paper-with-me

Papers

ReadTwice: Reading Very Large Documents with Memories

2021-05-10 · NAACL 2021 4 · Yury Zemlyanskiy, Joshua Ainslie, Michiel de Jong, Philip Pham, Ilya Eckstein, Fei Sha

Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose ReadTwice, a simple and effective technique that combines several strengths of prior approaches to model long-range dependencies with Transformers. The main idea is to read text in small segments, in parallel, summarizing each segment into a memory table to be used in a second read of the text. We show that the method outperforms models of comparable size on several question answering (QA) datasets and sets a new state of the art on the challenging NarrativeQA task, with questions about entire books. Source code and pre-trained checkpoints for ReadTwice can be found at https://goo.gle/research-readtwice.

📄 PDF Abstract BibTeX arXiv:2105.04241

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

2024-02-15 · Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John Canny 외

Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system tha…

Reading ComprehensionRetrieval

Memorizing Documents with Guidance in Large Language Models

2024-06-23 · Bumjin Park, Jaesik Choi

Training data plays a pivotal role in AI models. Large language models (LLMs) are trained with massive amounts of documents, and their parameters hold document-related contents. Recently, several studies identified conte…

MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems

2025-10-16 · Jihao Zhao, Zhiyuan Ji, Simin Niu, Hanyu Wang 외 arxiv

The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilit…

Deep Inductive Logic Reasoning for Multi-Hop Reading Comprehension

2022-05-01 · ACL 2022 5 · Wenya Wang, Sinno Pan

Multi-hop reading comprehension requires an ability to reason across multiple documents. On the one hand, deep learning approaches only implicitly encode query-related information into distributed embeddings which fail t…

Deep LearningMulti-Hop Reading ComprehensionReading ComprehensionRelational Reasoning

Equipping Transformer with Random-Access Reading for Long-Context Understanding

2024-05-21 · Chenghao Yang, Zi Yang, Nan Hua

Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues with length extrapolation caused by pre…

ChunkingLong-Context Understanding