paper-with-me

홈 › Papers

CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering

2020-11-01 · COLING 2020 8 · Junru Lu, Gabriele Pergola, Lin Gui, Binyang Li, Yulan He

We introduce CHIME, a cross-passage hierarchical memory network for question answering (QA) via text generation. It extends XLNet introducing an auxiliary memory module consisting of two components: the context memory collecting cross-passage evidences, and the answer memory working as a buffer continually refining the generated answers. Empirically, we show the efficacy of the proposed architecture in the multi-passage generative QA, outperforming the state-of-the-art baselines with better syntactically well-formed answers and increased precision in addressing the questions of the AmazonQA review dataset. An additional qualitative analysis revealed the interpretability introduced by the memory module.

📄 PDF Abstract BibTeX arXiv:2011.00519

Code (1)

LuJunru/CHIME 공식 구현 pytorch

Tasks

Question AnsweringText Generation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Interpretability 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Generative Archimedean Copulas

2021-02-22 · Yuting Ng, Ali Hasan, Khalil Elkhalil, Vahid Tarokh

We propose a new generative modeling technique for learning multidimensional cumulative distribution functions (CDFs) in the form of copulas. Specifically, we consider certain classes of copulas known as Archimedean and …

Computational Efficiency

Modeling Multi-hop Question Answering as Single Sequence Prediction

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, t…

Answer GenerationDecoderGenerative Question AnsweringMulti-hop Question Answering+4

Modeling Multi-hop Question Answering as Single Sequence Prediction

2022-05-18 · ACL 2022 5 · Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Nitish Shirish Keskar 외

Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, t…

Answer GenerationDecoderGenerative Question AnsweringMulti-hop Question Answering+4

A Unified Query-based Generative Model for Question Generation and Question Answering

2017-09-04 · Linfeng Song, Zhiguo Wang, Wael Hamza

We propose a query-based generative model for solving both tasks of question generation (QG) and question an- swering (QA). The model follows the classic encoder- decoder framework. The encoder takes a passage and a quer…

DecoderQuestion AnsweringQuestion GenerationQuestion-Generation+1

CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference

2025-12-12 · Yanru Chen, Runyang Tian, Yue Pan, Zheyu Li 외 arxiv

The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated …