UniteD-SRL: A Unified Dataset for Span- and Dependency-Based Multilingual and Cross-Lingual Semantic Role Labeling

Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available. While recent work has attained growing success, results on gold multilingual benchmarks are still not easily comparable across languages, making it difficult to grasp where we stand. For example, in CoNLL-2009, the standard benchmark for multilingual SRL, language-to-language comparisons are affected by the fact that each language has its own dataset which differs from the others in size, domains, sets of labels and annotation guidelines. In this paper, we address this issue and propose UniteD-SRL, a new benchmark for multilingual and cross-lingual, span- and dependency-based SRL. UniteD-SRL provides expert-curated parallel annotations using a common predicate-argument structure inventory, allowing direct comparisons across languages and encouraging studies on cross-lingual transfer in SRL. We release UniteD-SRL v1.0 at https://github.com/SapienzaNLP/united-srl.

Sister Help: Data Augmentation for Frame-Semantic Role Labeling

While FrameNet is widely regarded as a rich resource of semantics in natural language processing, a major criticism concerns its lack of coverage and the relative paucity of its labeled data compared to other commonly used lexical resources such as PropBank and VerbNet. This paper reports on a pilot study to address these gaps. We propose a data augmentation approach, which uses existing frame-specific annotation to automatically annotate other lexical units of the same frame which are unannotated. Our rule-based approach defines the notion of a **sister lexical unit** and generates frame-specific augmented data for training. We present experiments on frame-semantic role labeling which demonstrate the importance of this data augmentation: we obtain a large improvement to prior results on frame identification and argument identification for FrameNet, utilizing both full-text and lexicographic annotations under FrameNet. Our findings on data augmentation highlight the value of automatic resource creation for improved models in frame-semantic parsing.

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.

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

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.

tWT--WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets

The stance detection task aims at detecting the stance of a tweet or a text for a target. These targets can be named entities or free-form sentences (claims). Though the task involves reasoning of the tweet with respect to a target, we find that it is possible to achieve high accuracy on several publicly available Twitter stance detection datasets without looking at the target sentence. Specifically, a simple tweet classification model achieved human-level performance on the WT--WT dataset and more than two-third accuracy on various other datasets. We investigate the existence of biases in such datasets to find the potential spurious correlations of sentiment-stance relations and lexical choice associated with the stance category. Furthermore, we propose a new large dataset free of such biases and demonstrate its aptness on the existing stance detection systems. Our empirical findings show much scope for research on the stance detection task and proposes several considerations for creating future stance detection datasets.

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.

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.

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.