Related papers: Retrieve-and-Fill for Scenario-based Task-Oriented…

We present a simple and accurate span-based model for semantic role labeling (SRL). Our model directly takes into account all possible argument spans and scores them for each label. At decoding time, we greedily select higher scoring…

The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…

Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to…

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…

Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we…

Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While these generalization capabilities to an unknown environment…

Recall the classical text generation works, the generation framework can be briefly divided into two phases: \textbf{idea reasoning} and \textbf{surface realization}. The target of idea reasoning is to figure out the main idea which will be…

Task-oriented semantic parsing models typically have high resource requirements: to support new ontologies (i.e., intents and slots), practitioners crowdsource thousands of samples for supervised fine-tuning. Partly, this is due to the…

Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent and slots in the user's input utterance. This creates a…

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on…

Extracting graph representation of visual scenes in image is a challenging task in computer vision. Although there has been encouraging progress of scene graph generation in the past decade, we surprisingly find that the performance of…

Frame semantic parsing is a complex problem which includes multiple underlying subtasks. Recent approaches have employed joint learning of subtasks (such as predicate and argument detection), and multi-task learning of related tasks (such…

In this paper, we propose using deep neural architectures (i.e., vision transformers and ResNet) as heuristics for sequential decision-making in robotic manipulation problems. This formulation enables predicting the subset of objects that…

The development of new assessment methods for the performance of automated vehicles is essential to enable the deployment of automated driving technologies, due to the complex operational domain of automated vehicles. One contributing…

The ability for computational agents to reason about the high-level content of real world scene images is important for many applications. Existing attempts at addressing the problem of complex scene understanding lack representational…

We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions…

Open-domain question answering can be formulated as a phrase retrieval problem, in which we can expect huge scalability and speed benefit but often suffer from low accuracy due to the limitation of existing phrase representation models. In…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentanglement between semantic…

Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more history into the model improves forecast quality. But in stochastic domains, distant history…