Parsing Model Research Articles

Semantic Graphical Dependence Parsing Model in Improving English Teaching Abilities

It is a very difficult problem to achieve high-order functionality for graphical dependency parsing without growing decoding difficulties. To solve this problem, this article offers a way for Semantic Graphical Dependence Parsing Model (SGDPM) with a language-dependency model and a beam search to represent high-order functions for computer applications. The first approach is to scan a large amount of unnoticed data using a baseline parser. It will build auto-parsed data to create the Language-dependence Model (LDM). The LDM is based on a set of new features during beam search decoding, where it will incorporate the LDM features into the parsing model and utilize the features in parsing models of bilingual text. Our approach has main benefits, which include rich high-order features that are described given the large size and the additional large crude corpus for increasing the difficulty of decoding. Further, SGDPM has been evaluated using the suggested method for parsing tasks of mono-parsing text and bi-parsing text to carry out experiments on the English and Chinese data in the mono-parsing text function using computer applications. Experimental results show that the most accurate Chinese data is obtained with the best known English data systems and their comparable accuracy. Furthermore, the lab-scale experiments on the Chinese/General bilingual information in the bitext parsing process outperform the best recorded existing solutions.

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

Abstract Dependency parsing is a complex process in natural language text processing, text to semantic transformation. The efficiency improvement of dependency parsing is a current and an active research area in the NLP community. The paper presents four transition-based dependency parser models with implementation using DL4J classifiers. The efficiency of the proposed models were tested with Hungarian language corpora. The parsing model uses a data representation form based on lightweight embedding and a novel morphological-description-vector format is proposed for the input layer. Based on the test experiments on parsing Hungarian text documents, the proposed list-based transitions parsers outperform the widespread stack-based variants.

A Neural Joint Model with BERT for Burmese Syllable Segmentation, Word Segmentation, and POS Tagging

The smallest semantic unit of the Burmese language is called the syllable. In the present study, it is intended to propose the first neural joint learning model for Burmese syllable segmentation, word segmentation, and part-of-speech ( POS ) tagging with the BERT. The proposed model alleviates the error propagation problem of the syllable segmentation. More specifically, it extends the neural joint model for Vietnamese word segmentation, POS tagging, and dependency parsing [28] with the pre-training method of the Burmese character, syllable, and word embedding with BiLSTM-CRF-based neural layers. In order to evaluate the performance of the proposed model, experiments are carried out on Burmese benchmark datasets, and we fine-tune the model of multilingual BERT. Obtained results show that the proposed joint model can result in an excellent performance.

Progressive One-shot Human Parsing

Prior human parsing models are limited to parsing humans into classes pre-defined in the training data, which is not flexible to generalize to unseen classes, e.g., new clothing in fashion analysis. In this paper, we propose a new problem named one-shot human parsing (OSHP) that requires to parse human into an open set of reference classes defined by any single reference example. During training, only base classes defined in the training set are exposed, which can overlap with part of reference classes. In this paper, we devise a novel Progressive One-shot Parsing network (POPNet) to address two critical challenges , i.e., testing bias and small sizes. POPNet consists of two collaborative metric learning modules named Attention Guidance Module and Nearest Centroid Module, which can learn representative prototypes for base classes and quickly transfer the ability to unseen classes during testing, thereby reducing testing bias. Moreover, POPNet adopts a progressive human parsing framework that can incorporate the learned knowledge of parent classes at the coarse granularity to help recognize the descendant classes at the fine granularity, thereby handling the small sizes issue. Experiments on the ATR-OS benchmark tailored for OSHP demonstrate POPNet outperforms other representative one-shot segmentation models by large margins and establishes a strong baseline. Source code can be found at https://github.com/Charleshhy/One-shot-Human-Parsing.

