Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userIncorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
دمج بناء الجملة والدلالات في دقة Aquerence مع شبكة انتباه الرسوم البيانية غير المتوجهة
588
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تم تجاهل المعلومات النحوية والدلية الخارجية إلى حد كبير من قبل نماذج حل النواة العصبية الحالية.في هذه الورقة، نقدم نموذجا مقرا له من الرسوم البيانية غير متجانسة لإدماج الهياكل النحوية والدلالية للجمل.يحتوي الرسم البياني المقترح على رسم بياني فرعي سنوي حيث يتم توصيل الرموز الرائعة بناء على شجرة التبعية، ورسم إلكتروني فرعي دلالي يحتوي على حجج ويستند كمستلزمات دورا دالايا كحواف.من خلال تطبيق شبكة انتباه الرسوم البيانية، يمكننا الحصول على تمثيل كلمة معدنية من الناحية النحوية وغير المعزز، والتي يمكن دمجها باستخدام طبقة تكامل اليقظة وآلية Gating.تجارب في OnTonotes 5.0 معيار المعيار إظهار فعالية نموذجنا المقترح.
External syntactic and semantic information has been largely ignored by existing neural coreference resolution models. In this paper, we present a heterogeneous graph-based model to incorporate syntactic and semantic structures of sentences. The proposed graph contains a syntactic sub-graph where tokens are connected based on a dependency tree, and a semantic sub-graph that contains arguments and predicates as nodes and semantic role labels as edges. By applying a graph attention network, we can obtain syntactically and semantically augmented word representation, which can be integrated using an attentive integration layer and gating mechanism. Experiments on the OntoNotes 5.0 benchmark show the effectiveness of our proposed model.
References used
https://aclanthology.org/
rate research
Read More
Existing sarcasm detection systems focus on exploiting linguistic markers, context, or user-level priors. However, social studies suggest that the relationship between the author and the audience can be equally relevant for the sarcasm usage and inte
rpretation. In this work, we propose a framework jointly leveraging (1) a user context from their historical tweets together with (2) the social information from a user's conversational neighborhood in an interaction graph, to contextualize the interpretation of the post. We use graph attention networks (GAT) over users and tweets in a conversation thread, combined with dense user history representations. Apart from achieving state-of-the-art results on the recently published dataset of 19k Twitter users with 30K labeled tweets, adding 10M unlabeled tweets as context, our results indicate that the model contributes to interpreting the sarcastic intentions of an author more than to predicting the sarcasm perception by others.
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.
Recently, disentanglement based on a generative adversarial network or a variational autoencoder has significantly advanced the performance of diverse applications in CV and NLP domains. Nevertheless, those models still work on coarse levels in the d
isentanglement of closely related properties, such as syntax and semantics in human languages. This paper introduces a deep decomposable model based on VAE to disentangle syntax and semantics by using total correlation penalties on KL divergences. Notably, we decompose the KL divergence term of the original VAE so that the generated latent variables can be separated in a more clear-cut and interpretable way. Experiments on benchmark datasets show that our proposed model can significantly improve the disentanglement quality between syntactic and semantic representations for semantic similarity tasks and syntactic similarity tasks.
Multi-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such as document metadata or
label structure. These approaches however either simply utilize the semantic information of metadata or employ the predefined parent-child label hierarchy, ignoring the heterogeneous graphical structures of metadata and labels, which we believe are crucial for accurate multi-label document classification. Therefore, in this paper, we propose a novel neural network based approach for multi-label document classification, in which two heterogeneous graphs are constructed and learned using heterogeneous graph transformers. One is metadata heterogeneous graph, which models various types of metadata and their topological relations. The other is label heterogeneous graph, which is constructed based on both the labels' hierarchy and their statistical dependencies. Experimental results on two benchmark datasets show the proposed approach outperforms several state-of-the-art baselines.
The encoder--decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not. However, relying solely on the source docu
ment can result in generating uncontrollable and inaccurate absent keyphrases. To address these problems, we propose a novel graph-based method that can capture explicit knowledge from related references. Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references. Then a heterogeneous graph is constructed to capture relations with different levels of granularity of the source document and its retrieved references. To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both source document and its references based on their relevance and significance. The experimental results on multiple KG benchmarks show that the proposed model achieves significant improvements against other baseline models, especially with regard to the absent keyphrase prediction.
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
