paper-with-me

홈 › Papers

Focused Attention Improves Document-Grounded Generation

2021-04-26 · NAACL 2021 4 · Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W Black, Ruslan Salakhutdinov

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue response generation. Our work introduces two novel adaptations of large scale pre-trained encoder-decoder models focusing on building context driven representation of the document and enabling specific attention to the information in the document. Additionally, we provide a stronger BART baseline for these tasks. Our proposed techniques outperform existing methods on both automated (at least 48% increase in BLEU-4 points) and human evaluation for closeness to reference and relevance to the document. Furthermore, we perform comprehensive manual inspection of the generated output and categorize errors to provide insights into future directions in modeling these tasks.

📄 PDF Abstract BibTeX arXiv:2104.12714

Code (1)

shrimai/Focused-Attention-Improves-Document-Grounded-Generation 공식 구현 pytorch

Tasks

DecoderResponse GenerationText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 &…
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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Multi-Head Attention 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…

Similar Papers 제목 키워드 기반

Asking Complex Questions with Multi-hop Answer-focused Reasoning

2020-09-16 · Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li 외

Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the i…

Question GenerationQuestion-Generation

UGent-T2K at the 2nd DialDoc Shared Task: A Retrieval-Focused Dialog System Grounded in Multiple Documents

2022-05-01 · dialdoc (ACL) 2022 5 · Yiwei Jiang, Amir Hadifar, Johannes Deleu, Thomas Demeester 외

This work presents the contribution from the Text-to-Knowledge team of Ghent University (UGent-T2K) to the MultiDoc2Dial shared task on modeling dialogs grounded in multiple documents. We propose a pipeline system, compr…

DecoderPassage RetrievalResponse GenerationRetrieval

QontSum: On Contrasting Salient Content for Query-focused Summarization

2023-07-14 · Sajad Sotudeh, Nazli Goharian

Query-focused summarization (QFS) is a challenging task in natural language processing that generates summaries to address specific queries. The broader field of Generative Information Retrieval (Gen-IR) aims to revoluti…

Answer GenerationContrastive LearningInformation RetrievalQuery-focused Summarization+1

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

2026-07-01 · Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi, Sai Soorya Rao Veeravalli 외 arxiv

As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal attributions have been explored in depth…

Question Answering

A Compare Aggregate Transformer for Understanding Document-grounded Dialogue

2020-10-01 · Findings of the Association for Computational Linguistics 2020 · Longxuan Ma, Wei-Nan Zhang, Runxin Sun, Ting Liu

Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue hi…

Response Generation