Semantically Enriched Models for Modal Sense Classification
نویسندگان
چکیده
Modal verbs have different interpretations depending on their context. Previous approaches to modal sense classification achieve relatively high performance using shallow lexical and syntactic features. In this work we uncover the difficulty of particular modal sense distinctions by eliminating both distributional bias and sparsity of existing small-scale annotated corpora used in prior work. We build a semantically enriched model for modal sense classification by novelly applying features that relate to lexical, proposition-level, and discourse-level semantic factors. Besides improved classification performance, especially for difficult sense distinctions, closer examination of interpretable feature sets allows us to obtain a better understanding of relevant semantic and contextual factors in modal sense classification.
منابع مشابه
Multilingual Modal Sense Classification using a Convolutional Neural Network
Modal sense classification (MSC) is a special WSD task that depends on the meaning of the proposition in the modal’s scope. We explore a CNN architecture for classifying modal sense in English and German. We show that CNNs are superior to manually designed feature-based classifiers and a standard NN classifier. We analyze the feature maps learned by the CNN and identify known and previously una...
متن کاملClassification of Modal Meaning in Negotiation Dialogues
This paper addresses modality classification for multi-issue bargaining dialogues in order to model human-like negotiation behaviour and to efficiently compute negotiation strategies. We propose a modality annotation and classification scheme comprising semantically distinguishable categories applied reliably by humans and machines. Our classification of modality varieties is based on both the ...
متن کاملInferring and evaluating semantic classes of verbs signaling modality
We infer semantic classes of verbs signaling modality from a purely syntactic classification of 637 German verbs by applying findings from linguistics about correspondences between verb meaning and syntax. Our extensive evaluation of the semantic classification is based on a linking to three other lexical resources at the word sense level: to the German wordnet GermaNet and to the English resou...
متن کاملHow textbooks (and learners) get it wrong: A corpus study of modal auxiliary verbs
Many elements contribute to the relative difficulty in acquiring specific aspects of English as a foreign language (Goldschneider & DeKeyser, 2001). Modal auxiliary verbs (e.g. could, might), are examples of a structure that is difficult for many learners. Not only are they particularly complex semantically, but especially in the Malaysian context ...
متن کاملPersonalised and Context-based Access to Corporate Knowledge: a Multi-modal and Multi-model Solution Approach for Learning Activities
This paper focuses on two technological aspects. Firstly, the MISTRAL system is briefly introduced in order to give some insights into one possible way of gaining and managing multi-modal information that is extracted from a meeting corpus and semantically enriched. And secondly, a multi-model approach is analysed and explained for the purpose of enabling different personalised and context-depe...
متن کامل