paper-with-me

홈 › Papers

Stage-wise Fine-tuning for Graph-to-Text Generation

2021-05-17 · ACL 2021 5 · Qingyun Wang, Semih Yavuz, Victoria Lin, Heng Ji, Nazneen Rajani

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.

📄 PDF Abstract BibTeX arXiv:2105.08021

Code (1)

EagleW/Stage-wise-Fine-tuning 공식 구현 pytorch

Tasks

Data-to-Text GenerationKB-to-Language GenerationLanguage ModelingLanguage ModellingPositionText Generation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
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 &…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…
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…
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 $x$…

Similar Papers 제목 키워드 기반

GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum

2026-03-30 · Shuwen Xu, Yao Xu, Jiaxiang Liu, Chenhao Yuan 외 arxiv

Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reasoning generalization. Specifically, existi…

Graph Question AnsweringReinforcement LearningKnowledge Graphs

RankPO: Preference Optimization for Job-Talent Matching

2025-03-13 · Yafei Zhang, Murray Wang, Yu Wang, Xiaohui Wang

Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and …

Contrastive Learning

Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankers

2025-03-28 · Francesca Pezzuti, Sean MacAvaney, Nicola Tonellotto

State-of-the-art cross-encoders can be fine-tuned to be highly effective in passage re-ranking. The typical fine-tuning process of cross-encoders as re-rankers requires large amounts of manually labelled data, a contrast…

Contrastive LearningLanguage ModelingLanguage ModellingLarge Language Model+2

BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations

2019-11-01 · WS 2019 11 · Chunhua Liu, Dong Yu

This paper describes our system for COIN Shared Task 1: Commonsense Inference in Everyday Narrations. To inject more external knowledge to better reason over the narrative passage, question and answer, the system adopts …

Machine Reading ComprehensionReading Comprehension

Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network

2020-04-20 · Guanming Xiong

In this paper, we present a two stage model for multi-hop question answering. The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of…

Graph Neural NetworkLanguage ModelingLanguage ModellingMulti-hop Question Answering+1