Language Sentences Research Articles

WiSign

In this article, we propose WiSign that recognizes the continuous sentences of American Sign Language (ASL) with existing WiFi infrastructure. Instead of identifying the individual ASL words from the manually segmented ASL sentence in existing works, WiSign can automatically segment the original channel state information (CSI) based on the power spectral density (PSD) segmentation method. WiSign constructs a five-layer Deep Belief Network (DBN) to automatically extract the features of isolated fragments, and then uses the Hidden Markov Model (HMM) with Gaussian mixture and Forward-Backward algorithm to recognize sign words. In order to further improve the accuracy, WiSign also integrates the language model N-gram, which uses the grammar rules of ASL to calibrate the recognized results of sign words. We implement a prototype of WiSign with commercial WiFi devices and evaluate its performance in real indoor environments. The results show that WiSign achieves satisfactory accuracy when recognizing ASL sentences that involve the movements of the head, arms, hands, and fingers.

The Duration of Pauses between Phrases in Reading Language

The aim of this research is to determine the duration of the pauses between paragraphs and sentences in reading language and their connection with the length and reading speed of said language units. The research material consists of 48 sound recordings (eight Lithuanian speakers read six texts representing different functional styles). The results show that all readers usually pause between paragraphs and the duration of those pauses depend on the reading speed: faster readers pause for approximately 400–1340 ms, while slower readers pause for 750–1800 ms. Pauses are the shortest after short paragraphs and they are 1.2 times longer after longer paragraphs. All the readers usually pause between sentences as well. Faster readers on average pause for 200–980 ms, slower readers pause for 340–1360 ms. The longer the sentence, the longer the pause after that sentence (up to 1.4 times). However, the pause can be the same duration after both long and medium length sentences.

Выражение личности в односоставных предложениях кыргызского языка с точки зрения русского языкового мышления

The category of personality/impersonality is a universal category. It is peculiar to all languages of the world, but manifests in them in different ways. The category of personality / impersonality is a two-sided, holistic entity. The Kyrgyz language picture of the world is dominated by the personality component, in Russian — impersonality. The article deals with the issues of expression of the personality in the one-part sentences of the Kyrgyz language from the point of view of Russian language thinking.

Recognition of Signed Expressions in an Experimental System Supporting Deaf Clients in the City Office.

The paper addresses the recognition of dynamic Polish Sign Language expressions in an experimental system supporting deaf people in an office when applying for an ID card. A method of processing a continuous stream of RGB-D data and a feature vector are proposed. The classification is carried out using the k-nearest neighbors algorithm with dynamic time warping, hidden Markov models, and bidirectional long short-term memory. The leave-one-subject-out protocol is used for the dataset containing 121 Polish Sign Language sentences performed five times by four deaf people. A data augmentation method is also proposed and tested. Preliminary observations and conclusions from the use of the system in a laboratory, as well as in real conditions with an experimental installation in the Office of Civil Affairs are given.

Осознанная саморегуляция как ресурс успешности по русскому языку у школьников с различным уровнем интеллекта

The article offers a new view of the assessment of success in the Russian language. Four language competencies are used as its indicators: Language Proficiency, Literacy, Word Structure, and Sentence Structure. The diagnosis is based on the principle of mastering the norms of the language. The study aims to identify regulatory and intellectual predictors of this success. Two hundred eighty-six students in grades 7 and 9 (50.3% girls) completed the questionnaire assessing the level of conscious self-regulation of V. I. Morosanova. In addition, they carried out Raven’s test and two tasks on the language competence assessment. The results showed that gender, age, conscious self-regulation and intelligence significantly influences success in Russian. It is important to note that the contribution of self-regulation significantly exceeded the contribution of intelligence in adolescence. We conducted a similar analysis of a sample divided by gender. The results shed light on the resources for increasing success in Russian for girls and boys. The development of intellectual abilities is promising for girls; the level of intelligence and conscious self-regulation (and above all, the Modeling process), are essential for boys.

