CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling

Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a simple and effective architecture for CSRL which aims to address this problem. Our model is based on a conversational structure aware graph network which explicitly encodes the speaker dependent information. We also propose a multi-task learning method to further improve the model. Experimental results on benchmark datasets show that our model with our proposed training objectives significantly outperforms previous baselines.

Common Sense Bias in Semantic Role Labeling

Large-scale language models such as ELMo and BERT have pushed the horizon of what is possible in semantic role labeling (SRL), solving the out-of-vocabulary problem and enabling end-to-end systems, but they have also introduced significant biases. We evaluate three SRL parsers on very simple transitive sentences with verbs usually associated with animate subjects and objects, such as, Mary babysat Tom'': a state-of-the-art parser based on BERT, an older parser based on GloVe, and an even older parser from before the days of word embeddings. When arguments are word forms predominantly used as person names, aligning with common sense expectations of animacy, the BERT-based parser is unsurprisingly superior; yet, with abstract or random nouns, the opposite picture emerges. We refer to this as common sense bias'' and present a challenge dataset for evaluating the extent to which parsers are sensitive to such a bias. Our code and challenge dataset are available here: github.com/coastalcph/comte

Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks

Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a further pre-training phase between pre-training and fine-tuning phases to adapt the model on the domain-specific unlabeled data can bring positive effects. However, most of these further pre-training works just keep running the conventional pre-training task, e.g., masked language model, which can be regarded as the domain adaptation to bridge the data distribution gap. After observing diverse downstream tasks, we suggest that different tasks may also need a further pre-training phase with appropriate training tasks to bridge the task formulation gap. To investigate this, we carry out a study for improving multiple task-oriented dialogue downstream tasks through designing various tasks at the further pre-training phase. The experiment shows that different downstream tasks prefer different further pre-training tasks, which have intrinsic correlation and most further pre-training tasks significantly improve certain target tasks rather than all. Our investigation indicates that it is of great importance and effectiveness to design appropriate further pre-training tasks modeling specific information that benefit downstream tasks. Besides, we present multiple constructive empirical conclusions for enhancing task-oriented dialogues.

On the Role of Corpus Ordering in Language Modeling

Language models pretrained on vast corpora of unstructured text using self-supervised learning framework are used in numerous natural language understanding and generation tasks. Many studies show that language acquisition in humans follows a rather structured simple-to-complex pattern and guided by this intuition, curriculum learning, which enables training of computational models in a meaningful order, such as processing easy samples before hard ones, has been shown to potentially reduce training time. The question remains whether curriculum learning can benefit pretraining of language models. In this work, we perform comprehensive experiments involving multiple curricula strategies varying the criteria for complexity and the training schedules. Empirical results of training transformer language models on English corpus and evaluating it intrinsically as well as after fine-tuning across eight tasks from the GLUE benchmark, show consistent improvement gains over conventional vanilla training. Interestingly, in our experiments, when evaluated on one epoch, the best model following a document-level hard-to-easy curriculum, outperforms the vanilla model by 1.7 points (average GLUE score) and it takes the vanilla model twice as many training steps to reach comparable performance.

Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers

Abstract Recently, multimodal transformer models have gained popularity because their performance on downstream tasks suggests they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three important factors that can impact the quality of learned representations: pretraining data, the attention mechanism, and loss functions. By pretraining models on six datasets, we observe that dataset noise and language similarity to our downstream task are important indicators of model performance. Through architectural analysis, we learn that models with a multimodal attention mechanism can outperform deeper models with modality-specific attention mechanisms. Finally, we show that successful contrastive losses used in the self-supervised learning literature do not yield similar performance gains when used in multimodal transformers.

