complutense de Madrid).
  • Ballesteros, M., & Nivre, J. (2012). MaltOptimizer: A system for MaltParser optimization. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12) (pp. 2757-2762).
  • Ballesteros, M., & Nivre, J. (2014). MaltOptimizer: Fast and effective parser optimization. Natural Language Engineering, 20(2), 317-339.
  • Ballesteros, M., Bohnet, B., Mille, S., & Wanner, L. (2015). Data-driven sentence generation with non-isomorphic trees. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 387-397).
  • Ballesteros, M., Carlini, R. (2013). MaltDiver: A transition-based parser visualizer. In Proceedings of the System Demonstration Session of ACL 2013 (pp. 25–30).
  • Ballesteros, M., Francisco, V., Herrera, J. D. L. C., Gervás, P., & León, C. (2012). Are the existing training corpora unnecessarily large?. Avances en el Procesamiento del Lenguaje Natural, 50, 23-30.
  • Bengtsson, J., & Skeppstedt, C. (2013). Automatic extractive single document summarization: An unsupervised approach (Master’s thesis, Chalmers University of Technology, University of Gothenburg).
  • Bernardi, R., Uijlings, J. R., & Le, D. T. (2013). Exploiting language models to recognize unseen actions. In Proceedings of the 3rd ACM conference on International conference on multimedia retrieval (pp. 231-238). ACM.
  • Betteridge, J., Ritter, A., & Mitchell, T. (2014). Assuming facts are expressed more than once. In The Twenty-Seventh International Conference on Computational Linguistics (COLING) (Vol. 2, pp. 1896–1906).
  • Bollegala, D., Maehara, T., & Yoshida, Y. (2014). Learning word representations from relational graphs. arXiv preprint arXiv:1411.0133.
  • Candito, M., & Seddah, D. (2012). Effectively long-distance dependencies in French: annotation and parsing evaluation. In TLT 11-The 11th International Workshop on Treebanks and Linguistic Theories (Vol. 11, p. 15).
  • Che, W., Guo, J., & Liu, T. (2014). Reliable dependency arc recognition. Expert Systems with Applications, 41(6), 2947-2956.
  • Che, W., Spitkovsky, V. I., & Liu, T. (2012, December). A comparison of Chinese parsers for Stanford dependencies. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2 (pp. 6-11). Association for Computational Linguistics.
  • Chen, D., & Manning, C. (2014). A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 740-750).
  • Daniel, R. (2012). Domain-independent mining of abstracts using indicator phrases. D-Lib Magazine, 18(7/8).
  • Dannélls, D. (2013). Multilingual text generation from structured formal representations. Data Linguistica, 23.
  • Dhivya, R., Dhanalakshmi, V., & Kumar, M. A. (2012, July). Clause boundary identification for tamil language using dependency parsing. In Signal Processing and Communication (ICSC), 2012 International Conference on (pp. 396-400). IEEE.
  • Donelaicio, K., Nivre, J., & Krupavicius, A. (2013). Lithuanian dependency parsing with rich morphological features. In Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically Rich Languages (pp. 12-21).
  • Elming, J., Johannsen, A., Klerke, S., Lapponi, E., Martinez Alonso, H., & Plank, B. (2013). Down-stream effects of tree-to-dependency conversions. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 617-626).
  • Eragani, A. K., & Kuchibhotla, V. (2014, December). A simple grammar-driven unlexicalised dependency parser to improve upon Malt Parser. In Asian Language Processing (IALP), 2014 International Conference on (pp. 13-16). IEEE.
  • Flannery, D., Miyao, Y., Neubig, G., & Mori, S. (2012, December). Training dependency parsers from partially annotated corpora. In Information and Media Technologies (Vol. 7, No. 4, pp. 1434-1445).
  • Gadde, S. P. K. (2015). Designing a data-driven clausal parsing framework (Doctoral dissertation, International Institute of Information Technology-Hyderabad).
  • Garcia, M., & Gamallo, P. (2013). Exploring the effectiveness of linguistic knowledge for biographical relation extraction. Natural Language Engineering, 1-33.
  • Gerdes, K. (2013). Predictive incremental parsing and its evaluation. In K. Gerdes, E. Hajicova, & L. Wanner (Eds.), Computational Dependency Theory (pp. 186-206). IOS Press.