FLIP FABRIC AND NAME BOARD (CASE STUDY IN PANGKALPINANG CITY, BANGKA BELITUNG ISLANDS)

This study aims to explain the forms of fabrik range errors and nameplate in the City of Pangkalpinang, Bangka Belitung Islands and find out the factors behind the occurrence of errors in the use of Indonesian in the fabric range and nameplate in the City of Pangkalpinang, Islands. Bangka Belitung. The method used in this research is qualitative descriptive method. The data collection technique used is the triangulation technique which consists of observation, documentation, and interviews. The subjects in this study were all fabric ranges and nameplate in the city of Pangkalpinang, Bangka Belitung Islands which experienced errors in writing with the use of Indonesian. The results of this study are: the form of class that is often done is in writing sentences in foreign languages, the use of non-standard words, the use of abbreviated words that are not explained, and the use of local languages. and the lack of understanding of the owner of the fabric, the education of the owner or maker cannot be biased because there are still errors even though the education is high through S2, then the purpose of making it does not pay attention to the rules of writing. and almost all spandex fabric or nameplate no one gives input or criticism, it's just that there are some from the public who ask questions related to writing or related businesses.

Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries

Actor and action video segmentation with language queries aims to segment out the expression referred objects in the video. This process requires comprehensive language reasoning and fine-grained video understanding. Previous methods mainly leverage dynamic convolutional networks to match visual and semantic representations. However, the dynamic convolution neglects spatial context when processing each region in the frame and is thus challenging to segment similar objects in the complex scenarios. To address such limitation, we construct a context modulated dynamic convolutional network. Specifically, we propose a context modulated dynamic convolutional operation in the proposed framework. The kernels for the specific region are generated from both language sentences and surrounding context features. Moreover, we devise a temporal encoder to incorporate motions into the visual features to further match the query descriptions. Extensive experiments on two benchmark datasets, Actor-Action Dataset Sentences (A2D Sentences) and J-HMDB Sentences, demonstrate that our proposed approach notably outperforms state-of-the-art methods.

Alternating Language Modeling for Cross-Lingual Pre-Training

Language model pre-training has achieved success in many natural language processing tasks. Existing methods for cross-lingual pre-training adopt Translation Language Model to predict masked words with the concatenation of the source sentence and its target equivalent. In this work, we introduce a novel cross-lingual pre-training method, called Alternating Language Modeling (ALM). It code-switches sentences of different languages rather than simple concatenation, hoping to capture the rich cross-lingual context of words and phrases. More specifically, we randomly substitute source phrases with target translations to create code-switched sentences. Then, we use these code-switched data to train ALM model to learn to predict words of different languages. We evaluate our pre-training ALM on the downstream tasks of machine translation and cross-lingual classification. Experiments show that ALM can outperform the previous pre-training methods on three benchmarks.1

IntroVNMT: An Introspective Model for Variational Neural Machine Translation

We propose a novel introspective model for variational neural machine translation (IntroVNMT) in this paper, inspired by the recent successful application of introspective variational autoencoder (IntroVAE) in high quality image synthesis. Different from the vanilla variational NMT model, IntroVNMT is capable of improving itself introspectively by evaluating the quality of the generated target sentences according to the high-level latent variables of the real and generated target sentences. As a consequence of introspective training, the proposed model is able to discriminate between the generated and real sentences of the target language via the latent variables generated by the encoder of the model. In this way, IntroVNMT is able to generate more realistic target sentences in practice. In the meantime, IntroVNMT inherits the advantages of the variational autoencoders (VAEs), and the model training process is more stable than the generative adversarial network (GAN) based models. Experimental results on different translation tasks demonstrate that the proposed model can achieve significant improvements over the vanilla variational NMT model.

Temporally Grounding Language Queries in Videos by Contextual Boundary-Aware Prediction

The task of temporally grounding language queries in videos is to temporally localize the best matched video segment corresponding to a given language (sentence). It requires certain models to simultaneously perform visual and linguistic understandings. Previous work predominantly ignores the precision of segment localization. Sliding window based methods use predefined search window sizes, which suffer from redundant computation, while existing anchor-based approaches fail to yield precise localization. We address this issue by proposing an end-to-end boundary-aware model, which uses a lightweight branch to predict semantic boundaries corresponding to the given linguistic information. To better detect semantic boundaries, we propose to aggregate contextual information by explicitly modeling the relationship between the current element and its neighbors. The most confident segments are subsequently selected based on both anchor and boundary predictions at the testing stage. The proposed model, dubbed Contextual Boundary-aware Prediction (CBP), outperforms its competitors with a clear margin on three public datasets.