Smartfit - Artificial Intelligence Based Virtual Dressing Room

In the current existing busy and modern lifestyle had led many people to purchase ready-made clothes from e-commerce stores or retail stores without actually knowing the fitting of the clothes, in the expectation of perfect fit. To improve the accessibility and increase the time efficiency of clothes trying on we have created a virtual clothes trial room environment. In this, we have introduced a virtual try-on strategy which is based on generative adversarial networks(GAN).Our technique will firstly obtain masking of cloth region of a person with the help of human parsing model. Next, the cloth region will be removed from the person's image and another desired cloth image is added on the region. This application will also be more useful for the shops which requires to show every clothes to customer and hence time consuming and requires more Human Effort.

Segment attention‐guided part‐aligned network for person re‐identification

Part misalignment of the human body caused by complex variations in viewpoint and pose poses a fundamental challenge to person re-identification. This letter examines Res2Net as the backbone network to extract multi-scale appearance features. At the same time, it uses the human parsing model to extract part features, which can be used as an attention stream to guide part features re-calibration from the spatial dimension. Additionally, in order to ensure the diversity of features, SAG-PAN effectively integrates the global appearance features of person image with part fine-grained features. The experimental results on the Market-1501, DukeMTMC-reID and CUHK03 datasets show that the proposed SAG-PAN achieved superior performance against the existing state-of-the-art methods.

Multi-level Chunk-based Constituent-to-Dependency Treebank Transformation for Tibetan Dependency Parsing

Dependency parsing is an important task for Natural Language Processing (NLP). However, a mature parser requires a large treebank for training, which is still extremely costly to create. Tibetan is a kind of extremely low-resource language for NLP, there is no available Tibetan dependency treebank, which is currently obtained by manual annotation. Furthermore, there are few related kinds of research on the construction of treebank. We propose a novel method of multi-level chunk-based syntactic parsing to complete constituent-to-dependency treebank conversion for Tibetan under scarce conditions. Our method mines more dependencies of Tibetan sentences, builds a high-quality Tibetan dependency tree corpus, and makes fuller use of the inherent laws of the language itself. We train the dependency parsing models on the dependency treebank obtained by the preliminary transformation. The model achieves 86.5% accuracy, 96% LAS, and 97.85% UAS, which exceeds the optimal results of existing conversion methods. The experimental results show that our method has the potential to use a low-resource setting, which means we not only solve the problem of scarce Tibetan dependency treebank but also avoid needless manual annotation. The method embodies the regularity of strong knowledge-guided linguistic analysis methods, which is of great significance to promote the research of Tibetan information processing.

Reassessing second language reading comprehension: Insights from the psycholinguistics notion of sentence processing

Theories and practices in second language reading pedagogy often overlook the sentence processing description from the psycholinguistics perspective. Second language reading comprehension is easily associated with vocabulary learning or discourse strategy. Yet, such activities can lead to an unnatural way of reading such as translating vocabularies or pointing out information as required. Meanwhile the authentic way of reading should encourage a natural stream of ideas to be interpreted from sentence to sentence. As suggested by the sentence processing notion from the psycholinguistics point of view, syntax appears to be the key to effective and authentic reading as opposed to the general belief of semantic or discourse information being the primary concern. This article argues that understanding the architecture of sentence processing, with syntactic parsing at the core of the underlying mechanism, can offer insights into the second language reading pedagogy. The concepts of syntactic parsing, reanalysis, and sentence processing models are described to give the idea of how sentence processing works. Additionally, a critical review on the differences between L1 and L2 sentence processing is presented considering the recent debate on individual differences as significant indicators of nativelike L2 sentence processing. Lastly, implications for the L2 reading pedagogy and potential implementation in instructional setting are discussed.

Multi-human Parsing with a Graph-based Generative Adversarial Model

Human parsing is an important task in human-centric image understanding in computer vision and multimedia systems. However, most existing works on human parsing mainly tackle the single-person scenario, which deviates from real-world applications where multiple persons are present simultaneously with interaction and occlusion. To address such a challenging multi-human parsing problem, we introduce a novel multi-human parsing model named MH-Parser, which uses a graph-based generative adversarial model to address the challenges of close-person interaction and occlusion in multi-human parsing. To validate the effectiveness of the new model, we collect a new dataset named Multi-Human Parsing (MHP), which contains multiple persons with intensive person interaction and entanglement. Experiments on the new MHP dataset and existing datasets demonstrate that the proposed method is effective in addressing the multi-human parsing problem compared with existing solutions in the literature.

