Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks
تفاعلات التمثيل المثيل عبر المهمة والتبعية التسمية لاستخراج المعلومات المشتركة مع شبكات تشفيرية رسمية
264
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعمل الأعمال الموجودة على استخراج المعلومات (IE) بشكل أساسي المهام الرئيسية الأربعة بشكل منفصل (إبلاغ الكيان بالاعتراف بالاعتراف، واستخراج العلاقة، والكشف عن الحدث، واستخراج الوسيطة)، وبالتالي الفشل في الاستفادة من التبعيات بين المهام. تقدم هذه الورقة نموذجا تعليميا عميقا جديدا لحل المهام الأربع الأربعة في وقت واحد في نموذج واحد (يسمى Fourie). بالمقارنة مع عدد قليل من العمل السابق في أداء مهام IE المشتركة، تتميز Fourie بمساهمات جديدة لالتقاط التبعيات بين المهام. أولا، في مستوى التمثيل، نقدم رسم بياني تفاعل بين مثيلات المهام الأربعة المستخدمة لإثراء تمثيل التنبؤ بمثيل واحد مع أولئك من مثيلات المهام الأخرى ذات الصلة. ثانيا، على مستوى العلامة، نقترح رسم بياني للاعتماد لأنواع المعلومات في المهام الأربعة IE التي تلتقط الاتصالات بين الأنواع المعبر عنها في جملة مدخلات. يتم تقديم آلية تنظيمية جديدة لإنفاذ الاتساق بين الرسوم البيانية الذهبية المتوقعة والتنبؤ بها لتحسين تعلم التمثيل. نظهر أن النموذج المقترح يحقق الأداء الحديثة للمفصل IE على كل من إعدادات التعلم أحادية اللغات وغير اللغوية بأثلاثة لغات مختلفة.
Existing works on information extraction (IE) have mainly solved the four main tasks separately (entity mention recognition, relation extraction, event trigger detection, and argument extraction), thus failing to benefit from inter-dependencies between tasks. This paper presents a novel deep learning model to simultaneously solve the four tasks of IE in a single model (called FourIE). Compared to few prior work on jointly performing four IE tasks, FourIE features two novel contributions to capture inter-dependencies between tasks. First, at the representation level, we introduce an interaction graph between instances of the four tasks that is used to enrich the prediction representation for one instance with those from related instances of other tasks. Second, at the label level, we propose a dependency graph for the information types in the four IE tasks that captures the connections between the types expressed in an input sentence. A new regularization mechanism is introduced to enforce the consistency between the golden and predicted type dependency graphs to improve representation learning. We show that the proposed model achieves the state-of-the-art performance for joint IE on both monolingual and multilingual learning settings with three different languages.
References used
https://aclanthology.org/
rate research
Read More
The tasks of Rich Semantic Parsing, such as Abstract Meaning Representation (AMR), share similar goals with Information Extraction (IE) to convert natural language texts into structured semantic representations. To take advantage of such similarity,
we propose a novel AMR-guided framework for joint information extraction to discover entities, relations, and events with the help of a pre-trained AMR parser. Our framework consists of two novel components: 1) an AMR based semantic graph aggregator to let the candidate entity and event trigger nodes collect neighborhood information from AMR graph for passing message among related knowledge elements; 2) an AMR guided graph decoder to extract knowledge elements based on the order decided by the hierarchical structures in AMR. Experiments on multiple datasets have shown that the AMR graph encoder and decoder have provided significant gains and our approach has achieved new state-of-the-art performance on all IE subtasks.
We study the problem of Event Causality Identification (ECI) to detect causal relation between event mention pairs in text. Although deep learning models have recently shown state-of-the-art performance for ECI, they are limited to the intra-sentence
setting where event mention pairs are presented in the same sentences. This work addresses this issue by developing a novel deep learning model for document-level ECI (DECI) to accept inter-sentence event mention pairs. As such, we propose a graph-based model that constructs interaction graphs to capture relevant connections between important objects for DECI in input documents. Such interaction graphs are then consumed by graph convolutional networks to learn document context-augmented representations for causality prediction between events. Various information sources are introduced to enrich the interaction graphs for DECI, featuring discourse, syntax, and semantic information. Our extensive experiments show that the proposed model achieves state-of-the-art performance on two benchmark datasets.
Recent metaphor identification approaches mainly consider the contextual text features within a sentence or introduce external linguistic features to the model. But they usually ignore the extra information that the data can provide, such as the cont
extual metaphor information and broader discourse information. In this paper, we propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level. At the sentence level, we leverage the metaphor information of words that except the target word in the sentence to strengthen the reasoning ability of our model via a novel label-enhanced contextualized representation. At the discourse level, the position-aware global memory network is adopted to learn long-range dependency among the same words within a discourse. Finally, our model combines the representations obtained from these two parts. The experiment results on two tasks of the VUA dataset show that our model outperforms every other state-of-the-art method that also does not use any external knowledge except what the pre-trained language model contains.
Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle
relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.
We offer a fine-grained information state annotation scheme that follows directly from the Incremental Unit abstract model of dialogue processing when used within a multimodal, co-located, interactive setting. We explain the Incremental Unit model and give an example application using the Localized Narratives dataset, then offer avenues for future research.
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
