Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exop
horic scenario. Exophoric pronouns are common in daily communications, where speakers may directly use pronouns to refer to some objects present in the environment without introducing the objects first. Although such objects are not mentioned in the dialogue text, they can often be disambiguated by the general topics of the dialogue. Motivated by this, we propose to jointly leverage the local context and global topics of dialogues to solve the out-of-text PCR problem. Extensive experiments demonstrate the effectiveness of adding topic regularization for resolving exophoric pronouns.
Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR). To further improve this approach, in this study, we made two proposals. The first is a new pretraining task that trains
MLMs on anaphoric relations with explicit supervision, and the second proposal is a new finetuning method that remedies a notorious issue, the pretrain-finetune discrepancy. Our experiments on Japanese ZAR demonstrated that our two proposals boost the state-of-the-art performance, and our detailed analysis provides new insights on the remaining challenges.
For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the English sentence. However, although fully resolving zero pronouns often ne
eds discourse context, in some cases, the local context within a sentence gives clues to the inference of the zero pronoun. In this study, we propose a data augmentation method that provides additional training signals for the translation model to learn correlations between local context and zero pronouns. We show that the proposed method significantly improves the accuracy of zero pronoun translation with machine translation experiments in the conversational domain.
This study investigate the relationship between quality of work
life and organizational citizenship behavior among workers at
Damascus University, the study aims to identify impact of quality of
working life on the organizational citizenship behav
ior following
dimensions (altruism, sportsmanship, civic virtue, courtesy,
Conscientiousness) among workers at University of Damascus , the
most important results indicate that there is a significant moral effect
of quality of work life on behaviors (altruism, sportsmanship, civic
virtue, courtesy, Conscientiousness) among workers at University of
Damascus.
This research invistigates Althaalbi explanation as well as the
explanation of other interpretors in specifying the antecedent
in some Quran Verses. The research introduces their
arguments, discussions and studies after summerizing them.
Finally, the research adopts one of the present opinions and
provides the reasons for this selection.
This research aimed to identify the relationship between the five big factors of personality and the martial parallel among a sample of chapels in Damascus, and to identify the differences inthe five big factors of personality and the martial paralle
l according to gender and years of marriage. The sample consists of 300 chapels from Damascus, and the researcher used martial parallel questionnaire and between the five big factors of personality questionnaire to study the relationship between the two variables, and T student and person correlation was used. The findings showed that there is a relationship between the martial parallel and Extraversion, Conscientiousness, and Neuroticism, and there is no relationship between martial parallel and Agreeableness and Opennessto Experience, and there are differences inmartial parallel according to gender. However, there are no differences in martial parallel according to years of marriage, and there are differences infive big factors of personality exceptOpenness to Experience factor according to gender, and there are differences in five big factors of personality except Agreeableness factor according to years of marriage.
