تحسنت أنسورية واحدة على أساس الأساس، والتي تحسنت بشكل كبير إلى الأساسي، في السنوات الأخيرة. لذلك بدأ الباحثون في إيلاء المزيد من الاهتمام لحالات أنشفورية أكثر تعقيدا مثل Anaphora غير المعقدة، كما هو الحال في Time-Warner يفكر في تحد قانوني لخطة اتصالات الاتصالات لشراء نصف شبكات Showtime Inc - وهي خطوة قد تؤدي إلى الحرب الشاملة بين الشركتين القويين. Anaphora Split-AnaPhora متدرج وأكثر تعقيدا للحل من Anaphora الوحيد السابق؛ ونتيجة لذلك، لا يتم تفاحها في العديد من مجموعات البيانات المصممة للاختبار COMESION، والاستعمال السابق بشأن حل هذا النوع من الأناحورا نفذت في ظروف غير واقعية تفترض أن أشرح الذهب و / أو جولد سبليت سبليتس المتاحة متوفرة. تركز هذه الأنظمة أيضا على أنسوجات سبليت سابقة فقط. في هذا العمل، نقدم نظاما يحل كلا من المدن الفردية والتقسيم السابقة، وتقييمه في بيئة أكثر واقعية يستخدم يذكر المتوقع. نبدأ أيضا في معالجة مسألة كيفية تقييم المدافعين الوحيدين والتقسيم السابق باستخدام مقاييس تقييم COMEARY القياسية.
The state-of-the-art on basic, single-antecedent anaphora has greatly improved in recent years. Researchers have therefore started to pay more attention to more complex cases of anaphora such as split-antecedent anaphora, as in Time-Warner is considering a legal challenge to Telecommunications Inc's plan to buy half of Showtime Networks Inc--a move that could lead to all-out war between the two powerful companies''. Split-antecedent anaphora is rarer and more complex to resolve than single-antecedent anaphora; as a result, it is not annotated in many datasets designed to test coreference, and previous work on resolving this type of anaphora was carried out in unrealistic conditions that assume gold mentions and/or gold split-antecedent anaphors are available. These systems also focus on split-antecedent anaphors only. In this work, we introduce a system that resolves both single and split-antecedent anaphors, and evaluate it in a more realistic setting that uses predicted mentions. We also start addressing the question of how to evaluate single and split-antecedent anaphors together using standard coreference evaluation metrics.
References used
https://aclanthology.org/
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
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from neighbor'' source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-righ
While neural networks produce state-of-the- art performance in several NLP tasks, they generally depend heavily on lexicalized information, which transfer poorly between domains. Previous works have proposed delexicalization as a form of knowledge di
Business Process Management (BPM) is the discipline which is responsible for management of discovering, analyzing, redesigning, monitoring, and controlling business processes. One of the most crucial tasks of BPM is discovering and modelling business
Split-and-rephrase is a challenging task that promotes the transformation of a given complex input sentence into multiple shorter sentences retaining equivalent meaning. This rewriting approach conceptualizes that shorter sentences benefit human read