From the earliest days, assessing the quality of word sense disambiguation algorithms had been primarily a matter of intrinsic evaluation, and “almost no attempts had been made to evaluate embedded WSD components”.3 Only very recently (2006) had extrinsic evaluations begun to provide some evidence for the value of WSD in end-user applications.4 Until 1990 or so, discussions of the sense disambiguation task focused mainly on illustrative examples rather than comprehensive evaluation. The early 1990s saw the beginnings of more systematic and rigorous intrinsic evaluations, including more formal experimentation on small sets of ambiguous words.5
In April 1997, Martha Palmer and Marc Light organized a workshop entitled Tagging with Lexical Semantics: Why, What, and How? in conjunction with the Conference on Applied Natural Language Processing.6 At the time, there was a clear recognition that manually annotated corpora had revolutionized other areas of NLP, such as part-of-speech tagging and parsing, and that corpus-driven approaches had the potential to revolutionize automatic semantic analysis as well.7 Kilgarriff recalled that there was "a high degree of consensus that the field needed evaluation", and several practical proposals by Resnik and Yarowsky kicked off a discussion that led to the creation of the Senseval evaluation exercises.8910
After SemEval-2010, many participants feel that the 3-year cycle is a long wait. Many other shared tasks such as Conference on Natural Language Learning (CoNLL) and Recognizing Textual Entailments (RTE) run annually. For this reason, the SemEval coordinators gave the opportunity for task organizers to choose between a 2-year or a 3-year cycle.11 The SemEval community favored the 3-year cycle. Although the votes within the SemEval community favored a 3-year cycle, organizers and coordinators had settled to split the SemEval task into 2 evaluation workshops. This was triggered by the introduction of the new *SEM conference. The SemEval organizers thought it would be appropriate to associate our event with the *SEM conference and collocate the SemEval workshop with the *SEM conference. The organizers got very positive responses (from the task coordinators/organizers and participants) about the association with the yearly *SEM, and 8 tasks were willing to switch to 2012. Thus was born SemEval-2012 and SemEval-2013. The current plan is to switch to a yearly SemEval schedule to associate it with the *SEM conference but not every task needs to run every year.12
The framework of the SemEval/Senseval evaluation workshops emulates the Message Understanding Conferences (MUCs) and other evaluation workshops ran by ARPA (Advanced Research Projects Agency, renamed the Defense Advanced Research Projects Agency (DARPA)).
Stages of SemEval/Senseval evaluation workshops14
Senseval-1 & Senseval-2 focused on evaluation WSD systems on major languages that were available corpus and computerized dictionary. Senseval-3 looked beyond the lexemes and started to evaluate systems that looked into wider areas of semantics, such as Semantic Roles (technically known as Theta roles in formal semantics), Logic Form Transformation (commonly semantics of phrases, clauses or sentences were represented in first-order logic forms) and Senseval-3 explored performances of semantics analysis on Machine translation.
As the types of different computational semantic systems grew beyond the coverage of WSD, Senseval evolved into SemEval, where more aspects of computational semantic systems were evaluated.
The SemEval exercises provide a mechanism for examining issues in semantic analysis of texts. The topics of interest fall short of the logical rigor that is found in formal computational semantics, attempting to identify and characterize the kinds of issues relevant to human understanding of language. The primary goal is to replicate human processing by means of computer systems. The tasks (shown below) are developed by individuals and groups to deal with identifiable issues, as they take on some concrete form.
The first major area in semantic analysis is the identification of the intended meaning at the word level (taken to include idiomatic expressions). This is word-sense disambiguation (a concept that is evolving away from the notion that words have discrete senses, but rather are characterized by the ways in which they are used, i.e., their contexts). The tasks in this area include lexical sample and all-word disambiguation, multi- and cross-lingual disambiguation, and lexical substitution. Given the difficulties of identifying word senses, other tasks relevant to this topic include word-sense induction, subcategorization acquisition, and evaluation of lexical resources.
The second major area in semantic analysis is the understanding of how different sentence and textual elements fit together. Tasks in this area include semantic role labeling, semantic relation analysis, and coreference resolution. Other tasks in this area look at more specialized issues of semantic analysis, such as temporal information processing, metonymy resolution, and sentiment analysis. The tasks in this area have many potential applications, such as information extraction, question answering, document summarization, machine translation, construction of thesauri and semantic networks, language modeling, paraphrasing, and recognizing textual entailment. In each of these potential applications, the contribution of the types of semantic analysis constitutes the most outstanding research issue.
