Marjorie McShane's Publications by Topic, Lightly Annotated

Associate Professor, Cognitive Science Department
Co-Director LEIA (Language-Endowed Intelligent Agents) Lab
Rensselaer Polytechnic Institute
mcsham2 [the sign] [rpi.edu]
My university website is here.
Marge McShane Photo

The following is a roughly chronological overview of areas in which I have worked.
Listed pubications are selective.
For a full list of publications, see my home page.

1. Slavic

1a. Slavic Lexicography

From 1990-1995, while earning a Master's degree in Russian literature and an Advanced Certification of Translation (Russian-English), I served as Developmental Editor for the Random House Russian-English Dictionary of Idioms (1995), by Sophia Lubensky. During this period, the author and I overhauled the manuscript twice. I collaborated equally with her on sense discrimination, writing definitions and usage notes, and selecting literary examples. I wrote all of the introductory materials to the work. Click here for sample pages.

The pedagogical utility of this approach to lexicography is described here:

Lubensky, S. and McShane, M. 2007. Bilingual phraseological dictionaries. In Burger, H., Dobrovol'skij, D., Kühn, P., and Norrick, N.R. (Eds.), Phraseologie / Phraseology: Ein internationales Handbuch zeitgenössischer Forschung / An International Handbook of Contemporary Research. Mouton de Gruyter, pp. 919-928. pdf

1b. Reference and Ellipsis in Slavic

My doctoral thesis, Ellipsis in Slavic: The Syntax-Discourse Interface (Princeton, 1998), presents rigorous, heuristic-oriented descriptions intended to permit a non-native speaker to explain and predict ellipsis usage in Russian and Polish. Aspects of that work were presented in a series of articles:

McShane, M. 1999. Predictive rules of direct object ellipsis in Russian. In Dziwirek, K. et al. (Eds.), Annual Workshop on Formal Approaches to Slavic Linguistics: The Seattle Meeting, 1998, pp. 329-348. Ann Arbor, Michigan: Michigan Slavic Publications. pdf

McShane, M. 1999. The ellipsis of accusative direct objects in Russian, Polish and Czech. Journal of Slavic Linguistics 7(1): 45-88. pdf

McShane, M. 2000. Hierarchies of parallelism in elliptical Polish structures. Journal of Slavic Linguistics, 8: 83-117. pdf

McShane, M. 2000. Verbal ellipsis in Russian, Polish and Czech. Slavic and East European Journal 44(2): 195-233. pdf

McShane, M. 2002. So where's that noun? Rusistika, 26: 7-14. pdf

McShane, M. 2002. Unexpressed objects in Russian. Journal of Slavic Linguistics, 10(1): 291-328. pdf

McShane, M. 2009. Subject ellipsis in Russian and Polish. In Holmberg, A. (Ed.), Special Issue on Partial Pro-Drop, Studia Linguistica, 63(1): 98-132. Cambridge University Press. pdf

Although not initially intended for computational applications, my approach to describing ellipsis was sufficiently precise to be a natural fit for knowledge-based natural language processing. I explored this connection in my 2005 book:

McShane, Marjorie. 2005. A Theory of Ellipsis. Oxford University Press.

In 2014 I presented a keynote address at the 2014 DIALOG conference, Russia's premier computational linguistics conference, recorded in the proceedings:

McShane, M. 2014. A multi-faceted approach to reference resolution in English and Russian. In Selegei, V. P. (Chief Editor), Computational Linguistics and Intellectual Technologies, Papers from the Annual International Conference Dialogue, Issue 13, pp. 391-409. pdf

2. Knowledge Elicitation & Modeling

In 1998-2005 I led a team developing the Boas and Boas II knowledge acquisition and elicitation systems, which sought to automatically elicit from untrained speakers of any language (L) sufficient structured knowledge to support the configuration of an L-to-English machine translation system. I led development of the linguistic theory and descriptions that were implemented in the system. This task involved analyzing data from dozens of languages to facilitate the creation of an extensive fine-grained metalanguage of formal parameters, their associated value sets, and linguistic realizations of those values. The following publications describe my experiences with Boas and its proper-name-oriented successor, Boas II, as well as lessons learned, application systems enhanced, and theoretical and methodological generalizations made possible by this work.

