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.

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 An HPSG approach to English comparative inversion

2012 ◽  
Author(s):  
Dong-woo Park
Keyword(s):  
Word Order ◽  
Special Kind ◽  
Verb Phrase ◽  
Auxiliary Verbs ◽  
The Subject ◽  
Auxiliary Verb ◽  
Order Domain

It has been analyzed that the word order of English comparative inversion is analogous to that of other subject-auxiliary inversions in that only a finite auxiliary verb can be followed by the subject. However, English comparative inversion should be distinguished from other inversions because the subject can be located between a cluster of auxiliary verbs and the non-auxiliary verb phrase in English comparative inversion. Existing analyses on subject-auxiliary inversion cannot account for this special kind of inversion. This paper proposes a new phrase type for English comparative inversion within the construction-based HPSG. In addition, I suggest that constraints on properties of lexemes participating in the new phrase type are governed by the construction-based approach, while the word order of English comparative inversion is determined by rules that the word order domain approach adopts. Also, it will be shown that these proposals can capture the word order of nor-inversion, as-inversion, and so-inversion as well as that of comparative inversion.

scholarly journals Video-Based Person Re-Identification by an End-To-End Learning Architecture with Hybrid Deep Appearance-Temporal Feature

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3669 ◽  
Author(s):  
Rui Sun ◽  
Qiheng Huang ◽  
Miaomiao Xia ◽  
Jun Zhang
Keyword(s):  
Feature Representation ◽  
Visual Sensor ◽  
Stream Structure ◽  
Temporal Features ◽  
Feature Structure ◽  
End To End ◽  
Global And Local ◽  
Siamese Networks ◽  
Appearance Feature ◽  
Temporal Feature

Video-based person re-identification is an important task with the challenges of lighting variation, low-resolution images, background clutter, occlusion, and human appearance similarity in the multi-camera visual sensor networks. In this paper, we propose a video-based person re-identification method called the end-to-end learning architecture with hybrid deep appearance-temporal feature. It can learn the appearance features of pivotal frames, the temporal features, and the independent distance metric of different features. This architecture consists of two-stream deep feature structure and two Siamese networks. For the first-stream structure, we propose the Two-branch Appearance Feature (TAF) sub-structure to obtain the appearance information of persons, and used one of the two Siamese networks to learn the similarity of appearance features of a pairwise person. To utilize the temporal information, we designed the second-stream structure that consisting of the Optical flow Temporal Feature (OTF) sub-structure and another Siamese network, to learn the person’s temporal features and the distances of pairwise features. In addition, we select the pivotal frames of video as inputs to the Inception-V3 network on the Two-branch Appearance Feature sub-structure, and employ the salience-learning fusion layer to fuse the learned global and local appearance features. Extensive experimental results on the PRID2011, iLIDS-VID, and Motion Analysis and Re-identification Set (MARS) datasets showed that the respective proposed architectures reached 79%, 59% and 72% at Rank-1 and had advantages over state-of-the-art algorithms. Meanwhile, it also improved the feature representation ability of persons.

scholarly journals The Meanings of Modal Auxiliary Verbs in the Movie "The Perks of being a Wallflower"

Lexicon ◽  
2018 ◽  
Vol 2 (2) ◽  
Author(s):  
Herlina Endah Atmaja
Keyword(s):  
Data Analysis ◽  
Auxiliary Verbs ◽  
Auxiliary Verb

This research attempts to investigate the meanings of modal auxiliary verbs in the movie The Perks of being a Wallflower. In particular, it aims to identify and classify the modal auxiliary verbs according to their meanings. The data used in this research were dialogues containing modal auxiliary verbs. The modal auxiliary verbs are analyzed semantically and pragmatically. Based on the data analysis, 171 modal auxiliary verbs were found in the movie. The most commonly used modal auxiliary verb in the movie is the modal auxiliary will (28.7%), followed by can (24.0%), would (21.6%), could (14.0%), should (7.0%), might (2.9%), and must (1.8%). From the 171 modal auxiliary verbs, 43 (25.1%) are used to express epistemic meanings, 23 (13.4%) are used to express deontic meanings, and 105 (61.3%) are used to express dynamic meanings. It was found in this research that the modal auxiliary verbs are most frequently used to express dynamic meanings.

scholarly journals An End-to-End Trainable Multi-Column CNN for Scene Recognition in Extremely Changing Environment

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1556 ◽  
Author(s):  
Zhenyu Li ◽  
Aiguo Zhou ◽  
Yong Shen
Keyword(s):  
Receptive Fields ◽  
Scene Recognition ◽  
Feature Representation ◽  
Learning Technology ◽  
Image Perception ◽  
Front End ◽  
Novel Approach ◽  
Layer Image ◽  
Retrieval Problem ◽  
End To End

