Corpus ID: 55383367

Modal Sense Classification At Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations

  title={Modal Sense Classification At Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations},
  author={Ana Marasovi{\'c} and Mengfei Zou and Alexis Palmer and Anette Frank},
  journal={Linguistic Issues in Language Technology},
Modal verbs have different interpretations depending on their context. Their sense categories – epistemic, deontic and dynamic – provide important dimensions of meaning for the interpretation of discourse. Previous work on modal sense classification achieved relatively high performance using shallow lexical and syntactic features drawn from small-size annotated corpora. Due to the restricted empirical basis, it is difficult to assess the particular difficulties of modal sense classification and… Expand
Modal sense classification with task-specific context embeddings
A simple approach of modal sense classification is proposed in which standard shallow features are enhanced with task-specific context embedding features, and enriched contextual representations fed into a simple SVM model lead to significant classification gains over shallow feature sets. Expand
Modal sense classi fi cation with task-speci fi c context embeddings
Sense disambiguation of modal constructions is a crucial part of natural language understanding. Framed as a supervised learning task, this problem heavily depends on an adequate featureExpand
Classification of telicity using cross-linguistic annotation projection
This paper addresses the automatic recognition of telicity, an aspectual notion, and successfully leverage additional silver standard training data in the form of projected annotations from parallel English-Czech data as well as context information, improving automatic telicity classification for English significantly compared to previous work. Expand
The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing
It is shown that detecting and classifying modal expressions is not only feasible, but also improves the detection of modal events in their own right. Expand
Title Classifying sentential modality in legal language : A use case infinancial
Texts expressed in legal language are often di cult and time consuming for lawyers to read through, particularly for the purpose of identifying relevant deontic modalities (obligations, prohibitionsExpand
Learning modals: A grammatical perspective
This study addresses the mapping problem for modal words: how do children learn the form‐to‐ meaning mappings for words like could or have to in their input languages and focuses on new work highlighting the developmental roles of syntactic categories and interrelationships between modal ‘force’ and ‘flavour’. Expand
Classifying sentential modality in legal language: a use case in financial regulations, acts and directives
This paper outlines a data-driven approach by classifying deontic modalities using ensembled Artificial Neural Networks that incorporate domain specific legal distributional semantic model (DSM) representations, in combination with, a general DSM representation. Expand
The necessity modals have to, must, need to, and should
When an ambiguous lexical item appears within a familiar string of words, it can instantly receive an appropriate interpretation from this context, thus being saturated by it. Such a context mayExpand
Semantic clause types and modality as features for argument analysis1
The role of semantic clause types and modality in argumentative texts and their role in semantics is investigated in this article. Expand
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios
A structured overview of methods that enable learning when training data is sparse including mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision are given. Expand


Semantically Enriched Models for Modal Sense Classification
This work uncovers the difficulty of particular modal sense distinctions by eliminating both distributional bias and sparsity of existing small-scale annotated corpora used in prior work and builds a semantically enriched model for modalsense classification by novelly applying features that relate to lexical, proposition-level, and discourse-level semantic factors. Expand
Multilingual Modal Sense Classification using a Convolutional Neural Network
It is shown that CNNs are superior to manually designed feature-based classifiers and a standard NN classifier, and the feature maps learned by the CNN are analyzed to identify known and previously unattested linguistic features. Expand
Cross-linguistic annotation of modality: a data-driven hierarchical model
We present an annotation model of modality which is (i) cross-linguistic, relying on a wide, strongly typologically motivated approach, and (ii) hierarchical and layered, accounting for bothExpand
Automatic prediction of aspectual class of verbs in context
A semi-supervised approach using linguistically-motivated features and a novel set of distributional features based on representative verb types allows us to predict classes accurately, even for unseen verbs. Expand
Exploiting Hidden Meanings: Using Bilingual Text for Monolingual Annotation
This paper describes efforts to exploit larger quantities of data while still focusing on linguistically deeper problems such as parsing and word sense disambiguation, and takes advantage of the shared meaning hidden between the lines of sentences in parallel translation. Expand
Cross-lingual Annotation Projection for Semantic Roles
An experimental evaluation on an English-German parallel corpus is provided which demonstrates the feasibility of inducing high-precision German semantic role annotation both for manually and automatically annotated English data. Expand
Modality and Negation: An Introduction to the Special Issue
An overview of how modality and negation have been modeled in computational linguistics is provided. Expand
Cross-Genre and Cross-Domain Detection of Semantic Uncertainty
A unified subcategorization of semantic uncertainty as different domain applications can apply different uncertainty categories is introduced and the domain adaptation for training the models offer an efficient solution for cross-domain and cross-genre semantic uncertainty recognition. Expand
An Unsupervised Method for Word Sense Tagging using Parallel Corpora
An unsupervised method for word sense disambiguation that exploits translation correspondences in parallel corpora is presented, using pseudo-translations, created by machine translation systems, in order to make possible the evaluation of the approach against a standard test set. Expand
Bootstrapping parsers via syntactic projection across parallel texts
Using parallel text to help solving the problem of creating syntactic annotation in more languages by annotating the English side of a parallel corpus, project the analysis to the second language, and train a stochastic analyzer on the resulting noisy annotations. Expand