Christiane Fellbaum

WordNet : an electronic lexical database

Part 1 The lexical database: nouns in WordNet, George A. Miller modifiers in WordNet, Katherine J. Miller a semantic network of English verbs, Christiane Fellbaum design and implementation of the WordNet lexical database and searching software, Randee I. Tengi. Part 2: automated discovery of WordNet relations, Marti A. Hearst representing verb alterations in WordNet, Karen T. Kohl et al the formalization of WordNet by methods of relational concept analysis, Uta E. Priss. Part 3 Applications of WordNet: building semantic concordances, Shari Landes et al performance and confidence in a semantic annotation task, Christiane Fellbaum et al WordNet and class-based probabilities, Philip Resnik combining local context and WordNet similarity for word sense identification, Claudia Leacock and Martin Chodorow using WordNet for text retrieval, Ellen M. Voorhees lexical chains as representations of context for the detection and correction of malapropisms, Graeme Hirst and David St-Onge temporal indexing through lexical chaining, Reem Al-Halimi and Rick Kazman COLOR-X - using knowledge from WordNet for conceptual modelling, J.F.M. Burg and R.P. van de Riet knowledge processing on an extended WordNet, Sanda M. Harabagiu and Dan I Moldovan appendix - obtaining and using WordNet.

Semantic networks of English

Principles of lexical semantics developed in the course of building an on-line lexical database are discussed. The approach is relational rather than componential. The fundamental semantic relation is synonymy, which is required in order to define the lexicalized concepts that words can be used to express. Other semantic relations between these concepts are then described. No single set of semantic relations or organizational structure is adequate for the entire lexicon: nouns, adjectives, and verbs each have their own semantic relations and their own organization determined by the role they must play in the construction of linguistic messages.

Making fine-grained and coarse-grained sense distinctions, both manually and automatically

In this paper we discuss a persistent problem arising from polysemy: namely the difficulty of finding consistent criteria for making fine-grained sense distinctions, either manually or automatically. We investigate sources of human annotator disagreements stemming from the tagging for the English Verb Lexical Sample Task in the Senseval-2 exercise in automatic Word Sense Disambiguation. We also examine errors made by a high-performing maximum entropy Word Sense Disambiguation system we developed. Both sets of errors are at least partially reconciled by a more coarse-grained view of the senses, and we present the groupings we use for quantitative coarse-grained evaluation as well as the process by which they were created. We compare the system’s performance with our human annotator performance in light of both fine-grained and coarse-grained sense distinctions and show that well-defined sense groups can be of value in improving word sense disambiguation by both humans and machines.

A semantic network of English: the mother of all WordNets

We give a brief outline of the design and contents of the English lexical database WordNet, which serves as a model for similarly conceived wordnets in several European languages. WordNet is a semantic network, in which the meanings of nouns, verbs, adjectives, and adverbs are represented in terms of their links to other (groups of) words via conceptual-semantic and lexical relations. Each part of speech is treated differently reflecting different semantic properties. We briefly discuss polysemy in WordNet, and focus on the case of meaning extensions in the verb lexicon. Finally, we outline the potential uses of WordNet not only for applications in natural language processing, but also for research in stylistic analyses in conjunction with a semantic concordance.

WordNet then and now

We briefly discuss the origin and development of WordNet, a large lexical database for English. We outline its design and contents as well as its usefulness for Natural Language Processing. Finally, we discuss crosslinguistic WordNets and complementary lexical resources.

SemEval-2010 Task 17: All-words Word Sense Disambiguation on a Specific Domain

Domain portability and adaptation of NLP components and Word Sense Disambiguation systems present new challenges. The difficulties found by supervised systems to adapt might change the way we assess the strengths and weaknesses of supervised and knowledge-based WSD systems. Unfortunately, all existing evaluation datasets for specific domains are lexical-sample corpora. This task presented all-words datasets on the environment domain for WSD in four languages (Chinese, Dutch, English, Italian). 11 teams participated, with supervised and knowledge-based systems, mainly in the English dataset. The results show that in all languages the participants where able to beat the most frequent sense heuristic as estimated from general corpora. The most successful approaches used some sort of supervision in the form of hand-tagged examples from the domain.

