paper-with-me

홈 › Papers

A Generative Approach to Titling and Clustering Wikipedia Sections

2020-05-22 · WS 2020 7 · Anjalie Field, Sascha Rothe, Simon Baumgartner, Cong Yu, Abe Ittycheriah

We evaluate the performance of transformer encoders with various decoders for information organization through a new task: generation of section headings for Wikipedia articles. Our analysis shows that decoders containing attention mechanisms over the encoder output achieve high-scoring results by generating extractive text. In contrast, a decoder without attention better facilitates semantic encoding and can be used to generate section embeddings. We additionally introduce a new loss function, which further encourages the decoder to generate high-quality embeddings.

📄 PDF Abstract BibTeX arXiv:2005.11216

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesClusteringDecoder

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
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…
Multi-Head Attention 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Learning Thematic Similarity Metric from Article Sections Using Triplet Networks

2018-07-01 · ACL 2018 7 · Liat Ein Dor, Yosi Mass, Alon Halfon, Elad Venezian 외

In this paper we suggest to leverage the partition of articles into sections, in order to learn thematic similarity metric between sentences. We assume that a sentence is thematically closer to sentences within its secti…

ArticlesClusteringCollaborative FilteringDocument Summarization+6

WikiOmnia: generative QA corpus on the whole Russian Wikipedia

2022-04-17 · Dina Pisarevskaya, Tatiana Shavrina

The General QA field has been developing the methodology referencing the Stanford Question answering dataset (SQuAD) as the significant benchmark. However, compiling factual questions is accompanied by time- and labour-c…

Question Answering

WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections

2020-12-29 · Findings (ACL) 2021 8 · Mingda Chen, Sam Wiseman, Kevin Gimpel

Datasets for data-to-text generation typically focus either on multi-domain, single-sentence generation or on single-domain, long-form generation. In this work, we cast generating Wikipedia sections as a data-to-text gen…

Data-to-Text GenerationFormSentenceText Generation

Recognizing Biographical Sections in Wikipedia

2015-09-01 · EMNLP 2015 9 · Alessio Palmero Aprosio, Sara Tonelli

Weakly Supervised Multilingual Causality Extraction from Wikipedia

2019-11-01 · IJCNLP 2019 11 · Chikara Hashimoto

We present a method for extracting causality knowledge from Wikipedia, such as Protectionism -{\textgreater} Trade war, where the cause and effect entities correspond to Wikipedia articles. Such causality knowledge is ea…

Articles