For example, in the word sense induction and disambiguation task, there are three separate phases:
The unsupervised evaluation for WSI considered two types of evaluation V Measure (Rosenberg and Hirschberg, 2007), and paired F-Score (Artiles et al., 2009). This evaluation follows the supervised evaluation of SemEval-2007 WSI task (Agirre and Soroa, 2007)
The tables below reflects the workshop growth from Senseval to SemEval and gives an overview of which area of computational semantics was evaluated throughout the Senseval/SemEval workshops.
The Multilingual WSD task was introduced for the SemEval-2013 workshop.17 The task is aimed at evaluating Word Sense Disambiguation systems in a multilingual scenario using BabelNet as its sense inventory. Unlike similar task like crosslingual WSD or the multilingual lexical substitution task, where no fixed sense inventory is specified, Multilingual WSD uses the BabelNet as its sense inventory. Prior to the development of BabelNet, a bilingual lexical sample WSD evaluation task was carried out in SemEval-2007 on Chinese-English bitexts.18
The Cross-lingual WSD task was introduced in the SemEval-2007 evaluation workshop and re-proposed in the SemEval-2013 workshop .19 To facilitate the ease of integrating WSD systems into other Natural Language Processing (NLP) applications, such as Machine Translation and multilingual Information Retrieval, the cross-lingual WSD evaluation task was introduced a language-independent and knowledge-lean approach to WSD. The task is an unsupervised Word Sense Disambiguation task for English nouns by means of parallel corpora. It follows the lexical-sample variant of the Classic WSD task, restricted to only 20 polysemous nouns.
It is worth noting that the SemEval-2014 have only two tasks that were multilingual/crosslingual, i.e. (i) the L2 Writing Assistant task, which is a crosslingual WSD task that includes English, Spanish, German, French and Dutch and (ii) the Multilingual Semantic Textual Similarity task that evaluates systems on English and Spanish texts.
The major tasks in semantic evaluation include the following areas of natural language processing. This list is expected to grow as the field progresses.20
The following table shows the areas of studies that were involved in Senseval-1 through SemEval-2014 (S refers to Senseval and SE refers to SemEval, e.g. S1 refers to Senseval-1 and SE07 refers to SemEval2007):
SemEval tasks have created many types of semantic annotations, each type with various schema. In SemEval-2015, the organizers have decided to group tasks together into several tracks. These tracks are by the type of semantic annotations that the task hope to achieve.21 Here lists the type of semantic annotations involved in the SemEval workshops:
A task and its track allocation is flexible; a task might develop into its own track, e.g. the taxonomy evaluation task in SemEval-2015 was under the Learning Semantic Relations track and in SemEval-2016, there is a dedicated track for Semantic Taxonomy with a new Semantic Taxonomy Enrichment task.2223
Blackburn, P., and Bos, J. (2005), Representation and Inference for Natural Language: A First Course in Computational Semantics, CSLI Publications. ISBN 1-57586-496-7. /wiki/ISBN_(identifier) ↩
Navigli, R (2009). "Word sense disambiguation". ACM Computing Surveys. 41 (2): 1–69. doi:10.1145/1459352.1459355. S2CID 461624. /wiki/Doi_(identifier) ↩
Palmer, M., Ng, H.T., & Hoa, T.D. (2006), Evaluation of WSD systems, in Eneko Agirre & Phil Edmonds (eds.), Word Sense Disambiguation: Algorithms and Applications, Text, Speech and Language Technology, vol. 33. Amsterdam: Springer, 75–106. https://books.google.com/books?id=GLck75U20pAC ↩