Complementary Auxiliary Classifiers for Label-Conditional Text Generation

Learning to generate text with a given label is a challenging task because natural language sentences are highly variable and ambiguous. It renders difficulties in trade-off between sentence quality and label fidelity. In this paper, we present CARA to alleviate the issue, where two auxiliary classifiers work simultaneously to ensure that (1) the encoder learns disentangled features and (2) the generator produces label-related sentences. Two practical techniques are further proposed to improve the performance, including annealing the learning signal from the auxiliary classifier, and enhancing the encoder with pre-trained language models. To establish a comprehensive benchmark fostering future research, we consider a suite of four datasets, and systematically reproduce three representative methods. CARA shows consistent improvement over the previous methods on the task of label-conditional text generation, and achieves state-of-the-art on the task of attribute transfer.

Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection in Task Oriented Dialog

The task of identifying out-of-domain (OOD) input examples directly at test-time has seen renewed interest recently due to increased real world deployment of models. In this work, we focus on OOD detection for natural language sentence inputs to task-based dialog systems. Our findings are three-fold:First, we curate and release ROSTD (Real Out-of-Domain Sentences From Task-oriented Dialog) - a dataset of 4K OOD examples for the publicly available dataset from (Schuster et al. 2019). In contrast to existing settings which synthesize OOD examples by holding out a subset of classes, our examples were authored by annotators with apriori instructions to be out-of-domain with respect to the sentences in an existing dataset.Second, we explore likelihood ratio based approaches as an alternative to currently prevalent paradigms. Specifically, we reformulate and apply these approaches to natural language inputs. We find that they match or outperform the latter on all datasets, with larger improvements on non-artificial OOD benchmarks such as our dataset. Our ablations validate that specifically using likelihood ratios rather than plain likelihood is necessary to discriminate well between OOD and in-domain data.Third, we propose learning a generative classifier and computing a marginal likelihood (ratio) for OOD detection. This allows us to use a principled likelihood while at the same time exploiting training-time labels. We find that this approach outperforms both simple likelihood (ratio) based and other prior approaches. We are hitherto the first to investigate the use of generative classifiers for OOD detection at test-time.

Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model (Student Abstract)

Consider a natural language sentence describing a specific step in a food recipe. In such instructions, recognizing actions (such as press, bake, etc.) and the resulting changes in the state of the ingredients (shape molded, custard cooked, temperature hot, etc.) is a challenging task. One way to cope with this challenge is to explicitly model a simulator module that applies actions to entities and predicts the resulting outcome (Bosselut et al. 2018). However, such a model can be unnecessarily complex. In this paper, we propose a simplified neural network model that separates action recognition and state change prediction, while coupling the two through a novel loss function. This allows learning to indirectly influence each other. Our model, although simpler, achieves higher state change prediction performance (67% average accuracy for ours vs. 55% in (Bosselut et al. 2018)) and takes fewer samples to train (10K ours vs. 65K+ by (Bosselut et al. 2018)).

Story Realization: Expanding Plot Events into Sentences

Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events. We provide results—including a human subjects study—for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches 1.

Differentiable Reasoning on Large Knowledge Bases and Natural Language

Reasoning with knowledge expressed in natural language and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering. General neural architectures that jointly learn representations and transformations of text are very data-inefficient, and it is hard to analyse their reasoning process. These issues are addressed by end-to-end differentiable reasoning systems such as Neural Theorem Provers (NTPs), although they can only be used with small-scale symbolic KBs. In this paper we first propose Greedy NTPs (GNTPs), an extension to NTPs addressing their complexity and scalability limitations, thus making them applicable to real-world datasets. This result is achieved by dynamically constructing the computation graph of NTPs and including only the most promising proof paths during inference, thus obtaining orders of magnitude more efficient models 1. Then, we propose a novel approach for jointly reasoning over KBs and textual mentions, by embedding logic facts and natural language sentences in a shared embedding space. We show that GNTPs perform on par with NTPs at a fraction of their cost while achieving competitive link prediction results on large datasets, providing explanations for predictions, and inducing interpretable models.

