Link prediction models can benefit from incorporating textual descriptions of entities and relations, enabling fully inductive learning and flexibility in dynamic graphs. We address the challenge of also capturing rich structured information about the local neighbourhood of entities and their relations, by introducing a Transformer-based approach that effectively integrates textual descriptions with graph structure, reducing the reliance on resource-intensive text encoders. Our experiments on three challenging datasets show that our Fast-and-Frugal Text-Graph (FnF-TG) Transformers achieve superior performance compared to the previous state-of-the-art methods, while maintaining efficiency and scalability.

Knowledge discovery in scientific literature is hindered by the increasing volume of publications and the scarcity of extensive annotated data. To tackle the challenge of information overload, it is essential to employ automated methods for knowledge extraction and processing. Finding the right balance between the level of supervision and the effectiveness of models poses a significant challenge. While supervised techniques generally result in better performance, they have the major drawback of demanding labeled data. This requirement is labor-intensive, time-consuming, and hinders scalability when exploring new domains. In this context, our study addresses the challenge of identifying semantic relationships between biomedical entities (e.g., diseases, proteins, medications) in unstructured text while minimizing dependency on supervision. We introduce a suite of unsupervised algorithms based on dependency trees and attention mechanisms and employ a range of pointwise binary classification methods. Transitioning from weakly supervised to fully unsupervised settings, we assess the methods’ ability to learn from data with noisy labels. The evaluation on four biomedical benchmark datasets explores the effectiveness of the methods, demonstrating their potential to enable scalable knowledge discovery systems less reliant on annotated datasets. Our approach tackles a central issue in knowledge discovery: balancing performance with minimal supervision which is crucial to adapting models to varied and changing domains. This study also investigates the use of pointwise binary classification techniques within a weakly supervised framework for knowledge discovery. By gradually decreasing supervision, we assess the robustness of these techniques in handling noisy labels, revealing their capability to shift from weakly supervised to entirely unsupervised scenarios. Comprehensive benchmarking offers insights into the effectiveness of these techniques, examining how unsupervised methods can reliably capture complex relationships in biomedical texts. These results suggest an encouraging direction toward scalable, adaptable knowledge discovery systems, representing progress in creating data-efficient methodologies for extracting useful insights when annotated data is limited.

Existing Reward Models (RMs), typically trained on general preference data, struggle in Retrieval Augmented Generation (RAG) settings, which require judging responses for faithfulness to retrieved context, relevance to the user query, appropriate refusals when context is insufficient, completeness and conciseness of information. To address the lack of publicly available RAG-centric preference datasets and specialised RMs, we introduce RAGferee, a methodology that repurposes question-answering (QA) datasets into preference pairs that prioritise groundedness over stylistic features, enabling the training of contextual RMs better suited to judging RAG responses. Using RAGferee, we curate a small preference dataset of 4K samples and fine-tune RMs ranging from 7B to 24B parameters. Our RAG-centric RMs achieve state-of-the-art performance on ContextualJudgeBench, surpassing existing 70B+ RMs trained on much larger (up to 2.4M samples) general corpora, with an absolute improvement of +15.5

The rapidly increasing number of biomedical publications presents a significant challenge for efficient knowledge discovery. To address this, we introduce an open-source, end-to-end framework designed to automatically extract and construct knowledge about specific diseases directly from unstructured text. To facilitate research in disease-related knowledge discovery, we create two annotated datasets focused on Rett syndrome (RS) and Alzheimer’s disease (AD), enabling the identification of semantic relations between various biomedical entities. We perform extensive benchmarking to evaluate different approaches for representing relations and entities, providing insights into optimal modeling strategies for semantic relation detection and highlighting language models’ competence in knowledge discovery. To gain a deeper understanding of the internal mechanisms of transformer models, we also conduct probing experiments, analyzing different layer representations and attention scores, to explore transformers’ ability to capture semantic relations within the text. Both the code and the datasets will be publicly available at https://github.com/christos42/Enhancing-Biomedical-Knowledge-Discovery-for-Diseases, encouraging further research in biomedical knowledge discovery.