McShane, M., Helmreich, S., Nirenburg, S. and Raskin, V. 2000. Slavic as testing grounds for a linguistic knowledge elicitation system. In King, T.H. and Sekerina, I.A. (Eds.), Formal Approaches to Slavic Linguistics: The Philadelphia Meeting, 1999, pp. 280-295. Ann Arbor, Michigan: Michigan Slavic Publications. pdf

McShane, M. and Zacharski, R. 2000. Modularity in knowledge elicitation and language processing. Proceedings of the Third Annual High Desert Linguistics Conference, pp. 93-104. University of New Mexico, Albuquerque, NM. pdf

Oflazer, K., Nirenburg, S. and McShane, M. 2001. Bootstrapping morphological analyzers by combining human elicitation and machine learning. Computational Linguistics 27(1): 59-85. pdf

McShane, M., Nirenburg, S., Cowie, J. and Zacharski, R. 2002. Embedding knowledge elicitation and MT systems within a single architecture. Machine Translation 17(4):271-305. pdf

McShane, M. 2003. Applying tools and techniques of natural language processing to the creation of resources for less commonly taught languages. IALLT Journal of Language Learning Technologies, 35(1): 25-46. pdf

McShane, M. and Nirenburg, S. 2003. Blasting open a choice space: Learning inflectional morphology for NLP. Computational Intelligence, 19(2): 111-135. pdf

McShane, M. and Nirenburg, S. 2003. Parameterizing and eliciting text elements across languages. Machine Translation, 18(2): 129-165. pdf

McShane, M., Nirenburg, S. and Zacharski, R. 2004. Mood and modality: Out of theory and into the fray. Natural Language Engineering, 19(1): 57-89. pdf

McShane, M., Zacharski, R., Beale, S. and Nirenburg, S. 2005. The Boas II named entity elicitation system. Working Paper #08-05, Institute for Language and Information Technologies, University of Maryland Baltimore County. pdf

McShane, M. 2009. Developing proper name recognition, translation and matching capabilities for low- and middle-density languages. In Nirenburg, S. (Ed.), Language Engineering for Lesser-Studied Languages. IOS Press, pp. 81-115. pdf

Nirenburg, S. and McShane, M. 2009. Computational field semantics: Acquiring an Ontological Semantic lexicon for a new language. In Nirenburg, S. (Ed.), Language Engineering for Lesser-Studied Languages. IOS Press, pp. 183-206. pdf

The Boas knowledge elicitation strategy can be applied to other domains as well, as shown here on the example of clinical medicine.

Nirenburg, S., McShane, M., and Beale, S. 2010. Hybrid methods of knowledge elicitation within a unified representational knowledge scheme. In: Filipe, J. and Dietz, J.L.G. (Eds.) Proceedings of the International Conference on Knowledge Engineering and Ontology Development (KEOD 2010), pp. 177-192. SciTePress. pdf

One question that arises for cognitive modeling is, to what extent can models be automatically generated from print sources? We explore that question with respect to acquiring and dynamically modifying the physiological models supporting virtual patient simulation:

McShane, M., Nirenburg, S., Jarrell, B., and Fantry, G. 2015. Learning components of computational models from texts. In Finlayson, M. A., Miller, B., Lieto, A. and Ronfard, R. (Eds.), Proceedings of the 6th Workshop on Computational Models of Narrative (CMN'15), pp. 108-123. Published in the Open Access Series in Informatics [OASIcs], Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, Dagstuhl Publishing, Germany. pdf

Another question in the field of NLP is, How is human time best spent for knowledge acquistion? Although the mainstream answer is "annotating corpora in support of supervised machine learning," we suggest that the time would be better spent in building ontological and lexical resources to support systems that will automatically analyze (i.e., annotate) text.

McShane, M., Nirenburg, S., Beale, S. and O'Hara, T. 2005. Semantically rich human-aided machine annotation. Proceedings the Workshop on Frontiers in Corpus Annotation II: Pie in the Sky, pp. 68-75, at the 43rd Annual Meeting of the Association for Computational Linguistics (ACL-05). Stroudsburg, PA: Association for Computational Linguistics. pdf

3. Ontological Semantics

Much of my work since the early 2000s has been within the paradigm of Ontological Semantics, an approach to automatic language understanding that can be used either autonomously or as a component of an intelligent agent system. This section presents work on non-agent-oriented NLP -- which is, however, directly applicable to agent-oriented NLP.

