Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEASE: Extractive-Abstractive Summarization End-to-End using the Information Bottleneck Principle
سهولة: ملخص مبادرة الاستخراجية - إلى النهاية باستخدام مبدأ الاختناق المعلومات
586
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتفوق أنظمة تلخيص التلخيص الحالية على نظرائهم المستخرجين، لكن اعتمادهم على نطاق واسع يمنعهم الافتقار المتأصل إلى الترجمة الشفوية. أنظمة تلخيص الاستخراجية، على الرغم من أنه قابل للتفسير، تعاني من التكرار وقلة الاتساق المحتمل. لتحقيق أفضل ما في العالمين، نقترح سهولة، وهو إطار خارجي - مبادرة ينشئ ملخصات إغراقية موجزة يمكن تتبعها مرة أخرى إلى ملخص مستخرج. يمكن تطبيق إطارنا على أي مشكلة توليد نصية قائمة على الأدلة ويمكن أن تستوعب النماذج المحددة مسبقا في بنية بسيطة. نستخدم مبدأ معلومات عنق المعلومات لتدريب الاستخلاص والتجريد المشترك في أزياء نهاية إلى نهاية. مستوحاة من البحث السابق الذي يستخدمه البشر إطارا من مرحلتين لتلخيص المستندات الطويلة (Jing و McKeown، 2000)، فإن إطار عملائنا أولا يستخرج كمية محددة مسبقا من الأدلة التي تمتد ثم يولد ملخصا باستخدام الأدلة فقط. باستخدام التقييمات التلقائية والبشرية، نوضح أن الملخصات التي تم إنشاؤها أفضل من خطوط الأساسيات الاستخراجية والاستخراجية الدخرية.
Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. Extractive summarization systems, though interpretable, suffer from redundancy and possible lack of coherence. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary. Our framework can be applied to any evidence-based text generation problem and can accommodate various pretrained models in its simple architecture. We use the Information Bottleneck principle to jointly train the extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans and then generates a summary using only the evidence. Using automatic and human evaluations, we show that the generated summaries are better than strong extractive and extractive-abstractive baselines.
References used
https://aclanthology.org/
rate research
Read More
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 p
aper, 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).
A currently popular research area in end-to-end speech translation is the use of knowledge distillation from a machine translation (MT) task to improve the speech translation (ST) task. However, such scenario obviously only allows one way transfer, w
hich is limited by the performance of the teacher model. Therefore, We hypothesis that the knowledge distillation-based approaches are sub-optimal. In this paper, we propose an alternative--a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student. This allows us to improve the performance of end-to-end ST more effectively than with a teacher-student paradigm. As a side benefit, performance of the MT model also improves. Experimental results show that in our mutual-learning scenario, models can effectively utilise the auxiliary information from peer models and achieve compelling results on Must-C dataset.
Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a setting where hand-annotated q
uestion entities are supplied to the model, leaving the important and non-trivial task of entity resolution (ER) outside the scope of E2E learning. In this work, we extend the boundaries of E2E learning for KGQA to include the training of an ER component. Our model only needs the question text and the answer entities to train, and delivers a stand-alone QA model that does not require an additional ER component to be supplied during runtime. Our approach is fully differentiable, thanks to its reliance on a recent method for building differentiable KGs (Cohen et al., 2020). We evaluate our E2E trained model on two public datasets and show that it comes close to baseline models that use hand-annotated entities.
A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost. One can instead consider an end-to-e
nd model that directly maps the input to the target output and simplify the entire process. However, such generation approach is known to lead to unstable performance if not designed carefully. Here we present our recent effort on transitioning from our existing pipeline-based IE system to an end-to-end system focusing on practical challenges that are associated with replacing and deploying the system in real, large-scale production. By carefully formulating document IE as a sequence generation task, we show that a single end-to-end IE system can be built and still achieve competent performance.
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
that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results. In this tutorial, we will first introduce the background and the latest progress of syntactic parsing and SRL/NMT. Then, we will summarize the key evidence about the syntactic impacts over these two concerning tasks, and explore the behind reasons from both computational and linguistic backgrounds.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
