scholarly journals Detection and Resolution of Verb Phrase Ellipsis

2016 ◽  
Vol 13 ◽  
Author(s):  
Marjorie McShane ◽  
Petr Babkin
Keyword(s):  
Real World ◽  
High Confidence ◽  
Verb Phrase Ellipsis ◽  
Verb Phrase ◽  
Auxiliary Verbs ◽  
Modal Auxiliaries ◽  
Vp Ellipsis ◽  
Build Systems

Verb phrase (VP) ellipsis is the omission of a verb phrase whose meaning can be reconstructed from the linguistic or real-world context. It is licensed in English by auxiliary verbs, often modal auxiliaries: She can go to Hawaii but he can’t [e]. This paper describes a system called ViPER (VP Ellipsis Resolver) that detects and resolves VP ellipsis, relying on linguistic principles such as syntactic parallelism, modality correlations, and the delineation of core vs. peripheral sentence constituents. The key insight guiding the work is that not all cases of ellipsis are equally difficult: some can be detected and resolved with high confidence even before we are able to build systems with human-level semantic and pragmatic understanding of text.

scholarly journals A Neural Network Approach to Verb Phrase Ellipsis Resolution

2019 ◽  
Vol 33 ◽  
pp. 7468-7475
Author(s):  
Wei-Nan Zhang ◽  
Yue Zhang ◽  
Yuanxing Liu ◽  
Donglin Di ◽  
Ting Liu
Keyword(s):  
Feature Representation ◽  
Neural Models ◽  
Neural Network Approach ◽  
Verb Phrase Ellipsis ◽  
Verb Phrase ◽  
Auxiliary Verbs ◽  
Verb Phrases ◽  
Automatic Composition ◽  
End To End ◽  
Auxiliary Verb

Verb Phrase Ellipsis (VPE) is a linguistic phenomenon, where some verb phrases as syntactic constituents are omitted and typically referred by an auxiliary verb. It is ubiquitous in both formal and informal text, such as news articles and dialogues. Previous work on VPE resolution mainly focused on manually constructing features extracted from auxiliary verbs, syntactic trees, etc. However, the optimization of feature representation, the effectiveness of continuous features and the automatic composition of features are not well addressed. In this paper, we explore the advantages of neural models on VPE resolution in both pipeline and end-to-end processes, comparing the differences between statistical and neural models. Two neural models, namely multi-layer perception and the Transformer, are employed for the subtasks of VPE detection and resolution. Experimental results show that the neural models outperform the state-of-the-art baselines in both subtasks and the end-to-end results.

NATIVE SPEAKERS’ VERSUS L2 LEARNERS’ SENSITIVITY TO PARALLELISM IN VP-ELLIPSIS

2009 ◽  
Vol 31 (1) ◽  
pp. 93-123 ◽  
Author(s):  
Nigel G. Duffield ◽  
Ayumi Matsuo
Keyword(s):  
Second Language ◽  
Native Speakers ◽  
Verb Phrase Ellipsis ◽  
Verb Phrase ◽  
L2 Learners ◽  
Cast Doubt ◽  
Vp Ellipsis

This article examines sensitivity to structural parallelism in verb phrase ellipsis constructions in English native speakers as well as in three groups of advanced second language (L2) learners. The results of a set of experiments, based on those of Tanenhaus and Carlson (1990), reveal subtle but reliable differences among the various learner groups. These differences are interpreted as showing that some L2 learners can acquire sensitivity to parallelism in the absence of surface transfer. Furthermore, the results cast doubt on two conventional theoretical claims: that the parallelism effect has a syntactic basis and that it is uniquely linked to instances of surface anaphora (Hankamer & Sag, 1976).

Ellipsis in Categorial Grammar

2018 ◽  
pp. 121-141
Author(s):  
Pauline Jacobson
Keyword(s):  
Categorial Grammar ◽  
Transitive Verb ◽  
Discourse Context ◽  
Verb Phrase Ellipsis ◽  
Verb Phrase ◽  
Fragment Answers ◽  
Vp Ellipsis ◽  
The Common ◽  
Special Case ◽  
Linguistic Material