Between approximately 2002 and 2015 I served as chief linguist and knowledge engineer in teams developing the OntoSem analysis system based on Ontological Semantics. The most comprehensive description of this system is in the following paper:

McShane, M., Nirenburg, S. and Beale, S. 2016. Language understanding with Ontological Semantics. Advances in Cognitive Systems 4:35-55. pdf

In Ontological Semantics, individual linguistic phenomena are treated by microtheories, some of which are described in the following papers. (Microtheories that more centrally involve agent modeling are presented in the next section.)

McShane, M., Beale, S. and Nirenburg, S. 2004. Some meaning procedures of Ontological Semantics. In Lino, M.T., Xavier, M.F., Ferreira, F., Costa, R., Silva, R. (Eds.), Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC-2004), pp. 1885-1888. Conference CD distributed by European Language Resources Association (ELRA), Paris, France. pdf

McShane, M., Beale, S. and Nirenburg, S. 2004. OntoSem methods for processing semantic ellipsis. In Moldovan, D. and Girju, R. (Eds.), Proceedings of HLT/NAACL 2004 Workshop on Computational Lexical Semantics, pp. 1-8. Stroudsburg, PA: Association for Computational Linguistics. pdf

McShane, M., Beale, S. and Nirenburg, S. 2006. The semantics of backing up (Or: What do to with prepositions and particles?). in Sutcliffe, G.C.J. and Goebel, R.G. (Eds.) Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference, Session on Trends in Natural Language Processing, pp. 770-775. pdf

McShane, M., Nirenburg, S. and Beale, S. 2015. The Ontological Semantic treatment of multiword expressions. Lingvisticæ Investigationes, 38(1): 73-110. John Benjamins Publishing Company.

Aspects of OntoSem system configuration, operation and evaluation are reported here:

Beale, S., Nirenburg, S. and McShane, M. 2003. Just-in-time grammar. Proceedings of the 2003 International Multiconference in Computer Science and Computer Engineering.

Nirenburg, S., McShane, M. and Beale, S. 2003. Enhancing recall in information extraction through ontological semantics. Proceedings of the Workshop on Ontologies and Information Extraction, Bucharest, Romania. pdf

Nirenburg, S., McShane, M. and Beale, S. 2003. Operative strategies in Ontological Semantics. Proceedings of HLT-NAACL-03 Workshop on Text Meaning, Edmonton, Alberta, Canada.

Nirenburg, S., Beale, S. and McShane, M. 2004. Evaluating the performance of the OntoSem semantic analyzer. In Hirst, G. and Nirenburg, S. (Eds.) Proceedings of the Second Workshop on Text Meaning Representation. Stroudsburg, PA: Association for Computational Linguistics, pp. 33-40. pdf

Nirenburg, S., McShane, M. and Beale, S. 2004. The rationale for building resources expressly for NLP. Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC 2004). European Language Resources Association. pdf

Beale, S., Lavoie, B., McShane, M., Nirenburg, S. and Korelsky, T. 2004. Question answering using Ontological Semantics. In Hirst, G. and Nirenburg, S. (Eds.) Proceedings of the Workshop on Text Meaning and Interpretation, pp. 41-48. Held in cooperation with the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-2004). Stroudsburg, PA: Association for Computational Linguistics. pdf

Java, A., Nirenburg, S., McShane, M., Finin, T., English, J. and Joshi, A. 2007. Using a natural language understanding system to generate Semantic Web content. International Journal on Semantic Web & Information Systems, 3(4): 50-74. pdf

Ontological Semantics is a language-neutral theory, so all work in this domain has multi-lingual applicability. The following papers focus on issues of multilinguality.