Automatic Question Generation u sing Sequence to Sequence RNN Model

Automatic Question Generation (AQG) has recently received growing focus in the processing of natural language (NLP). This attempts to create questions from a text paragraph, where certain sub-spans of the passage in question will answer the questions produced.. Traditional methods predominantly use rigid heuristic rules to turn a sentence into related questions. In this research, we suggest using the neural encoder-decoder model to produce substantive and complex questions from the sentences of natural language. We apply a attention-based sequence to sequence learning paradigm for the task and analyze the impact of encoding sentence vs. knowledge at paragraph level. Information retrieval and NLP are the core components of AQG. It incorporates the application of production rules; recurrent neural network (RNN) based encoder-decoder sequence to sequence (seq2seq) models, and other intelligent techniques. RNN is used because of its long short term memory power (LSTM).The proposed system focus on generating factual WH type questions.

Aligned attention for common multimodal embeddings

Deep learning has been attributed to incredible advances in computer vision, natural language processing, and general pattern understanding. Recent discoveries have enabled efficient vector representations of both visual and written stimuli. Robustly transferring between the two modalities remains a challenge that could yield benefits for search, retrieval, and storage applications. We introduce a simple, yet highly effective approach for building a connection space where natural language sentences are tightly coupled with visual data. In this connection space, similar concepts lie close, whereas dissimilar concepts lie far apart, irrespective of their modality. We introduce an attention mechanism to align multimodal embeddings that are learned through a multimodal metric loss function. We evaluate the learned common vector space on multiple image–text datasets—Pascal Sentences, NUS-WIDE-10k, XMediaNet, Flowers, and Caltech-UCSD Birds. We extend our method to five different modalities of image, sentence, audio, video, and 3D models to demonstrate cross-modal retrieval on the XMedia dataset. We obtain state-of-the-art retrieval and zero-shot retrieval across all datasets.

SENTENCE ARTICULATION IN BRAZILIAN SIGN LANGUAGE – LIBRAS

Articulation of sentences is a grammatical strategy found in any natural language. This phenomenon generates complex constructions which appear in a gradient continuum (parataxis – hypotaxis – enchainment), based on the integration of syntactical, semantical, and pragmatical levels of the language in use. The current research is based on the functionalist perspective of language. The objective of this paper is to describe the process of articulation of sentences in Brazilian Sign Language (Libras). Thereto, we aim at identifying strategies of articulating sentences in Brazilian sign language, taking into account possible complex articulations. We analyze videos taken from conversations via social networks, produced in bidirectional and a-synchronic interaction by three signing deaf of Brazilian sign language. The videos were analyzed on Elan, a multimodal program which enables simultaneous description of audio and/or video. This is an on-going research and here we discuss some initial findings. Among the results, we enhance that Libras employs different discourse strategies of articulating complex sentences: the use of juxtaposition and facial expressions to articulate complex sentences, as well as the use of lexical items to characterize different complex relations, which emphasize the richness and creativity of Brazilian sign language. Thus, complex sentences in Brazilian sign language embodies different discursive strategies to structure parataxis, hypotaxis and enchainment.

The structure of communicative acts

Utterances of natural language sentences can be used to communicate not just contents, but also forces. This paper examines this topic from a cross-linguistic perspective on sentential mood (declarative, interrogative, imperative). Recent work in this area focuses on conversational dynamics: the three sentence types can be associated with distinctive kinds of conversational effects called sentential forces, modeled as three kinds of updates to the discourse context. This paper has two main goals. First, it provides two arguments, on empirical and methodological grounds, for treating sentential force (context update rules) as part of a compositional dynamic semantics, rather than a dynamic pragmatics. Second, it formulates a minimal dynamic semantic analysis that covers the data at the heart of these arguments, incorporating existing analyses of the three major moods, evidentials and conjunction. A further aim of the paper is to sharpen the distinction between sentential force and utterance (illocutionary) force, and discuss its implications.

English Language Sentences According to Structure

This research paper is focused on the linguistics of English language, specifically on the English language types of sentences according to their structure. By saying that this research paper is focused on the types of sentences according to structure, it is understood that sentences will be analyzed from the morphological point of view. As the title signifies and as mentioned, this thesis will analyze the types of sentences according to structure, this a morphological concern. This thesis is ought to analyze and determine how these types of sentences are formed and used but also as a study of concerns that would be beneficial to new students of English language linguistics.