As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question their true capabilities. For a
more informative evaluation than accuracy on text classification tasks can offer, we propose evaluating systems through a novel measure of prediction coherence. We apply our framework to two existing language understanding benchmarks with different properties to demonstrate its versatility. Our experimental results show that this evaluation framework, although simple in ideas and implementation, is a quick, effective, and versatile measure to provide insight into the coherence of machines' predictions.
Story visualization is an underexplored task that falls at the intersection of many important research directions in both computer vision and natural language processing. In this task, given a series of natural language captions which compose a story
, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform text-to-image synthesis models on this task. However, there is room for improvement of generated images in terms of visual quality, coherence and relevance. We present a number of improvements to prior modeling approaches, including (1) the addition of a dual learning framework that utilizes video captioning to reinforce the semantic alignment between the story and generated images, (2) a copy-transform mechanism for sequentially-consistent story visualization, and (3) MART-based transformers to model complex interactions between frames. We present ablation studies to demonstrate the effect of each of these techniques on the generative power of the model for both individual images as well as the entire narrative. Furthermore, due to the complexity and generative nature of the task, standard evaluation metrics do not accurately reflect performance. Therefore, we also provide an exploration of evaluation metrics for the model, focused on aspects of the generated frames such as the presence/quality of generated characters, the relevance to captions, and the diversity of the generated images. We also present correlation experiments of our proposed automated metrics with human evaluations.
Automatic abstractive summaries are found to often distort or fabricate facts in the article. This inconsistency between summary and original text has seriously impacted its applicability. We propose a fact-aware summarization model FASum to extract
and integrate factual relations into the summary generation process via graph attention. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems. Empirical results show that the fact-aware summarization can produce abstractive summaries with higher factual consistency compared with existing systems, and the correction model improves the factual consistency of given summaries via modifying only a few keywords.
The research aims to identify the role of organizational culture in reducing resistance to
change of the employees through a study of the relationship between the dimensions of the
organizational culture, and the reasons of resistance change by emp
loyees working in Lattakia City
Council. To achieve the objectives of the research, a questionnaire was designed and distributed to
(343) employees in Lattakia City Council, (315) questionnaire were complete and valid for
statistical analysis, with a response rate of (91.84%). Relying on multiple regression, the following
results were reached:
1. There is a strong inverse relationship which is statistically significant between the
elements after the containment and interdependence of (empowerment, staff development,
teamwork and participation), and a reeducation of the resistance of workers to change, wherever
after containment and coherence elements are available, there is a decline in the causes resistance
of workers to change.
2. There is strong inverse relationship that is statistically significant between the elements
after the consistency and uniformity of working (core values, agreement, coordination and
integration), and a reduction of resistance workers to change, i.e. when elements after consistency
and homogeneity are availed, they lead to a decline in the causes of workers resistance to change.
3. There is strong inverse relationship which is statistically significant between the elements
of the human aspects (respect and appreciation, justice, encouragement achievement, and social
welfare), and the reeducation of workers resistance to change, i.e., whenever there are elements of
the human aspects, there is a decline of the causes of workers resistance to change.
4. There is strong inverse relationship which is statistically significant between the elements
after the organizational climate of (administrative practices, rewards, communications, and
surveillance system), and the reduction of workers resistance to change, i.e., wherever after the
organizational climate elements are available, there is a decline in the causes of workers resistance
to change.
تقوم هذه الدراسة على رصد عدد من عناصر الاتِّساق و الانسجام في أحد
النصوص الشعرية المهمة التي أبدعها الشاعر العربي أحمد عبد المعطي حجازي، و هو نص يتعامل مع شهر أيار و ما وقع فيه من أحداث مهمة، مستنداً إلى الكشف عن آليات الاتِّساق: الإحالات النصية و ا
لحذف و الوصل و الاتِّساق المعجمي، و آليات الانسجام النصي: البنية الكلية للنص، و العنوان، و التكرار و المعرفة الكلية للعالم و الانقطاع و غيرها، و ختم البحث بخاتمة قصيرة تلخِّص أهم نتائج البحث.