McShane, M., Nirenburg, S. and Beale, S. 2005. An NLP lexicon as a largely language independent resource. Machine Translation, 19(2): 139-173. pdf

McShane, M., Nirenburg, S. and Beale, S. 2004. OntoSem and SIMPLE: Two multi-lingual world views. Proceedings of the Second Workshop on Text Meaning and Interpretation. Held in cooperation with ACL-2004. Stroudsburg, PA: Association for Computational Linguistics, pp. 25-32. pdf

4. Language Understanding Within Overall Agent Cognition

Within agent systems, language serves one of many possible perceptive inputs (others being vision, interoception, haptics, non-speech audio, signals from sensors). Aspects of language processing that are strongly affected by overall agent cognition are described in the following papers:

Nirenburg, S., McShane, M. and Beale, S. 2005. Increasing understanding: Interpreting events of change. In Huang, C-R., Lenci, A. and Oltramari, A. (Eds.), Proceedings of the OntoLex Workshop at the Second International Joint Conference on Natural Language Processing (IJCNLP-05), pp. 43-52. Asian Federation of Natural Language Processing. pdf

Nirenburg, S., Beale, S., McShane, M., Jarrell, B. and Fantry, G. 2008. Language understanding in Maryland Virtual Patient. Proceedings of the Workshop on Speech Processing for Safety Critical Translations and Pervasive Applications at the 22nd Inernational Conference on Computational Linguistics (COLING 2008), pp. 36-39. pdf

McShane, M., Nirenburg, S., and Beale, S. 2008. Two kinds of paraphrase in modeling embodied cognitive agents. In Samsonovich, A. V. (Ed.), Biologically Inspired Cognitive Architectures: Papers from the AAAI Fall Symposium, pp. 162-167. AAAI Technical Report FS-08-04. Menlo Park, CA: AAAI Press. pdf

McShane, M., Nirenburg, S. and Beale, S. 2008. Ontology, lexicon and fact repository as leveraged to interpret events of change. In Huang, C., Calzolari, N., Gangemi, A., Lenci, A., Oltramari, A. and Prevot, L. (Eds.), Ontology and the Lexicon: A Natural Language Processing Perspective, pp. 98-121. Cambridge University Press. pdf

Nirenburg, S., McShane, M., and Beale, S. 2008. Resolving paraphrases to support modeling language perception in an intelligent agent. In Bos, J., Delmonte, R. (Eds.), Semantics in Text Processing: STEP 2008 Conference Proceedings, pp. 179-192. London: College Publications. pdf

McShane, M., and Nirenburg, S. 2009. Dialog modeling within intelligent agent modeling. In Jönsson, A., Alexandersson, J., Traum, D., Zukerman, I. (Eds.), Proceedings of the 6th IJCAI Workshop on Knowledge and Reasoning in Practical Dialog Systems. pp. 52-59. pdf

McShane, M., Beale, S., and Babkin, P. 2014. Nominal compound interpretation by intelligent agents. Linguistic Issues in Language Technology (LiLT), 10(1): 1-34. pdf

Reference and ellipsis have remained particular topics of interest for me throughout my career, as they are especially important for agent applications. The following papers are devoted to the realistic treatment of these essential but difficult and rarely treated phenomena.

McShane, M., Nirenburg, S. and Beale, S. 2005. Semantics-based resolution of fragments and underspecified structures. Traitement Automatique des Langues, 46(1): 163-184. pdf

McShane, M. 2009. Reference resolution challenges for an intelligent agent: The need for knowledge. IEEE Intelligent Systems, 24(4): 47-58. pdf

McShane, M., Beale, S., and Nirenburg, S. 2010. Reference resolution supporting lexical disambiguation. Proceedings of the Fourth IEEE International Conference on Semantic Computing, pp. 16-23. IEEE. pdf

McShane, M., Nirenburg, S., and Beale, S. 2011. Reference-related memory management in intelligent agents emulating humans. In: Langley, P. (Ed.), Advances in Cognitive Systems. Papers from the AAAI Fall Symposium, pp. 232-239. AAAI technical report FS-11-01. Menlo Park, CA: AAAI Press. 2011. pdf

McShane, M., Nirenburg, S., Beale, S. and Johnson, B. 2012. Resolving elided scopes of modality in OntoAgent. Advances in Cognitive Systems, 2: 95-112. pdf

McShane, M. and Nirenburg, S. 2013. Use of ontology, lexicon and fact repository for reference resolution in Ontological Semantics. In Oltramari, A., Vossen, P., Qin, L., Hovy, E. (Eds.), New Trends of Research in Ontologies and Lexical Resources. Springer. New Trends of Research in Ontologies and Lexical Resources, Theory and Applications of Natural Language Processing, pp. 157-185. pdf

I have also studied how to integrate decision-making about action into the process of language understanding. In the near term, agents will certainly not be able to fully understand every aspect of every imaginable utterance, but they can be configured to judge whether their current understanding is actionable, given their plans and goals in conjunction with their estimated confidence in what they have understood.

