Related papers: AMPERE: AMR-Aware Prefix for Generation-Based Even…

Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the entire image, the depicted event, and the interactions between…

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…

While text-based event extraction has been an active research area and has seen successful application in many domains, extracting semantic events from speech directly is an under-explored problem. In this paper, we introduce the Speech…

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…

Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense disambiguation and co-reference…

Complex Event Recognition (CER) systems are used to identify complex patterns in event streams, such as those found in stock markets, sensor networks, and other similar applications. An important task in such patterns is aggregation, which…

Abstract Meaning Representation (AMR) is a recently designed semantic representation language intended to capture the meaning of a sentence, which may be represented as a single-rooted directed acyclic graph with labeled nodes and edges.…

Monitoring and analyzing process traces is a critical task for modern companies and organizations. In scenarios where there is a gap between trace events and reference business activities, this entails an interpretation problem, amounting…

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated…

The diverse relationships among real-world events, including coreference, temporal, causal, and subevent relations, are fundamental to understanding natural languages. However, two drawbacks of existing datasets limit event relation…

A plethora of approaches have been proposed for joint entity-relation (ER) extraction. Most of these methods largely depend on a large amount of manually annotated training data. However, manual data annotation is time consuming, labor…

Event Detection (ED) -- the task of identifying event mentions from natural language text -- is critical for enabling reasoning in highly specialized domains such as biomedicine, law, and epidemiology. Data generation has proven to be…

Argument mining involves multiple sub-tasks that automatically identify argumentative elements, such as claim detection, evidence extraction, stance classification, etc. However, each subtask alone is insufficient for a thorough…

As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing. We find that 1) Semantic role labeling…

Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large…

Events are essential components of speech and texts, describing the changes in the state of entities. The event extraction task aims to identify and classify events and find their participants according to event schemas. Manually predefined…

Structural extraction of events within discourse is critical since it avails a deeper understanding of communication patterns and behavior trends. Event argument extraction (EAE), at the core of event-centric understanding, is the task of…

Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve…