Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings
تحسين العقوبة القائمة على الرسم البياني الطلب مع أمر الزوجية المتوقعة بشكل متكرر
309
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يمكن تصنيف نماذج ترتيب الجملة المهيمنة في طرازات طلب الزوجية ونماذج ضبط التسلسل. ومع ذلك، هناك محاولة قليلة للجمع بين هذين النوعين من النماذج، والتي تمتلك بمثابة مزايا تكميلية. في هذه الورقة، نقترح إطارا رواية ترتيب جملة جديدة يقدم اثنين من المصنفين لتحقيق استخدام أفضل لطلبات الزوجية لطلب الجملة القائمة على الرسم البياني (يين وآخرون 2019، 2021). خصيصا، بالنظر إلى الرسم البياني للكيان الجماعي الأولي، نقدم أولا مصنف في الرسم البياني للتنبؤ بأمر الزوج بين الجمل المرتبطة. بعد ذلك، بطريقة تكرارية، استنادا إلى الرسم البياني الذي تم تحديثه من قبل طلبات الزوجية عالية الواثقة مسبقا، يتم استخدام مصنف آخر للتنبؤ بأمر الزوج غير المؤكد. أخيرا، نحن نتكيف مع نموذج طلب جملة قائمة على أساس GRN (يين وآخرون 2019، 2021) على أساس الرسم البياني النهائي. تجارب على خمسة مجموعات بيانات شائعة الاستخدام توضح فعالية وعمل نموذجنا. خاصة، عند تزويد Bert (Devlin et al. 2019) و FHDecoder (يين وآخرون 2020)، ينص نموذجنا على أداء الحديث عن الفن. يتوفر الكود الخاص بنا في https://github.com/deeplearnxmu/irseg.
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models. However, there is little attempt to combine these two types of models, which inituitively possess complementary advantages. In this paper, we propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering (Yin et al. 2019, 2021). Specially, given an initial sentence-entity graph, we first introduce a graph-based classifier to predict pairwise orderings between linked sentences. Then, in an iterative manner, based on the graph updated by previously predicted high-confident pairwise orderings, another classifier is used to predict the remaining uncertain pairwise orderings. At last, we adapt a GRN-based sentence ordering model (Yin et al. 2019, 2021) on the basis of final graph. Experiments on five commonly-used datasets demonstrate the effectiveness and generality of our model. Particularly, when equipped with BERT (Devlin et al. 2019) and FHDecoder (Yin et al. 2020), our model achieves state-of-the-art performance. Our code is available at https://github.com/DeepLearnXMU/IRSEG.
References used
https://aclanthology.org/
rate research
Read More
Sentence splitting involves the segmentation of a sentence into two or more shorter sentences. It is a key component of sentence simplification, has been shown to help human comprehension and is a useful preprocessing step for NLP tasks such as summa
risation and relation extraction. While several methods and datasets have been proposed for developing sentence splitting models, little attention has been paid to how sentence splitting interacts with discourse structure. In this work, we focus on cases where the input text contains a discourse connective, which we refer to as discourse-based sentence splitting. We create synthetic and organic datasets for discourse-based splitting and explore different ways of combining these datasets using different model architectures. We show that pipeline models which use discourse structure to mediate sentence splitting outperform end-to-end models in learning the various ways of expressing a discourse relation but generate text that is less grammatical; that large scale synthetic data provides a better basis for learning than smaller scale organic data; and that training on discourse-focused, rather than on general sentence splitting data provides a better basis for discourse splitting.
Sentence fusion is a conditional generation task that merges several related sentences into a coherent one, which can be deemed as a summary sentence. The importance of sentence fusion has long been recognized by communities in natural language gener
ation, especially in text summarization. It remains challenging for a state-of-the-art neural abstractive summarization model to generate a well-integrated summary sentence. In this paper, we explore the effective sentence fusion method in the context of text summarization. We propose to build an event graph from the input sentences to effectively capture and organize related events in a structured way and use the constructed event graph to guide sentence fusion. In addition to make use of the attention over the content of sentences and graph nodes, we further develop a graph flow attention mechanism to control the fusion process via the graph structure. When evaluated on sentence fusion data built from two summarization datasets, CNN/DaliyMail and Multi-News, our model shows to achieve state-of-the-art performance in terms of Rouge and other metrics like fusion rate and faithfulness.
Understanding narrative text requires capturing characters' motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal- states of characters in a story. We explicitly model entities, their i
nteractions and the context in which they appear, and learn rich representations for them. We experiment with different task-adaptive pre-training objectives, in-domain training, and symbolic inference to capture dependencies between different decisions in the output space. We evaluate our model on two narrative understanding tasks: predicting character mental states, and desire fulfillment, and conduct a qualitative analysis.
Argument pair extraction (APE) aims to extract interactive argument pairs from two passages of a discussion. Previous work studied this task in the context of peer review and rebuttal, and decomposed it into a sequence labeling task and a sentence re
lation classification task. However, despite the promising performance, such an approach obtains the argument pairs implicitly by the two decomposed tasks, lacking explicitly modeling of the argument-level interactions between argument pairs. In this paper, we tackle the APE task by a mutual guidance framework, which could utilize the information of an argument in one passage to guide the identification of arguments that can form pairs with it in another passage. In this manner, two passages can mutually guide each other in the process of APE. Furthermore, we propose an inter-sentence relation graph to effectively model the inter-relations between two sentences and thus facilitates the extraction of argument pairs. Our proposed method can better represent the holistic argument-level semantics and thus explicitly capture the complex correlations between argument pairs. Experimental results show that our approach significantly outperforms the current state-of-the-art model.
Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relationa
l facts in dialogues are not supported by any single sentence, dialogue-based relation extraction requires a comprehensive understanding of dialogue. In this paper, we propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues. In addition, we propose a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialogue-based RE. Experiments on a dialogue-based RE dataset and three ERC datasets demonstrate that our model is very effective in various dialogue-based natural language understanding tasks. In these experiments, TUCORE-GCN outperforms the state-of-the-art models on most of the benchmark datasets. Our code is available at https://github.com/BlackNoodle/TUCORE-GCN.
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
