Natural Answer Generation with Heterogeneous Memory
Memory augmented encoder-decoder framework has achieved promising progress for natural language generation tasks. Such frameworks enable a decoder to retrieve from a memory during generation. However, less research has been done to take care of the memory contents from different sources, which are often of heterogeneous formats. In this work, we propose a novel attention mechanism to encourage the decoder to actively interact with the memory by taking its heterogeneity into account. Our solution attends across the generated history and memory to explicitly avoid repetition, and introduce related knowledge to enrich our generated sentences. Experiments on the answer sentence generation task show that our method can effectively explore heterogeneous memory to produce readable and meaningful answer sentences while maintaining high coverage for given answer information.
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationDecoderQuestion AnsweringSentenceText GenerationSimilar Papers 제목 키워드 기반
Memory-Augmented Knowledge Fusion with Safety-Aware Decoding for Domain-Adaptive Question Answering
Domain-specific question answering (QA) systems for services face unique challenges in integrating heterogeneous knowledge sources while ensuring both accuracy and safety. Existing large language models often struggle wi…
Question AnsweringBeyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
In existing memory benchmarks for Large Language Models (LLMs), the evaluated dialogue sessions often lack long-term semantic consistency, and the underlying personas tend to be flat and static. Furthermore, in real-worl…
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through d…
Question AnsweringIntegrating Large Language Models with Graph-based Reasoning for Conversational Question Answering
We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables…
Conversational Question AnsweringKnowledge GraphsQuestion AnsweringRetrieval+1Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from a…
Question AnsweringVideo Question AnsweringVisual Question Answering (VQA)