تفترض أن معظم الدراسات السابقة حول حالة المعلومات (IS) تصنيف وتجسير التعرف anaphora أن ذكر الذهب أو معلومات شجرة النحوية يتم إعطاء (Hou et al.، 2013؛ Roesiger et al.، 2018؛ هو، 2020؛ يو ويوسيو، 2020) وبعد في هذه الورقة، نقترح نهج عصبي نهاية إلى نهج لتصنيف حالة المعلومات. يتكون نهجنا من مكون استخراج الأوراق ومكون مهمة لحالة المعلومات. خلال وقت الاستدلال، يأخذ نظامنا نصا الخام حيث أن المدخلات ويولد يشرح مع وضع المعلومات الخاصة بهم. على Corpus Isnotes (Markert et al.، 2012)، نوضح أن مكون تعيين حالة معلوماتنا يحقق نتائج جديدة من الفنادق الجديدة على الحبيبات الجميلة التصنيف بناء على طلب الذهب. علاوة على ذلك، يؤدي نظامنا أفضل بكثير من خطوط الأساس الأخرى لكلا من الاستخراج والحبوب الدقيق التصنيف في الإعداد النهائي. أخيرا، نطبق نظامنا على باشي (Roesiger، 2018) و SCICORP (Roesiger، 2016) للتعرف على الحسارة المرجعية. نجد أن نظامنا المنتهي بنا مدروسا على ISNOT يحقق نتائج تنافسية بشأن تجسيد التعرف على الحساب مقارنة بالنظام السابق الذي يعتمد على معلومات النحوية وتدرب على مجموعات البيانات داخل المجال (YU و Poesio ، 2020).
Most previous studies on information status (IS) classification and bridging anaphora recognition assume that the gold mention or syntactic tree information is given (Hou et al., 2013; Roesiger et al., 2018; Hou, 2020; Yu and Poesio, 2020). In this paper, we propose an end-to-end neural approach for information status classification. Our approach consists of a mention extraction component and an information status assignment component. During the inference time, our system takes a raw text as the input and generates mentions together with their information status. On the ISNotes corpus (Markert et al., 2012), we show that our information status assignment component achieves new state-of-the-art results on fine-grained IS classification based on gold mentions. Furthermore, our system performs significantly better than other baselines for both mention extraction and fine-grained IS classification in the end-to-end setting. Finally, we apply our system on BASHI (Roesiger, 2018) and SciCorp (Roesiger, 2016) to recognize referential bridging anaphora. We find that our end-to-end system trained on ISNotes achieves competitive results on bridging anaphora recognition compared to the previous state-of-the-art system that relies on syntactic information and is trained on the in-domain datasets (Yu and Poesio, 2020).
References used
https://aclanthology.org/
Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic role labelin
This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks
Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks. However, it usually involves multiple-s
We propose a novel problem within end-to-end learning of task oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain
A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (