Related papers: Combining Textual and Structural Information for P…

This study introduces a novel approach to sentence-level relation extraction (RE) that integrates Graph Neural Networks (GNNs) with Large Language Models (LLMs) to generate contextually enriched support documents. By harnessing the power of…

Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar…

Entities are essential elements of natural language. In this paper, we present methods for learning multi-level representations of entities on three complementary levels: character (character patterns in entity names extracted, e.g., by…

Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due…

Sentence embeddings encode natural language sentences as low-dimensional dense vectors. A great deal of effort has been put into using sentence embeddings to improve several important natural language processing tasks. Relation extraction…

Large Language Models (LLMs) increasingly rely on knowledge graphs for factual reasoning, yet how retrieval design shapes their performance remains unclear. We examine how question decomposition changes the retrieved subgraph's content and…

Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…

Injecting textual information into knowledge graph (KG) entity representations has been a worthwhile expedition in terms of improving performance in KG oriented tasks within the NLP community. External knowledge often adopted to enhance KG…

Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items,…

Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves…

Document-level relation extraction (DocRE) poses the challenge of identifying relationships between entities within a document as opposed to the traditional RE setting where a single sentence is input. Existing approaches rely on logical…

Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel…

Machine learning in materials science faces challenges due to limited experimental data, as generating synthesis data is costly and time-consuming, especially with in-house experiments. Mining data from existing literature introduces issues…

In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled…

Recent advances in large language models enable documents to be represented as dense semantic embeddings, supporting similarity-based operations over large text collections. However, many web-scale systems still rely on flat clustering or…

A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets…

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…

Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily…

The paper introduces mixed networks, a new framework for expressing and reasoning with probabilistic and deterministic information. The framework combines belief networks with constraint networks, defining the semantics and graphical…

Language models can be used to identify relationships between financial entities in text. However, while structured output mechanisms exist, prompting-based pipelines still incur autoregressive decoding costs and decouple graph construction…