Learn to Describe Objects the way ‘Ordinary’ People Do by Using Language Technology
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Speaking consists to a large extend in making statements about objects: ‘”The babyis asleep”, “The gameis over”, etc. Yet objects can be described in many ways: it, the library, the first building to the right, etc. The way how an object is described or referred to depends to a large extent on the context, i.e. the set of elements (physically or mentally present in the listeners mind) with which the target can be confused (think of different kind of round objects you can purchase in a sporting goods retail store). Hence, the question: how does a speakers decide on the information to convey (content) and on the linguistic resource to use (expression)? This implies among other things pragmatic knowledge, which is often learned on the basis of correlations. People realize that changes of the situation often reflect in language: different inputs (ideas, objects of a scene) yielding different outputs, i.e. linguistic forms. We present here a setting that allows for this kind of learning. It is a web-based application that generates a scene and various descriptions of its components. Users can change the scene and watch how these choices affect (or not) the linguistic form. The descriptions are produced in English and French, and they are rated in terms of communicative adequacy. This should allow students not only to learn to produce correct sentences, but also help them to realize which one of them is, communicatively speaking, the most adequate form.
Abstract
Speaking consists to a large extend in making statements about objects: ‘”The babyis asleep”, “The gameis over”, etc. Yet objects can be described in many ways: it, the library, the first building to the right, etc. The way how an object is described or referred to depends to a large extent on the context, i.e. the set of elements (physically or mentally present in the listeners mind) with which the target can be confused (think of different kind of round objects you can purchase in a sporting goods retail store). Hence, the question: how does a speakers decide on the information to convey (content) and on the linguistic resource to use (expression)? This implies among other things pragmatic knowledge, which is often learned on the basis of correlations. People realize that changes of the situation often reflect in language: different inputs (ideas, objects of a scene) yielding different outputs, i.e. linguistic forms. We present here a setting that allows for this kind of learning. It is a web-based application that generates a scene and various descriptions of its components. Users can change the scene and watch how these choices affect (or not) the linguistic form. The descriptions are produced in English and French, and they are rated in terms of communicative adequacy. This should allow students not only to learn to produce correct sentences, but also help them to realize which one of them is, communicatively speaking, the most adequate form.
참고문헌 (19)
- Appelt, D., "Planning English Referring Expressions" (1985), Cambridge University Press
- Bateman J, "Handbook of Computational Linguistics" (2015), Oxford University Press
- Berko, J., "The child's learning of English morphology", Word, (14), pp.150~177 (1958)
- Briffault, X., "What do we mean when we say to the left of to the right? How to learn about space by building and exploring a microworld?", Proceedings of the 6th International Conference on Artificial Intelligence: Methodology, Systems, Applications, pp.363~371 (1994)
- Dale, R., "Generating Referring Expressions: Constructing Descriptions in a Domain of Objects and Processes" (1992), MIT Press
- Dale, R., "Computational interpretations of the Gricean maxims in the generation of referring expressions", Cognitive Science, 19(2), pp.233~263 (1995)
- Davey, A., "Discourse Production" (1978), Edinburgh University Press
- Gatt, A., "The TUNA-REG challenge 2009 :Overview and evaluation results", ENLG ’09: Proceedings of the 12th European Workshop on Natural Language Generation, pp.174~182 (2009)
- Gregory, R., "Eye and Brain: The Psychology of Seeing" (1966), McGraw Hill
- Grice, P., "Syntax and Semantics, 3:Speech Acts" (1975), Academic Press
- Krahmer, E., "Computational generation of referring expressions: A survey", Computational Linguistics, 38(1), pp.173~218 (2012)
- Krahmer, E., "Graph-based generation of referring expressions", Computational Linguistics, 29(1), pp.53~72 (2003)
- Matthews, D. E., "How toddlers and preschoolers learn to uniquely identify referents for others: A training study", Child Development, 78(6), pp.1744~1759 (2007)
- Olson D. R., "Language and Thought: Aspects of a Cognitive Theory of Semantics", Psychological Review, 77, pp.257~273 (1970)
- Pechmann, T., "Incremental speech production and referential overspecification", Linguistics, 27, pp.89~110 (1989)
- Reiter, E., "Current research in natural language generation", pp.257~285 (1990), Academic Press
- van Deemter, K, "Towards a computational psycholinguistics of reference production", Topics in Cognitive Science, 4(2), pp.166~183 (2012)
- van Deemter, K., "Building a semantically transparent corpus for the generation of referring expressions", INLG ’06: Proceedings of the Fourth International Natural Language Generation Conference, pp.130~132 (2006)
- "WebREG: un outil pour apprendre les expressions référentielles" (2010)[URL]