Discovering microbe-disease associations from the literature using a hierarchical long short-term memory network and an ensemble parser model

With recent advances in biotechnology and sequencing technology, the microbial community has been intensively studied and discovered to be associated with many chronic as well as acute diseases. Even though a tremendous number of studies describing the association between microbes and diseases have been published, text mining methods that focus on such associations have been rarely studied. We propose a framework that combines machine learning and natural language processing methods to analyze the association between microbes and diseases. A hierarchical long short-term memory network was used to detect sentences that describe the association. For the sentences determined, two different parse tree-based search methods were combined to find the relation-describing word. The ensemble model of constituency parsing for structural pattern matching and dependency-based relation extraction improved the prediction accuracy. By combining deep learning and parse tree-based extractions, our proposed framework could extract the microbe-disease association with higher accuracy. The evaluation results showed that our system achieved an F-score of 0.8764 and 0.8524 in binary decisions and extracting relation words, respectively. As a case study, we performed a large-scale analysis of the association between microbes and diseases. Additionally, a set of common microbes shared by multiple diseases were also identified in this study. This study could provide valuable information for the major microbes that were studied for a specific disease. The code and data are available at https://github.com/DMnBI/mdi_predictor.

Knowledge graph mining for realty domain using dependency parsing and QAT models

The real estate business has a lot of risks, and in order to minimize them, you need a lot of information from different sources. Systems based on natural language processing can help customers find this information more easily: question answering, information retrieval, etc. The existing method of question answering requires data aligned with possible questions, which are not easy to obtain, in contrast, the knowledge-graph provides structured information. In this paper, we propose semi-automated ontology generation for the realty domain and a subsequent method for information retrieval related to the knowledge-graph of this ontology. The first contribution is the method for relation extraction method based on dependency-parsing and semantic similarity evaluation, which allows us to form ontology for a particular domain. The second contribution is knowledge-graph completion method based on question answering over text neural network. Our experimental analysis shows the efficiency of the proposed approaches.

Deep Graph-Based Character-Level Chinese Dependency Parsing

Character-level Chinese dependency parsing has been a concern of several studies that naturally handle word segmentation, POS (Part of Speech) tagging and dependency parsing jointly in an end-to-end way. Previous work mostly concentrates on a transition-based framework for this task because of its easy adaption, which is extremely important when feature representation relies heavily on the decoding strategy, particularly under the traditional statistical setting. Recently, on the one hand, sophisticated deep neural networks and deep contextualized word representations have greatly weakened the dependence between feature representation and decoding. On the other hand, (first-order) graph-based models, especially the biaffine parsers, are straightforward for dependency parsing, and meanwhile they can yield competitive parsing performance. In this paper, we make a comprehensive investigation of the deep graph-based character-level dependency parsing for Chinese. We start from an extension of a standard graph-based biaffine parser, and then exploit Chinese BERT as well as our improved encoders based on transformers to enhance the character-level dependency parsing model. We conduct a series of experiments on the Chinese benchmark datasets, showing the performances of various graph-based character-level models and analyzing the advantages of the character-level dependency parsing under the deep neural setting.

Self-Correction for Human Parsing.