McShane, M. and Nirenburg, S. 2015. OntoAgents gauge their confidence in language understanding. In Ahmed, N., Cummings, M., and Mille, C. (Eds.), Self-Confidence in Autonomous Systems: Papers from the AAAI Fall Symposium. Technical report FS-15-05, pp. 22-29. Menlo Park, CA: AAAI Press. pdf

Nirenburg, S. and McShane, M. 2015. The interplay of language processing, reasoning and decision-making in cognitive computing. In Biemann, C., Handschuh, S., Freitas, A., Meziane, F., and Métais, E. (Eds.), Natural Language Processing and Information Systems, Proceedings of the 20th International Conference on Applications of Natural Language to Information Systems (NLDB 2015), pp. 167-179. Springer Lecture Notes in Computer Science 9103. pdf

McShane, M. and Nirenburg, S. 2015. Decision-making during language understanding by intelligent agents, pp. 310-319. Artificial General Intelligence, Volume 9205 of the series Lecture Notes in Computer Science. pdf

5. Cognitive Modeling Without a Language Emphasis

OntoAgents are intelligent agents that have a simulated and mind and, optionally, a simulated body. In the Maryland Virtual Patient (MVP) project, OntoAgents served as virtual patients and virtual tutors. The theoretical substrate and architecture of OntoAgent are discussed in the following publications. The most salient feature of OntoAgent is that it is a knowledge environment in which the same ontology and metalanguage of description are used for language processing, memory management, and reasoning.

Nirenburg, S., McShane, M. and Beale, S. 2008. A simulated physiological/cognitive "double agent". In Beal, J., Bello, P., Cassimatis, N., Coen, M. and Winston, P. (Eds.), Papers from the AAAI Fall Symposium "Naturally Inspired Cognitive Architectures". AAAI Technical Report FS-08-06. Menlo Park, CA: AAAI Press. pdf

Nirenburg, S., McShane, M., Beale, S. and Jarrell, B. 2008. Adaptivity in a multi-agent clinical simulation system. In Honkela, T., Pöllä, M., Paukkeri, M. And Simula, O. (Eds.), Proceedings of the 2nd International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR’08), pp. 32-39. Multiprint Espoo. pdf

McShane, M., S. Nirenburg, B. Jarrell, S. Beale, G. Fantry. 2009. Maryland Virtual Patient: A knowledge-based, language-enabled simulation and training system. Bio-Algorithms and Med-Systems: 5(9): 57-63. pdf

Nirenburg, S., McShane, M., Beale, S., Jarrell, B. and Fantry, G. 2009. Integrating cognitive simulation into the Maryland Virtual Patient. In Westwood, J. D., Westwood, S. W., et al. (Eds.), Medicine Meets Virtual Reality 17, pp. 224-229. In the series Studies in Health Technology and Informatics. Amsterdam, Berlin, Oxford, Tokyo, Washington, DC: IOS Press. pdf

Nirenburg, S., McShane, M. and Beale, S. 2009. A unified ontological-semantic substrate for physiological simulation and cognitive modeling. In Proceedings of the International Conference on Biomedical Ontology (ICBO-2009), 139-142. pdf

Nirenburg, S., McShane, M., Beale, S., English, J. and Catizone, R. 2010. Four kinds of learning in one agent-oriented environment. In Samsonovich, A.V., Jóhannsdóttir, K.R., Chella, A., Goertzel, B. (Eds.), Proceedings of the First International Conference on Biologically Inspired Cognitive, pp. 92-97. IOS Press. pdf

McShane, M. and Nirenburg, S. 2012. A knowledge representation language for natural language processing, simulation and reasoning. International Journal of Semantic Computing, 6(1): 3-23. pdf

Like people, intelligent agents must be able to infer the mental states of others, a process known as mindreading, or mental model ascription.