Resnik, P. (2006), WSD in NLP applications, in Eneko Agirre & Phil Edmonds (eds.), Word Sense Disambiguation: Algorithms and Applications. Dordrecht: Springer, 299–338. ↩
Yarowsky, D. (1992), Word-sense disambiguation using statistical models of Roget’s categories trained on large corpora. Proceedings of the 14th Conference on Computational Linguistics, 454–60. doi:10.3115/992133.992140 /wiki/Doi_(identifier) ↩
Palmer, M., & Light, M. (1999), Tagging with Lexical Semantics: Why, What, and How?| ACL SIGLEX workshop on tagging text with lexical semantics: what, why, and how? Archived 2010-07-15 at the Wayback Machine Natural Language Engineering 5(2): i–iv. http://www.ims.uni-stuttgart.de/~light/tueb_html/semtag_ws.html ↩
Ng, H.T. (1997), Getting serious about word sense disambiguation. Proceedings of the ACL SIGLEX Workshop on Tagging Text with Lexical Semantics: Why, What, and How? 1–7. ↩
Philip Resnik and Jimmy Lin (2010). Evaluation of NLP Systems. In Alexander Clark, Chris Fox, and Shalom Lappin, editors. The Handbook of Computational Linguistics and Natural Language Processing. Wiley-Blackwellis. 11:271 ↩
Adam Kilgarriff and Martha Palmer (ed. 2000). Special Issue of Computers and the Humanities, SENSEVAL98:Evaluating Word Sense Disambiguation Systems. Kluwer, 34: 1–2. ↩
Scott Cotton, Phil Edmonds, Adam Kilgarriff, and Martha Palmer (ed. 2001). SENSEVAL-2: Second International Workshop on Evaluating Word Sense Disambiguation Systems. SIGLEX Workshop, ACL03, Toulouse, France. ↩
SIGLEX: Message Board (2010) Retrieved on Aug 15, 2012, from http://www.clres.com/siglex/messdisp.php?id=111 http://www.clres.com/siglex/messdisp.php?id=111 ↩
SemEval 3 Google Group post. Retrieved on Aug 15, 2012, from https://groups.google.com/forum/?fromgroups#!topic/semeval3/8YXMvVlH-CM%5B1-25%5D https://groups.google.com/forum/?fromgroups#!topic/semeval3/8YXMvVlH-CM%5B1-25%5D ↩
Language Resources and Evaluation Volume 43, Number 2[dead link] http://springerlink.com/1574-020x/43/2/ ↩
Kilgarriff, A. (1998). SENSEVAL: An Exercise in Evaluating Word Sense Disambiguation Programs. In Proc. LREC, Granada, May 1998. Pp 581--588 ↩
"Tasks < SemEval-2017". alt.qcri.org. Retrieved 2018-05-04. http://alt.qcri.org/semeval2017/index.php?id=tasks ↩
"Tasks < SemEval-2018". alt.qcri.org. Retrieved 2018-05-04. http://alt.qcri.org/semeval2018/index.php?id=tasks ↩
Navigli, R., Jurgens, D., & Vannella, D. (2013, June). Semeval-2013 task 12: Multilingual word sense disambiguation. In Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval 2013), in conjunction with the Second Joint Conference on Lexical and Computational Semantics (* SEM 2013) (pp. 222-231). ↩
Peng Jin, Yunfang Wu and Shiwen Yu. SemEval-2007 task 05: multilingual Chinese-English lexical sample. Proceedings of the 4th International Workshop on Semantic Evaluations, p.19-23, June 23–24, 2007, Prague, Czech Republic. http://aclweb.org/anthology-new/S/S07/S07-1004.pdf ↩
Lefever, E., & Hoste, V. (2013, June). Semeval-2013 task 10: Cross-lingual word sense disambiguation. In Second joint conference on lexical and computational semantics (Vol. 2, pp. 158-166). ↩
SemEval Portal (n.d.). In ACLwiki. Retrieved August 12, 2010 from http://aclweb.org/aclwiki/index.php?title=SemEval_Portal http://aclweb.org/aclwiki/index.php?title=SemEval_Portal ↩
SemEval-2015 website. Retrieved Nov 14, 2014 http://alt.qcri.org/semeval2015/index.php?id=tasks http://alt.qcri.org/semeval2015/index.php?id=tasks ↩
Georgeta Bordea, Paul Buitelaar, Stefano Faralli and Roberto Navigli. 2015. Semeval-2015 task 17: Taxonomy Extraction Evaluation (TExEval). In Proceedings of the 9th International Workshop on Semantic Evaluation. Denver, USA. ↩
SemEval-2016 website. Retrieved Jun 4 2015 http://alt.qcri.org/semeval2016/ http://alt.qcri.org/semeval2016/ ↩