Document-level relation extraction typically relies on text-based encoders and hand-coded pooling heuristics to aggregate information learned by the encoder. In this paper, we leverage the intrinsic graph processing capabilities of the Transformer model and propose replacing hand-coded pooling methods with new tokens in the input, which are designed to aggregate information via explicit graph relations in the computation of attention weights. We introduce a joint text-graph Transformer model and a graph-assisted declarative pooling (GADePo) specification of the input, which provides explicit and high-level instructions for information aggregation. GADePo allows the pooling process to be guided by domain-specific knowledge or desired outcomes but still learned by the Transformer, leading to more flexible and customisable pooling strategies. We evaluate our method across diverse datasets and models and show that our approach yields promising results that are consistently better than those achieved by the hand-coded pooling functions.

We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability explicit, by inputting graph edges into the attention weight computations and predicting graph edges with attention-like functions, thereby integrating explicit graphs into the latent graphs learned by pretrained Transformers. Adding iterative graph refinement provides a joint embedding of input, output, and latent graphs, allowing non-autoregressive graph prediction to optimise the complete graph without any bespoke pipeline or decoding strategy. Empirical results show that this architecture achieves state-of-the-art accuracies for modelling a variety of linguistic structures, integrating very effectively with the latent linguistic representations learned by pretraining.

Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both efficiency and effectiveness. In this paper, we study the State-of-the-Art (SotA) Dense Passage Retrieval (DPR) retriever and Fusion-in-Decoder (FiD) reader pipeline, and show that it significantly underperforms when applied to ODConvQA tasks due to various limitations. We then propose and evaluate strong yet simple and efficient baselines, by introducing a fast reranking component between the retriever and the reader, and by performing targeted finetuning steps. Experiments on two ODConvQA tasks, namely TopiOCQA and OR-QuAC, show that our method improves the SotA results, while reducing reader's latency by 60%. Finally, we provide new and valuable insights into the development of challenging baselines that serve as a reference for future, more intricate approaches, including those that leverage Large Language Models (LLMs).

Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al., 2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.

We present the Romanian legislative corpus which is a valuable linguistic asset for the development of machine translation systems, especially for under-resourced languages. The knowledge that can be extracted from this resource is necessary for a deeper understanding of how law terminology is used and how it can be made more consistent. At this moment, the corpus contains more than 144k documents representing the legislative body of Romania. This corpus is processed and annotated at different levels: linguistically (tokenized, lemmatized and POS-tagged), dependency parsed, chunked, named entities identified and labeled with IATE terms and EUROVOC descriptors. Each annotated document has a CONLL-U Plus format consisting of 14 columns; in addition to the standard 10-column format, four other types of annotations were added. Moreover the repository will be periodically updated as new legislative texts are published. These will be automatically collected and transmitted to the processing and annotation pipeline. The access to the corpus is provided through ELRC infrastructure.

In a human-machine dialog scenario, deciding the appropriate time for the machine to take the turn is an open research problem. In contrast, humans engaged in conversations are able to timely decide when to interrupt the speaker for competitive or non-competitive reasons. In state-of-the-art turn-by-turn dialog systems the decision on the next dialog action is taken at the end of the utterance. In this paper, we propose a token-by-token prediction of the dialog state from incremental transcriptions of the user utterance. To identify the point of maximal understanding in an ongoing utterance, we a) implement an incremental Dialog State Tracker which is updated on a token basis (iDST) b) re-label the Dialog State Tracking Challenge 2 (DSTC2) dataset and c) adapt it to the incremental turn-taking experimental scenario. The re-labeling consists of assigning a binary value to each token in the user utterance that allows to identify the appropriate point for taking the turn. Finally, we implement an incremental Turn Taking Decider (iTTD) that is trained on these new labels for the turn-taking decision. We show that the proposed model can achieve a better performance compared to a deterministic handcrafted turn-taking algorithm.

In this paper, we present our approach that has won the ITAmoji task of the 2018 edition of the EVALITA evaluation campaign1. ITAmoji is a classification task for predicting the most probable emoji (a total of 25 classes) to go along with the target tweet written by a given person in Italian. We demonstrate that using only textual features is insufficient to achieve reasonable performance levels on this task and propose a system that is able to benefit from the multimodal information contained in the training set, enabling significant gains and earning us the first place in the final ranking.