Nirenburg, S., McShane, M. and Beale, S. 2010. Aspects of metacognitive self-awareness in Maryland Virtual Patient. In Pirrone, R., Azevedo, R. and Biswas, G. (Eds.), Cognitive and Metacognitive Educational Systems: Papers from the AAAI Fall Symposium. AAAI Technical Report FS-10-01, pp. 69-74. Association for the Advancement of Artificial Intelligence. pdf

McShane, M., Nirenburg, S., Beale, S., Jarrell, B., Fantry, G. and Mallott, D. 2013. Mind-, body- and emotion-reading. Proceedings of the Annual Meeting of the International Association for Computing and Philosophy (IACAP 2013). pdf

McShane, M. 2014. Parameterizing mental model ascription across intelligent agents. Interaction Studies, 15(3): 404-425. pdf

Mindreading supports not only language understanding and decision-making, it can also support such advanced capabilities as detecting errors, lies, and decision-making biases.

McShane, M., Beale, S., Nirenburg, S., Jarrell, B. and Fantry, G. 2012. Inconsistency as a diagnostic tool in a society of intelligent agents. Artificial Intelligence in Medicine (AIIM), 55(3): 137-48. pdf

McShane, M., Nirenburg, S., and Jarrell, B. 2013. Modeling decision-making biases. Biologically-Inspired Cognitive Architectures (BICA) Journal, 3: 39-50. pdf

Ethical concerns related to intelligent agent development are discussed here:

Nirenburg, S. and McShane, M. 2012. Agents modeling agents: Incorporating ethics-related reasoning. Proceedings of the Symposium on Moral Cognition and Theory of Mind at the AISB/IACAP World Congress, 2012. pdf

The disease models to support interactive physiological simulation are described in the papers below. I collaborated with medical experts, on the one hand, and programmers, on the other, to develop these models.

McShane, M., Fantry, G., Beale, S., Nirenburg, S. and Jarrell, B. 2007. Disease interaction in cognitive simulations for medical training. In Proceedings of the MODSIM World Conference & Exposition, Virginia Beach. pdf

McShane, M., Nirenburg, S., Beale, S., Jarrell, B. and Fantry, G. 2007. Knowledge-based modeling and simulation of diseases with highly differentiated clinical manifestations. In Bellazzi, R., Abu-Hanna, A., Hunter, J. (Eds.) Proceedings of the 11th Conference on Artificial Intelligence in Medicine (AIME 07), pp. 34-43. Berlin, Heidelberg: Springer-Verlag. pdf

Jarrell, B., Nirenburg, S., McShane, M., Fantry, G., Beale, S., Mallott, D. and Razcek, J. 2007. An interactive, cognitive simulation of gastroesophageal reflux disease. In Medicine Meets Virtual Reality 15: in vivo, in vitro, in silico: Designing the Next in Medicine. In the series Studies in Health Technology and Informatics, Volume 125, pp. 194-199. pdf

McShane, M., Jarrell, B., Fantry, G., Nirenburg, S., Beale, S. and Johnson, B. 2008. Revealing the conceptual substrate of biomedical cognitive models to the wider community. In Westwood, J.D., Haluck, R.S., Hoffman, H.M., Mogel, G.T., Phillips, R., Robb, R.A. et al. (Eds.), Medicine Meets Virtual Reality 16: Parallel, combinatorial, convergent: NextMed by Design, pp. 281-286. Amsterdam; Berlin; Oxford; Tokyo; Washington, DC: IOS Press. pdf

McShane, M., Nirenburg, S., Jarrell, B., and Fantry, G. 2015. Learning components of computational models from texts. In Mark A. Finlayson, Ben Miller, Antonio Lieto, and Remi Ronfard (Eds.), Proceedings of the 6th Workshop on Computational Models of Narrative (CMN'15), pp. 108-123. Published in the Open Access Series in Informatics [OASIcs], Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, Dagstuhl Publishing, Germany. pdf

6. Non-Semantic Natural Langauge Processing

Although most of my work in NLP has involved semantic analysis, I have also explored treating difficult linguistic phenomena using non-semantic ("cheaper", incomplete, though still linguistically-informed) methods. Specifically, I have led the development of language analysis (sub)systems that detect and resolve verb phrase ellipsis as well difficult nominal referring expressions, such as the demonstrative pronouns this and that, which can refer to one or more propositions potentially realized as a span of text. I do not consider "surfacy" language processing a replacement for deep-semantic processing; instead, it is a useful tool as we work toward developing truly sophisticated intelligent agents.