  • Gonzalez, M., & Giménez, J. (2014). An open toolkit for automatic machine translation (Meta-) evaluation. Department of Information and Communication Technologies, Pompeu Fabra University.
  • Goto, I., Utiyama, M., Onishi, T., & Sumita, E. (2012). An empirical comparison of parsers in constraining reordering for EJ patent machine translation. Information and Media Technologies, 7(4), 1457-1468.
  • Haulrich, M. W. (2012). Data-driven bitext dependency parsing and alignment (Doctoral dissertation, Copenhagen Business School).
  • Haulrich, M. W. (2012). Data-driven bitext dependency parsing and alignment (Doctoral dissertation, Copenhagen Business School).
  • Illig, J., Allee, W., Roth, D., & Klakow, D. (2014). Unsupervised parsing for generating surface-based relation extraction patterns. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (pp. 100–105).
  • Itoh, M., Yoshinaga, N., Toyoda, M., & Kitsuregawa, M. (2012, March). Analysis and visualization of temporal changes in bloggers’ activities and interests. In Pacific Visualization Symposium (PacificVis), 2012 IEEE (pp. 57-64). IEEE.
  • Jain, S., & Agrawal, B. (2013). A dynamic confusion score for dependency arc labels. In Proceedings of the Sixth International Joint Conference on Natural Language Processing (pp. 1236–1240).
  • Jain, S., Agrawal, B., Tammewar, A., Bhat, R. A., & Sharma, D. M. (2013). Exploring semantic information in Hindi WordNet for Hindi dependency parsing.
  • Kawahara, D., Shinzato, K., Shibata, T., & Kurohashi, S. (2013). Precise information retrieval exploiting predicate-argument structures. In International Joint Conference on Natural Language Processing (IJCNLP) (pp. 37-45).
  • Khallash, M., Hadian, A., & Minaei-Bidgoli, B. (2013). An empirical study on the effect of morphological and lexical features in Persian dependency parsing. In Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically Rich Languages (pp. 97-107).
  • Kocincová, L. (2012, May). Reproducing Czech syntactic parsing results published in CoNLL tasks. In Sixth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN (pp. 23-31).
  • Kundu, B., & Choudhury, S. K. (2014). How to know best machine translation system in advance before translating a sentence?. Computing, 96(12), 1159-1170.
  • Lapponi, E. (2012). Why not!: Sequence labeling the scope of negation using dependency features (Master’s thesis). University of Oslo.
  • Lapponi, E., Velldal, E., Øvrelid, L., & Read, J. (2012). Uio 2: Sequence labeling negation using dependency features. In * SEM 2012: The First Joint Conference on Lexical and Computational Semantics (pp. 319-327).
  • Li, H., Cheng, X., Adson, K., Kirshboim, T., & Xu, F. (2012). Annotating opinions in German political news. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC-2012) (pp. 1167-1170).
  • Li, L. (2012). Computational modeling of lexical ambiguity (Doctoral dissertation). Saarland University.
  • Li, L., Xie, J., Way, A., & Liu, Q. (2014). Transformation and decomposition for efficiently implementing and improving dependency-to-string model in Moses. In Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (pp. 122-131).
  • Llitjos, A. F., & Carbonell, J. G. (2016, August). Predicate Argument Alignment using a Global Coherence Model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 60-70).
  • Mambrini, F., & Passarotti, M. (2012). Will a parser overtake Achilles? First experiments on parsing the ancient Greek dependency treebank. In Proceedings of the Eleventh International Workshop on Treebanks and Linguistic Theories (pp. 133-144).
  • Manione, R., Arisio, F., & Gerbino, E. (2012). Design of components for understanding, dialogue management and feedback to the user. DIRHA Project.
  • Mazzei, A. (2015). Simple voting algorithms for Italian parsing. In P. Monachesi (Ed.), Harmonization and Development of Resources and Tools for Italian Natural Language Processing within the PARLI Project (pp. 163-173). Springer International Publishing.
  • Mazzei, A., & Bosco, C. (2012). Simple parser combination. In Semantic Processing of Legal Texts (SPLeT 2012) Workshop Programme (pp. 65-69).
  • Mendt, T., Muriithi, P., Samota, E., & Mendt, M. (2014). State of the art NLP: Multilingualism and semantic parsing in information retrieval and extraction. University of Tours.
  • Nivre, J., Tiedemann, J., Versley, Y., & Cetinoglu, O. (2016). Using universal dependencies in syntax-based machine translation. In Proceedings of the 1st Workshop on Universal Dependencies (UDW 2016) (pp. 84–93).
  • Park, J., Lannion, F., Kurohashi, S., & Choi, K. S. (2013). Towards fully lexicalized dependency parsing for Korean. In Proceedings of the International Workshop on Parsing Technologies (IWPT) (pp. 123-127).
  • Perleka, E. (2013). Plagiarism detection: An overview of text alignment techniques (Master’s thesis). University of Gothenburg.
  • Pettersson, E., & Megyesi, B. (2013). An SMT approach to automatic annotation of historical text. In Proceedings of the Workshop on Computational Historical Linguistics at NODALIDA 2013 (pp. 54-69).
  • Pettersson, E., & Megyesi, B. B. (2012). Parsing the past: Identification of verb constructions in historical text. In Proceedings of the NAACL-HLT 2012 Sixth Workshop on Statistical Machine Translation (pp. 217-227).
  • Plank, B., & Søgaard, A. (2013). Experiments in domain adaptation for parsing. In Evaluation of Natural Language and Speech Tools for Italian (pp. 78-83). Springer Berlin Heidelberg.
  • Pradel, C., Haemmerlé, O., & Hernandez, N. (2013, October). Demo: Swip, a semantic web interface using patterns. In International Semantic Web Conference (Posters & Demos) (pp. 85-88).
  • Pretkalni?a, L., & Rituma, L. (2013). Statistical syntactic parsing for Latvian. In Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013) (pp. 272-286).
  • Prokopidis, P., Papavassiliou, V., Toral, A., Poch, M., Thurmair, G., & Bisazza, A. (2014). Final report on the corpus acquisition & annotation subsystem and its components. PANACEA Project.
  • Rudnick, A. (2012). Transition-based dependency parsing with pluggable classifiers. arXiv preprint arXiv:1211.0074.
  • Røkenes, H. D. (2012). Graph-based natural language processing: Graph edit distance applied to the task of detecting plagiarism (Master’s thesis). University of Oslo.
  • Saveski, G. L. (2014). Accessing Natural Language Processing Engines and Tasks (Master’s thesis). Tampere University of Technology.
  • Unger, C., Freitas, A., & Cimiano, P. (2014). An introduction to question answering over linked data. In P. Mika et al. (Eds.), Reasoning Web. Reasoning on the Web in the Big Data Era (pp. 100-140). Springer International Publishing.
  • Van de Cruys, T., Afantenos, S., & Muller, P. (2013). Multilingual semantic similarity of words and compositional phrases using latent vector weighting. In Second Joint Conference on Lexical and Computational Semantics (*SEM) (Vol. 2, pp. 98-102).
  • Viereckel, N., & Tiedemann, J. (2014). Identification of idiomatic expressions using parallel subtitle corpora. Lingue e linguaggio, 13(2), 291-310.
  • Volokh, A. (2013). Performance-oriented dependency parsing (Doctoral dissertation). Saarland University, Saarbrücken, Germany.
  • Walter, S., Unger, C., & Cimiano, P. (2013). A corpus-based approach for the induction of ontology lexica. In I. Gurevych et al. (Eds.) Natural Language Processing and Information Systems (pp. 102-113). Springer Berlin Heidelberg.
  • Walter, S., Unger, C., & Cimiano, P. (2014). ATOLL—A framework for the automatic induction of ontology lexica. Data & Knowledge Engineering, 94, 148-162.
  • Wróblewska, A., & Woli?ski, M. (2012). Preliminary experiments in Polish dependency parsing. In Security and Intelligent Information Systems (pp. 179-188). Springer Berlin Heidelberg.
  • Wu, X., Zhou, J., Sun, Y., Liu, Z., Yu, D., Wu, H., & Wang, H. (2013). Generalization of words for chinese dependency parsing. In Proceedings of IWPT 2013 (pp. 76-86).
  • Yin, D. (2013, January). Chinese syntactic parsing based on linguistic entity-relationship model. In Proceedings of the 22nd ACM international conference on Information & Knowledge Management (pp. 2399-2402). ACM.
  • Young, P., Lai, A., Hodosh, M., & Hockenmaier, J. (2014). From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics, 2, 67-78.