Labeling pixel-level masks for fine-grained semantic segmentation tasks, e.g., human parsing, remains a challenging task. The ambiguous boundary between different semantic parts and those categories with similar appearances are usually confusing for annotators, leading to incorrect labels in ground-truth masks. These label noises will inevitably harm the training process and decrease the performance of the learned models. To tackle this issue, we introduce a noise-tolerant method in this work, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models. In particular, starting from a model trained with inaccurate annotations as initialization, we design a cyclically learning scheduler to infer more reliable pseudo masks by iteratively aggregating the current learned model with the former sub-optimal one in an online manner. Besides, those correspondingly corrected labels can in turn to further boost the model performance. In this way, the models and the labels will reciprocally become more robust and accurate during the self-correction learning cycles. Our SCHP is model-agnostic and can be applied to any human parsing models for further enhancing their performance. Extensive experiments on four human parsing models, including Deeplab V3+, CE2P, OCR and CE2P+, well demonstrate the effectiveness of the proposed SCHP. We achieve the new state-of-the-art results on 6 benchmarks, including LIP, Pascal-Person-Part and ATR for single human parsing, CIHP and MHP for multi-person human parsing and VIP for video human parsing tasks. In addition, benefiting the superiority of SCHP, we achieved the 1st place on all the three human parsing tracks in the 3rd Look Into Person Challenge. The code is available at https://github.com/PeikeLi/Self-Correction-Human-Parsing.

A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing

Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined at the word-level. Therefore word segmentation is the precondition of dependency parsing, which makes dependency parsing suffer from error propagation and unable to directly make use of character-level pre-trained language models (such as BERT). In this paper, we propose a graph-based model to integrate Chinese word segmentation and dependency parsing. Different from previous transition-based joint models, our proposed model is more concise, which results in fewer efforts of feature engineering. Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing. Additionally, when BERT is combined, our model can substantially reduce the performance gap of dependency parsing between joint models and gold-segmented word-based models. Our code is publicly available at https://github.com/fastnlp/JointCwsParser

A Principled Approach to Feature Selection in Models of Sentence Processing.

Among theories of human language comprehension, cue-based memory retrieval has proven to be a useful framework for understanding when and how processing difficulty arises in the resolution of long-distance dependencies. Most previous work in this area has assumed that very general retrieval cues like [+subject] or [+singular] do the work of identifying (and sometimes misidentifying) a retrieval target in order to establish a dependency between words. However, recent work suggests that general, handpicked retrieval cues like these may not be enough to explain illusions of plausibility (Cunnings & Sturt, 2018), which can arise in sentences like The letter next to the porcelain plate shattered. Capturing such retrieval interference effects requires lexically specific features and retrieval cues, but handpicking the features is hard to do in a principled way and greatly increases modeler degrees of freedom. To remedy this, we use well-established word embedding methods for creating distributed lexical feature representations that encode information relevant for retrieval using distributed retrieval cue vectors. We show that the similarity between the feature and cue vectors (a measure of plausibility) predicts total reading times in Cunnings and Sturt's eye-tracking data. The features can easily be plugged into existing parsing models (including cue-based retrieval and self-organized parsing), putting very different models on more equal footing and facilitating future quantitative comparisons.

Tree Rotations for Dependency Trees: Converting the Head-Directionality of Noun Phrases

To overcome the lack of NLP resources for the low-resource languages, we can utilize tools that are already available for other highresource languages and then modify the output to conform to the target language. In this study, we proposed an approach to convert an Indonesian constituency treebank to a dependency treebank by utilizing an English NLP tool (Stanford CoreNLP) to create the initial dependency treebank. Some annotations in this initial treebank did not conform to Indonesian grammar, especially noun phrases’ head-directionality. Noun phrases in English usually have head-final direction, while in Indonesian is the opposite, head-initial. We proposed a variant of tree rotations algorithm named headSwap for dependency trees. We used this algorithm to convert the head-directionality for noun phrases that were initially labeled as a compound. Moreover, we also proposed a set of rules to rename the dependency relation labels to conform to the recent guidelines. To evaluate our proposed method, we created a gold standard of 2,846 tokens that were annotated manually. Experiment results showed that our proposed method improved the Unlabeled Attachment Score (UAS) with a margin of 32.5% from 61.6 to 94.1% and the Labeled Attachment Score (LAS) with a margin of 41% from 44.1 to 85.1%. Finally, we created a new Indonesian dependency treebank that converted automatically using our proposed method that consists of 25,416 tokens. The dependency parser model built using this treebank has UAS of 75.90% and LAS of 70.38%.