George a. miller

George Armitage Miller died on July 22, 2012, at the age of ninety-two. He led a rich life full of accomplishments in the three areas of activity that he had chosen as a young man: psychology, writing, and golf. Miller was not only a witness but a key player in the major paradigm shift of the 20th century that came to be known as the cognitive revolution. Incredible as it may seem today, his teachers at Harvard followed the behaviorist dogma and recognized neither the autonomy nor the significance of the human mind. It took two courageous young scientists—George Miller and Jerome Bruner—to assert, each in their own domain of investigation, that the mind is a worthwhile subject of study. They started out by teaching a course boldly entitled “Cognition” and eventually established the Center for Cognitive Studies, ultimately making behaviorism obsolete. Miller drew an analogy between the human mind and a computer, noting that both store and process huge amounts of information. At the same time, human shortterm memory is limited, as his most celebrated paper on the “Magical Number Seven” demonstrates (Miller 1956/1994). Miller showed that chunking information into meaningful units helps recall, though the number of units that can be memorized seems to hover around seven. For example, U.S. telephone numbers are broken down into three groups of three, three, and four digits (area code, local exchange, and individual number). Chunk parsers (Abney 1991) build on the idea that sentence processing proceeds in phrases, reflected in prosodic patterns. Among our cognitive faculties, it was language in particular that fascinated George, a gifted writer. One attraction was that linguistic behavior could be observed, tested, and evaluated quantitatively with the experimental paradigms available to psycholinguists at a time when brain imaging techniques had not yet been developed. The rules of language, with their recursive aspects, could be seen as a kind of program. Although he collaborated with Noam Chomsky on the formal aspects of language, Miller in later life harbored a suspicion of highly abstract theories of syntax. His interest lay primarily in the lexicon, not only because of his authorial love of words, but also because of its size, open-endedness, and dynamic aspects. Moreover, the growth of children’s lexicons offered a window into their cognitive development. Miller is probably best known to readers of Computational Linguistics for his creation of the large lexical database WordNet (Miller 1995). WordNet’s use as a resource for natural language processing was in fact unintended, and its rapid adoption by the NLP community came as a surprise. George was interested in human semantic organization and wanted to test the then-fashionable concept of semantic networks, which allowed for plausible and elegant models of semantic representation and seemed supported by experiments testing lexical access and retrieval (Collins and Quillian 1969). Miller wondered whether a semantic network could in fact be built for the bulk of the English lexicon. In the mid 1980s, he recruited a group of colleagues, students, and his wife Kitty and, without much further instruction, asked them to cluster nouns, verbs, and

On the Role of Lexical and World Knowledge in RTE3

To score well in RTE3, and even more so to create good justifications for entailments, substantial lexical and world knowledge is needed. With this in mind, we present an analysis of a sample of the RTE3 positive entailment pairs, to identify where and what kinds of world knowledge are needed to fully identify and justify the entailment, and discuss several existing resources and their capacity for supplying that knowledge. We also briefly sketch the path we are following to build an RTE system (Our implementation is very preliminary, scoring 50.9% at the time of RTE). The contribution of this paper is thus a framework for discussing the knowledge requirements posed by RTE and some exploration of how these requirements can be met.

Towards Open Data for Linguistics: Linguistic Linked Data

‘Open Data’ has become very important in a wide range of fields. However for linguistics, much data is still published in proprietary, closed formats and is not made available on the web. We propose the use of linked data principles to enable language resources to be published and interlinked openly on the web, and we describe the application of this paradigm to the modeling of two resources, WordNet and the MASC corpus. Here, WordNet and the MASC corpus serve as representative examples for two major classes of linguistic resources, lexical-semantic resources and annotated corpora, respectively.Furthermore, we argue that modeling and publishing language resources as linked data offers crucial advantages as compared to existing formalisms. In particular, it is explained how this can enhance the interoperability and the integration of linguistic resources. Further benefits of this approach include unambiguous identifiability of elements of linguistic description, the creation of dynamic, but unambiguous links between different resources, the possibility to query across distributed resources, and the availability of a mature technological infrastructure. Finally, recent community activities are described.

Putting Semantics into WordNet's Morphosemantic Links

To add to WordNets contents, and specifically to aid automatic reasoning with WordNet, we classify and label the current relations among derivationally and semantically related noun-verb pairs. Manual inspection of thousands of pairs shows that there is no one-to-one mapping of form and meaning for derivational affixes, which exhibit far less regularity than expected. We determine a set of semantic relations found across a number of morphologically defined noun-verb pair classes.