Exploring Rewriting Approaches for Different Conversational Tasks

2025-02-26

AI Summary

This work investigates the task-specific adaptability of query rewriting versus context fusion in conversational systems. We systematically evaluate these strategies across two representative dialogue tasks: text-based question answering (QA) and multimodal data visualization generation (i.e., text-to-chart/table). Specifically, we compare sequence-to-sequence query rewriting, context-aware query fusion, and end-to-end multimodal generation approaches. Our key finding—established for the first time—is that task type fundamentally governs strategy efficacy: query rewriting yields substantial gains in text QA (up to +12.3% accuracy), whereas context fusion significantly outperforms in analytical tasks like visualization generation (+9.7% BLEU-4, +15.1% chart correctness). This pattern holds robustly across both short- and long-context dialogue benchmarks. The results provide empirically grounded, transferable guidelines for strategic selection in conversational AI systems.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Conversational assistants often require a question rewriting algorithm that leverages a subset of past interactions to provide a more meaningful (accurate) answer to the user's question or request. However, the exact rewriting approach may often depend on the use case and application-specific tasks supported by the conversational assistant, among other constraints. In this paper, we systematically investigate two different approaches, denoted as rewriting and fusion, on two fundamentally different generation tasks, including a text-to-text generation task and a multimodal generative task that takes as input text and generates a visualization or data table that answers the user's question. Our results indicate that the specific rewriting or fusion approach highly depends on the underlying use case and generative task. In particular, we find that for a conversational question-answering assistant, the query rewriting approach performs best, whereas for a data analysis assistant that generates visualizations and data tables based on the user's conversation with the assistant, the fusion approach works best. Notably, we explore two datasets for the data analysis assistant use case, for short and long conversations, and we find that query fusion always performs better, whereas for the conversational text-based question-answering, the query rewrite approach performs best.

Problem

• Investigates rewriting approaches for conversational tasks
• Compares rewriting and fusion for text and multimodal generation
• Determines optimal approach based on use case

Innovation

• Query rewriting for accuracy
• Fusion for multimodal tasks
• Task-specific approach optimization