The effectiveness of the role of faculties of physical education in the Syrian Arab Republic in the preparation of students

Abstract Universities are considered the most important institutions that affect individuals and are affected by them. The three main functions of the university are education, scientific research and community service. Hence, it is necessary to emphasize the role of faculties of Physical Education as part of the university in the preparation and refinement of the skills and experiences of students including qualifying them professionally and giving them the necessary practical experience. The present age is the age of knowledge explosion. It is noted nowadays that there is a lack of interest in knowing the role of faculties of physical education in society. Therefore, it is necessary to consider the role of the faculties of Physical Education and the relevance of their outputs that can be seen in the large number of graduates to the latest advances of our age and cognitive development. Every improvement of the faculty is accompanied by a change in matching students in the future with business requirements. Hence, the researcher believes that it is necessary to consider the effectiveness of the role of faculties of physical education in the preparation of students and the development of their expertise and skills in light of the latest developments and in accordance with the requirements of working life. The researcher designed a questionnaire according to the scientific steps of its outline as a tool for research. The questionnaire was distributed to students of the Faculty of Physical Education in the governorate of Lattakia and Hama. The calculation of the final grades of each paragraph was then presented. At the end of the research, several conclusions and recommendations were reached: The educational, psychological, administrative, and professional factors (which have been mentioned) inside and outside colleges are some of the reasons that are responsible for weakening the role of colleges and their ability to influence students and prepare them to be proficient in the fields of their work and specialization in addition to the decline of motivation and desire of students to pursue the study. The needs for colleges to understand the need to make a change in their method of flooding the labor market with graduates without paying attention to the needs of this market and the needs of the community. Rather, they must build graduates who have ‘’global” characteristics that enable them to work and engage in any area according to the needs of society and the requirements of the labor market.

Role of Head Nurses in Documenting , Evaluating and Reviewing Staff Performance at Tishreen University Hospital from Nursing staff's viewpoint

The aim of the research was to evaluate the role of the head nurses in documenting, evaluating and reviewing the performance of nursing staff at Tishreen University Hospital from the point of view of nursing staff. Random sample was used , it consisted of 50% of the nursing staff at Tishreen University Hospital during the application of the research there number (300 ) nurses. A developed tool for collecting information was used based on recent research literature, and data were collected and analyzed using SPSS version (20). The most important results were that the evaluation of the role of the head nurses was at moderate level in documenting and evaluating the performance of the nursing staff, while the evaluation of the research sample for the role of the head nurses in reviewing their performance was at a good level.

The possibility of exploitation of sea wave power in Syria

This paper presents the characterization of sea wave behavior in some areas of Lattakia shore, through monitoring for more than one site different from each other by terrain, water depth and bottom type (sand, rocks). It also presents results of measurements of wave height values and their period at breakwater area of Lattakia port, and also shows results of power calculations trans- mitted with waves and speed of those waves, and brings a comparison of energy values calculated using different experimental equations is being used globally, and shows that wave's speed and period are independent from each other. Also shows that it is possible to apply wave power techniques in Syria ,relying on principle of high strength and low height , best way to achieve this is through hydraulic circuits ,and installation of a central system and several subsystems connected to it ,this provides a continuous flow of power.

role of head nurses in managing staff performance at Tishreen university hospital

The purpose of the study was to assess the role of the head nurses in managing the performance of the nursing staff at Tishreen University Hospital from the point of view of the nursing staff and the head nurses. The sample that have been used was available of the head nurses and the simple randomness of the nursing staff and was composed of 55.5% of head nurses and their number was (30) head nurses And 50% of the nursing staff participating in the Tishreen University Hospital during the application of the research and their number was (300) nurse. An improved tool for gathering information was used based on recent research literatures, and data were collected and analyzed using SPSS version 20. The most important results: The assessment of the role of head nurses in managing staff performance at Tishreen University Hospital in general was in a good level.

The role of the scientific police in the criminal investigation and the legitimacy of its means

There is no doubt that the advanced scientific developments that have emerged on the scene in the modern era have led to radical changes in the methods of criminal evidence that were not known before, based on scientific theories. The results of scientific research and its uses in the field of criminal investigation played a major role in proving the crime and its relation to the perpetrator, Therefore, in order to achieve the best results, it was necessary to organize a specialized body to obtain scientific evidence.