Scene recognition is an essential part in the vision-based robot navigation domain. The successful application of deep learning technology has triggered more extensive preliminary studies on scene recognition, which all use extracted features from networks that are trained for recognition tasks. In the paper, we interpret scene recognition as a region-based image retrieval problem and present a novel approach for scene recognition with an end-to-end trainable Multi-column convolutional neural network (MCNN) architecture. The proposed MCNN utilizes filters with receptive fields of different sizes to have Multi-level and Multi-layer image perception, and consists of three components: front-end, middle-end and back-end. The first seven layers VGG16 are taken as front-end for two-dimensional feature extraction, Inception-A is taken as the middle-end for deeper learning feature representation, and Large-Margin Softmax Loss (L-Softmax) is taken as the back-end for enhancing intra-class compactness and inter-class-separability. Extensive experiments have been conducted to evaluate the performance according to compare our proposed network to existing state-of-the-art methods. Experimental results on three popular datasets demonstrate the robustness and accuracy of our approach. To the best of our knowledge, the presented approach has not been applied for the scene recognition in literature.

scholarly journals A Customized Deep Neural Network Approach to Investigate Travel Mode Choice with Interpretable Utility Information

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Zhengchao Zhang ◽  
Congyuan Ji ◽  
Yineng Wang ◽  
Yanni Yang
Keyword(s):  
Neural Network ◽  
Learning Community ◽  
Mode Choice ◽  
Feature Representation ◽  
Classification Problems ◽  
Neural Network Approach ◽  
Nonlinear Fitting ◽  
Linear Utility ◽  
Utility Models ◽  
Fully Connected

Discrete choice modeling of travel modes is an essential part of traffic planning and management. Thus far, this field has been dominated by multinomial logit (MNL) models with a linear utility specification. However, deep neural networks (DNNs), owing to their powerful capacity of nonlinear fitting, are now rapidly replacing these models. This is because, by using DNNs, mode choice can be assimilated with the classification problems within the machine learning community. This article proposes a newly designed DNN framework for traffic mode choice in the style of two hidden layers. First, a local-connected layer automatically extracts an effective utility specification from the available data, and then, a fully connected layer augments the feature representation. Validated by a practical city-wide multimodal traffic dataset in Beijing, our model significantly outperforms the random utility models and simple fully connected neural network in terms of the prediction accuracy. Besides the comparison of the predictive power, we also present the interpretability of the proposed model.

Lemmatization of compound tenses in English

1999 ◽  
Vol 22 (1-2) ◽  
pp. 71-122
Author(s):  
Maurice Gross
Keyword(s):  
Modal Verbs ◽  
Auxiliary Verbs ◽  
Finite State ◽  
Compound Verbs ◽  
Auxiliary Verb

We generalize the process of lemmatization of verbs to their compound tenses. Usually, lemmatization is limited on verbs conjugated by means of suffixes; tense auxiliaries and modal verbs (e.g. I have left, I am leaving, I could leave) are ignored. We have constructed a set of 83 finite-state grammars which parse auxiliary verbs and thus recognizes the ‘head verb’, that is, the lemma. We generalize the notion of auxiliary verb to verbs with sentential complements which have transformed constructions (e.g. I want to go) that can be parsed in exactly the same way as tense auxiliaries or modal verbs. Ambiguities arise, in particular because adverbial inserts occur inside the compound verbs,. We show how local grammars describing nominal contexts can be used to reduce the degree of ambiguity.

scholarly journals The Distribution of the Perfect Auxiliaries be/have in Middle English Texts

2018 ◽  
pp. 33-46
Author(s):  
Katarzyna Alicja Zdziera
Keyword(s):  
Simple Model ◽  
Middle English ◽  
16Th Century ◽  
Auxiliary Verbs ◽  
15Th Century ◽  
Verbs Of Motion ◽  
Verb Phrases ◽  
Main Factors ◽  
Germanic Languages

Like many Germanic languages, English has developed specific periphrastic constructions to express perfective meaning. Before being fully grammaticalized in the 16th century, they were used occasionally in Old and Middle English as complex verb phrases with either habban ‘to have’ or beon/wesan ‘to be’ acting as auxiliary verbs. By the Modern English period, forms created with be disappeared from the language and were almost completely replaced by forms with have, a process which did not occur, for instance, in German. As the data on this development are quite scarce, a relatively simple model is assumed with a steady diachronic progress towards the system established in Modern English, a model which disregards synchronic variation. This paper attempts to investigate the distribution of the perfective constructions with be and have, especially in the 15th century texts and to identify the main factors accounting for diff erences in their usage. Instead of taking into account only the diachronic aspect of the development described, the present study focuses mainly on investigating the synchronic variation in the auxiliaries used with the two most frequent verbs of motion, namely come and go in the perfective meaning.

Sign in / Sign up

Export Citation Format

Share Document