Related papers: OntoGUM: Evaluating Contextualized SOTA Coreferenc…
The application of on-device language models (ODLMs) on resource-constrained edge devices is a multi-dimensional problem that strikes a fine balance between computational effectiveness, memory, power usage, and linguistic capacity across…
Retrieval-Augmented Generation (RAG) enhances LLM factuality, but multi-domain applications face challenges like lack of diverse benchmarks and poor out-of-domain generalization. The first contribution of this work is to introduce a diverse…
While coreference resolution is traditionally used as a component in individual document understanding, in this work we take a more global view and explore what can we learn about a domain from the set of all document-level coreference…
Multilingual coreference resolution (MCR) has been a long-standing and challenging task. With the newly proposed multilingual coreference dataset, CorefUD (Nedoluzhko et al., 2022), we conduct an investigation into the task by using its…
Organizing a large-scale knowledge graph into a typed property graph requires structural decisions -- which entities become nodes, which properties become edges, and what schema governs these choices. Existing approaches embed these…
Whether Large Language Models (LLMs) truly possess human-like Theory of Mind (ToM) capabilities has garnered increasing attention. However, existing benchmarks remain largely restricted to narrow paradigms like false belief tasks, failing…
Since the first end-to-end neural coreference resolution model was introduced, many extensions to the model have been proposed, ranging from using higher-order inference to directly optimizing evaluation metrics using reinforcement…
Most existing medication recommendation models learn representations for medical concepts based on electronic health records (EHRs) and make recommendations with learnt representations. However, most medications appear in the dataset for…
Coreference resolution, the task of identifying expressions in text that refer to the same entity, is a critical component in various natural language processing applications. This paper presents a novel end-to-end neural coreference…
Large Language Models (LLMs) have achieved remarkable success but remain data-inefficient, especially when learning from small, specialized corpora with limited and proprietary data. Existing synthetic data generation methods for continue…
Large Language Models (LLMs) demonstrate significant advantages in leveraging structured world knowledge and multi-step reasoning capabilities. However, fundamental challenges arise when transforming LLMs into real-world recommender systems…
Generative recommendation is an emerging paradigm that leverages the extensive knowledge of large language models by formulating recommendations into a text-to-text generation task. However, existing studies face two key limitations in (i)…
Structured data sources, such as tables, graphs, and databases, are ubiquitous knowledge sources. Despite the demonstrated capabilities of large language models (LLMs) on plain text, their proficiency in interpreting and utilizing…
Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark…
With the wide proliferation of Deep Neural Networks in high-stake applications, there is a growing demand for explainability behind their decision-making process. Concept learning models attempt to learn high-level 'concepts' - abstract…
We present an end-to-end system for musical key estimation, based on a convolutional neural network. The proposed system not only out-performs existing key estimation methods proposed in the academic literature; it is also capable of…
Ontologies are useful for automatic machine processing of domain knowledge as they represent it in a structured format. Yet, constructing ontologies requires substantial manual effort. To automate part of this process, large language models…
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. Compared with the general coreference resolution task, the main challenge of PCR is the coreference relation prediction…
Coreference resolution in biomedical texts presents unique challenges due to complex domain-specific terminology, high ambiguity in mention forms, and long-distance dependencies between coreferring expressions. In this work, we present a…
Subword tokenization has become the de-facto standard for tokenization, although comparative evaluations of subword vocabulary quality across languages are scarce. Existing evaluation studies focus on the effect of a tokenization algorithm…