A systematic review of unsupervised approaches to grammar induction

AbstractThis study systematically reviews existing approaches to unsupervised grammar induction in terms of their theoretical underpinnings, practical implementations and evaluation. Our motivation is to identify the influence of functional-cognitive schools of grammar on language processing models in computational linguistics. This is an effort to fill any gap between the theoretical school and the computational processing models of grammar induction. Specifically, the review aims to answer the following research questions: Which types of grammar theories have been the subjects of grammar induction? Which methods have been employed to support grammar induction? Which features have been used by these methods for learning? How were these methods evaluated? Finally, in terms of performance, how do these methods compare to one another? Forty-three studies were identified for systematic review out of which 33 described original implementations of grammar induction; three provided surveys and seven focused on theories and experiments related to acquisition and processing of grammar in humans. The data extracted from the 33 implementations were stratified into 7 different aspects of analysis: theory of grammar; output representation; how grammatical productivity is processed; how grammatical productivity is represented; features used for learning; evaluation strategy and implementation methodology. In most of the implementations considered, grammar was treated as a generative-formal system, autonomous and independent of meaning. The parser decoding was done in a non-incremental, head-driven fashion by assuming that all words are available for the parsing model and the output representation of the grammar learnt was hierarchical, typically a dependency or a constituency tree. However, the theoretical and experimental studies considered suggest that a usage-based, incremental, sequential system of grammar is more appropriate than the formal, non-incremental, hierarchical view of grammar. This gap between the theoretical as well as experimental studies on one hand and the computational implementations on the other hand should be addressed to enable further progress in computational grammar induction research.

Incremental structure building of preverbal PPs in Dutch

Abstract Incremental comprehension of head-final constructions can reveal structural attachment preferences for ambiguous phrases. This study investigates how temporarily ambiguous PPs are processed in Dutch verb-final constructions. In De aannemer heeft op het dakterras bespaard/gewerkt ‘The contractor has on the roof terrace saved/worked’, the PP is locally ambiguous between attachment as argument and as adjunct. This ambiguity is resolved by the sentence-final verb. In a self-paced reading task, we manipulated the argument/adjunct status of the PP, and its position relative to the verb. While we found no reading-time differences between argument and adjunct PPs, we did find that transitive verbs, for which the PP is an argument, were read more slowly than intransitive verbs, for which the PP is an adjunct. We suggest that Dutch parsers have a preference for adjunct attachment of preverbal PPs, and discuss our findings in terms of incremental parsing models that aim to minimize costly reanalysis.

From text to graph: a general transition-based AMR parsing using neural network

Semantic understanding is an essential research issue for many applications, such as social network analysis, collective intelligence and content computing, which tells the inner meaning of language form. Recently, Abstract Meaning Representation (AMR) is attracted by many researchers for its semantic representation ability on an entire sentence. However, due to the non-projectivity and reentrancy properties of AMR graphs, they lose some important semantic information in parsing from sentences. In this paper, we propose a general AMR parsing model which utilizes a two-stack-based transition algorithm for both Chinese and English datasets. It can incrementally parse sentences to AMR graphs in linear time. Experimental results demonstrate that it is superior in recovering reentrancy and handling arcs while is competitive with other transition-based neural network models on both English and Chinese datasets.

A Lexical Dependency Probability Model for Mongolian Based On Integration of Morphological and Syntactic Features

Syntactic parsing is an important topic in the field of Mongolian language information processing. Compared with English and Chinese dependency parsing, Mongolian dependency parsing is still at the beginning stage. Mongolian syntactic parsing lack of Treebank resources seriously, under such conditions, a high quality syntactic parser cannot be developed by statistical methods simply. Aiming at the characteristics that Mongolian language has rich morphological features, this paper presented a rule and statistics-based dependency parsing model using Mongolian Dependency Treebank as training and evaluation data. The morphological and syntactic rules are represented using complex features and unification operations. The statistical model is represented using lexical dependent probability. This model has now achieved accuracies of 77.18%, 69.42% and 95.44% for the unlabelled annotation score, the labeled annotation score and the head word annotation score respectively.