paper-with-me

홈 › Papers

Chain-of-Skills: A Configurable Model for Open-domain Question Answering

2023-05-04 · Kaixin Ma, Hao Cheng, Yu Zhang, Xiaodong Liu, Eric Nyberg, Jianfeng Gao

The retrieval model is an indispensable component for real-world knowledge-intensive tasks, e.g., open-domain question answering (ODQA). As separate retrieval skills are annotated for different datasets, recent work focuses on customized methods, limiting the model transferability and scalability. In this work, we propose a modular retriever where individual modules correspond to key skills that can be reused across datasets. Our approach supports flexible skill configurations based on the target domain to boost performance. To mitigate task interference, we design a novel modularization parameterization inspired by sparse Transformer. We demonstrate that our model can benefit from self-supervised pretraining on Wikipedia and fine-tuning using multiple ODQA datasets, both in a multi-task fashion. Our approach outperforms recent self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.

📄 PDF Abstract BibTeX arXiv:2305.03130

Code (1)

mayer123/udt-qa pytorch

Tasks

Open-Domain Question AnsweringQuestion AnsweringRetrievalWorld Knowledge

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
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…
Multi-Head Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining

2009-12-01 · NeurIPS 2009 12 · George Konidaris, Andrew G. Barto

We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains, that builds chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

healthAIChain: Improving security and safety using Blockchain Technology applications in AI-based healthcare systems

2023-11-01 · Naresh Kshetri, James Hutson, Revathy G

Blockchain as a digital ledger for keeping records of digital transactions and other information, it is secure and decentralized technology. The globally growing number of digital population every day possesses a signifi…

Can large language models reason about medical questions?

2022-07-17 · Valentin Liévin, Christoffer Egeberg Hother, Andreas Geert Motzfeldt, Ole Winther

Although large language models (LLMs) often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge. We set out to investigate…

MedQAMultiple-choiceMultiple Choice Question Answering (MCQA)Prompt Engineering+3

Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering

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

Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAin-centri…

Open-Domain Question AnsweringQuestion Answering

Granger Causal Interaction Skill Chains

2023-06-15 · Caleb Chuck, Kevin Black, Aditya Arjun, Yuke Zhu 외

Reinforcement Learning (RL) has demonstrated promising results in learning policies for complex tasks, but it often suffers from low sample efficiency and limited transferability. Hierarchical RL (HRL) methods aim to add…

reinforcement-learningReinforcement Learning (RL)