Related papers: Graph Pre-training for AMR Parsing and Generation
Despite extensive research on parsing of English sentences into Abstraction Meaning Representation (AMR) graphs, which are compared to gold graphs via the Smatch metric, full-document parsing into a unified graph representation lacks…
As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser. Previous studies formalize it as a…
Large language models (LLMs) have demonstrated remarkable in-context reasoning capabilities across a wide range of tasks, particularly with unstructured inputs such as language or images. However, LLMs struggle to handle structured data,…
Graphs with abundant attributes are essential in modeling interconnected entities and enhancing predictions across various real-world applications. Traditional Graph Neural Networks (GNNs) often require re-training for different graph tasks…
Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs). Myriad approaches have linearized the input graph as a sequence of tokens to fit the PLM…
Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks. However, bridging the modality gap between graph structures and text remains a significant challenge. Traditional…
Automatic open-domain dialogue evaluation has attracted increasing attention, yet remains challenging due to the complexity of assessing response appropriateness. Traditional evaluation metrics, typically trained with true positive and…
User-generated texts available on the web and social platforms are often long and semantically challenging, making them difficult to annotate. Obtaining human annotation becomes increasingly difficult as problem domains become more…
The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to…
Recent efforts leverage Large Language Models (LLMs) for modeling text-attributed graph structures in node classification tasks. These approaches describe graph structures for LLMs to understand or aggregate LLM-generated textual attribute…
Large language models (LLMs) have achieved impressive performance on many natural language processing tasks. However, their capabilities on graph-structured data remain relatively unexplored. In this paper, we conduct a series of…
Text Generation aims to produce plausible and readable text in a human language from input data. The resurgence of deep learning has greatly advanced this field, in particular, with the help of neural generation models based on pre-trained…
With an ever increasing size of text present on the Internet, automatic summary generation remains an important problem for natural language understanding. In this work we explore a novel full-fledged pipeline for text summarization with an…
Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However, given the open-ended nature of LLMs, e.g., their ability…
Graphs are an essential data structure utilized to represent relationships in real-world scenarios. Prior research has established that Graph Neural Networks (GNNs) deliver impressive outcomes in graph-centric tasks, such as link prediction…
Significant efforts have been dedicated to integrating the powerful Large Language Models (LLMs) with diverse modalities, particularly focusing on the fusion of language, vision and audio data. However, the graph-structured data, which is…
In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models,…
We introduce a novel scheme for parsing a piece of text into its Abstract Meaning Representation (AMR): Graph Spanning based Parsing (GSP). One novel characteristic of GSP is that it constructs a parse graph incrementally in a top-down…
Pre-trained sentence representations are crucial for identifying significant sentences in unsupervised document extractive summarization. However, the traditional two-step paradigm of pre-training and sentence-ranking, creates a gap due to…
Query understanding plays a key role in exploring users' search intents and facilitating users to locate their most desired information. However, it is inherently challenging since it needs to capture semantic information from short and…