One of the fundamental tenets of (most versions of) Categorial Grammar is that the syntax and semantics work ‘in tandem’: the syntax proves expressions well-formed while the semantics assigns them a meaning. Under this view (termed Direct Compositionality), it is difficult at best to state a rule deleting or silencing material under identity with some other overt linguistic material in the discourse context, which suggests that the common wisdom that there is ‘silent linguistic material’ is incorrect. This chapter explores an alternative way to view VP-ellipsis without silent linguistic material. Using conventions developed in earlier work within variable-free semantics and Direct Compositionality, it is shown that such an approach extends immediately to Antecedent Contained Deletion (which is just a special case of ‘transitive verb phrase ellipsis’) as well as to pseudogapping. The chapter also briefly explores the analysis of fragment answers to questions without invoking silent linguistic material, and shows that some of the apparent challenges to this view are in fact not real challenges.

scholarly journals Exploring the steps of Verb Phrase Ellipsis

2016 ◽  
Author(s):  
Zhengzhong Liu ◽  
Edgar Gonzàlez Pellicer ◽  
Daniel Gillick
Keyword(s):  
Verb Phrase Ellipsis ◽  
Verb Phrase

scholarly journals A CONTRASTIVE ANALYSIS OF SIMPLE SENTENCES IN ENGLISH AND JAVANESE LANGUAGE

2018 ◽  
Vol 1 (2) ◽  
Author(s):  
Fitriyani Fitriyani ◽  
D.P. Ramendra ◽  
I.W. Swandana
Keyword(s):  
Qualitative Research ◽  
Major Elements ◽  
Contrastive Analysis ◽  
Simple Sentence ◽  
Verb Phrase ◽  
Auxiliary Verbs ◽  
Similarities And Differences ◽  
English Textbooks ◽  
Simple Sentences ◽  
Action Verbs

This research studied about English and Javanese simple sentences which aimed to find the similarities and differences between English simple sentences and Javanese language. This study is descriptive qualitative research that applied contrastive analysis as the methodology. The data were taken from English textbooks and Javanese magazines. The results of this study showed there were similarities and differences in English and Javanese language simple sentences. The similarities were (1) some of simple sentence have similar patterns were SP for verbal sentence and SPO patterns. (2) the major elements were subject and predicator. The differences were (1) Javanese language had SP pattern for nominal, adjectival, prepositional, and numeral sentence. While in English there was no pattern. (2) In English, predicator must be in verb phrase: auxiliary verbs, linking verbs, or action verbs. However, In Javanese language, the predicator of a sentence might be in verb phrase, adjectival phrase, and prepositional phrase.

scholarly journals THE TRANSLATION OF ELLIPSIS AND EVENT REFERENCE IN JK ROWLING'S HARRY POTTER AND THE GOBLET OF FIRE

2016 ◽  
Vol 3 (1) ◽  
Author(s):  
Adi Loka Sujono
Keyword(s):  
Content Analysis ◽  
Qualitative Content Analysis ◽  
Harry Potter ◽  
Analysis Method ◽  
Verb Phrase Ellipsis ◽  
Verb Phrase ◽  
Literal Translation ◽  
Content Analysis Method

<p>The study aims to investigate the translation of ellipsis and event reference in JK Rowling‘s‘ Harry Potter and the Goblet of Fire. In this present study, a qualitative content analysis method was employed. In translating the ellipsis and event reference, semantic and syntactic referents should be taken into account. Concerning with reference to eventualities, three forms of referents namely verb phrase ellipsis, so anaphora and pronominal event reference are analysed. Some adjustments such as literal translation, explicitation, omission, and the like are made.</p>

scholarly journals Partial Label Learning with Self-Guided Retraining

2019 ◽  
Vol 33 ◽  
pp. 3542-3549 ◽  
Author(s):  
Lei Feng ◽  
Bo An
Keyword(s):  
Real World ◽  
Optimization Problem ◽  
State Of The Art ◽  
Ground Truth ◽  
Learning Approaches ◽  
High Confidence ◽  
Infinity Norm ◽  
Real World Datasets ◽  
Partial Label Learning ◽  
Optimization Efficiency

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with partially labeled examples. Specifically, we propose a unified formulation with proper constraints to train the desired model and perform pseudo-labeling jointly. For pseudo-labeling, unlike traditional self-training that manually differentiates the ground-truth label with enough high confidence, we introduce the maximum infinity norm regularization on the modeling outputs to automatically achieve this consideratum, which results in a convex-concave optimization problem. We show that optimizing this convex-concave problem is equivalent to solving a set of quadratic programming (QP) problems. By proposing an upper-bound surrogate objective function, we turn to solving only one QP problem for improving the optimization efficiency. Extensive experiments on synthesized and real-world datasets demonstrate that the proposed approach significantly outperforms the state-of-the-art partial label learning approaches.

Sign in / Sign up

Export Citation Format

Share Document