McShane, M., and Babkin, P. 2015. Automatic ellipsis resolution: Recovering covert information from text. Proceedings of Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15), pp. 572-578. Association for the Advancement of Artificial Intelligence. pdf

McShane, M. 2015. Expectation-driven treatment of difficult referring expressions. Proceedings of the Third Annual Conference on Advances in Cognitive Systems (ACS-2015), Article 11. pdf

McShane, M., Nirenburg, S. and Babkin, P. 2015. Sentence trimming in service of verb phrase ellipsis resolution. Proceedings of the EuroAsianPacific Joint Conference on Cognitive Science (EAP CogSci 2015). Volume 1419 of CEUR Workshop Proceedings, CEUR-WS.org, pp. 228-233. pdf

McShane, M. and Babkin, P. Submitted (Sept. 2015). Automatically resolving difficult referring expressions. Advances in Cognitive Systems.

McShane, M. and Babkin, P. Submitted (Aug. 2015). Detection and resolution of verb phrase (often modal-scope) ellipsis. Linguistic Issues in Language Technology (LiLT).

7. Pedagogy

In working on the Boas knowledge elicitation system -- specifically, the induction of morphological analyzers -- I developed an approach to Polish inflection that I wished I'd had access to as a student of Polish. I found it more intuitive to represent Polish inflection for non-native speakers (as for computer systems) as many highly specific paradigms rather than very few paradigms subject to complex rule sets, as is typical of grammars of Polish. The pedagogically-oriented version of that work is found in my 2003 book and a more comprehensive manuscript:

McShane, M. 2003. An Innovative, Practical Approach to Polish Inflection. Lincom Europa. Preprint

McShane, Marjorie. 2001. Polish Inflection Fit for Man and Machine. Memoranda in Computer and Cognitive Science, MCCS-01-325. 221 pages. The Computing Research Laboratory, New Mexico State University. pdf

For shorter treatments of nominal and verbal inflection reflecting this approach, see, respectively:
McShane, M. 2001. One formal approach leads to another. Formal Approaches to Slavic Linguistics: The Bloomington Meeting, 2000. Ann Arbor, Michigan: Michigan Slavic Publications. pdf

McShane, M. 2002. Out of the box. In Janda, L.A., Franks, S. and Feldstein, R. (Eds.), Where One's Tongue Rules Well: A Festschrift for Charles E. Townsend. Indiana Slavic Studies 13: 147-155. pdf

The following article proposes that a more flexible notion of "paradigm" would foster student learning in a way that traditional paradigm tables do not. This work, too, stemmed from the research on knowledge elicitation for language processing.

McShane, M. 2003. Redefining "paradigm" for (computer-aided) language instruction. Foreign Language Annals, 36 (2): 198-207. pdf

The following suggest how methodologies developed for the Boas language eliciation system could be applied to pedagogy:

McShane, Marjorie, Ron Zacharski and Sergei Nirenburg. 2005. From knowledge elicitation system to teaching tool. Working Paper #04-05, Institute for Language and Information Technologies, University of Maryland Baltimore County. pdf

McShane, Marjorie and Ron Zacharski. 2005. User-extensible on-line lexicons for language learning. Working Paper #05-05, Institute for Language and Information Technologies, University of Maryland Baltimore County. pdf

8. Editing

In 2014, I served as Co-Chair of the 36th Annual Conference of the Cognitive Science Society and, accordingly, as Co-Editor of its proceedings.

In that year I also served as guest editor for a special issue of the journal Interaction Studies, entitled Mental Model Ascription by Intelligent Agents.

9. Miscellaneous

I was invited to write two entries in the Cambridge Encyclopedia of the Language Sciences:

McShane, M. 2010. Ambiguity. In Hogan, Patrick C. (Ed.), The Cambridge Encyclopedia of the Language Sciences. Cambridge University Press. pdf

McShane, M. 2010. Ellipsis. In Hogan, Patrick C. (Ed.), The Cambridge Encyclopedia of the Language Sciences. Cambridge University Press. pdf

The following describes the history of work on natural language processing, including the early split between the NLP and reasoning communities, which has yet to be bridged.
Nirenburg, S. and McShane, M. Forthcoming. Natural language processing. In Chipman, S. (Ed.), The Oxford Handbook of Cognitive Science.

Last updated: May 2016