SGG: Learning to Select, Guide, and Generate for Keyphrase Generation
- URL: http://arxiv.org/abs/2105.02544v1
- Date: Thu, 6 May 2021 09:43:33 GMT
- Title: SGG: Learning to Select, Guide, and Generate for Keyphrase Generation
- Authors: Jing Zhao, Junwei Bao, Yifan Wang, Youzheng Wu, Xiaodong He, Bowen
Zhou
- Abstract summary: Keyphrases concisely summarize the high-level topics discussed in a document.
Most existing keyphrase generation approaches synchronously generate present and absent keyphrases.
We propose a Select-Guide-Generate (SGG) approach to deal with present and absent keyphrase generation separately.
- Score: 38.351526320316786
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Keyphrases, that concisely summarize the high-level topics discussed in a
document, can be categorized into present keyphrase which explicitly appears in
the source text, and absent keyphrase which does not match any contiguous
subsequence but is highly semantically related to the source. Most existing
keyphrase generation approaches synchronously generate present and absent
keyphrases without explicitly distinguishing these two categories. In this
paper, a Select-Guide-Generate (SGG) approach is proposed to deal with present
and absent keyphrase generation separately with different mechanisms.
Specifically, SGG is a hierarchical neural network which consists of a
pointing-based selector at low layer concentrated on present keyphrase
generation, a selection-guided generator at high layer dedicated to absent
keyphrase generation, and a guider in the middle to transfer information from
selector to generator. Experimental results on four keyphrase generation
benchmarks demonstrate the effectiveness of our model, which significantly
outperforms the strong baselines for both present and absent keyphrases
generation. Furthermore, we extend SGG to a title generation task which
indicates its extensibility in natural language generation tasks.
Related papers
- SimCKP: Simple Contrastive Learning of Keyphrase Representations [36.88517357720033]
We propose SimCKP, a simple contrastive learning framework that consists of two stages: 1) An extractor-generator that extracts keyphrases by learning context-aware phrase-level representations in a contrastive manner while also generating keyphrases that do not appear in the document; and 2) A reranker that adapts scores for each generated phrase by likewise aligning their representations with the corresponding document.
arXiv Detail & Related papers (2023-10-12T11:11:54Z) - Retrieval-Augmented Multilingual Keyphrase Generation with
Retriever-Generator Iterative Training [66.64843711515341]
Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text.
We call attention to a new setting named multilingual keyphrase generation.
We propose a retrieval-augmented method for multilingual keyphrase generation to mitigate the data shortage problem in non-English languages.
arXiv Detail & Related papers (2022-05-21T00:45:21Z) - Towards Document-Level Paraphrase Generation with Sentence Rewriting and
Reordering [88.08581016329398]
We propose CoRPG (Coherence Relationship guided Paraphrase Generation) for document-level paraphrase generation.
We use graph GRU to encode the coherence relationship graph and get the coherence-aware representation for each sentence.
Our model can generate document paraphrase with more diversity and semantic preservation.
arXiv Detail & Related papers (2021-09-15T05:53:40Z) - Heterogeneous Graph Neural Networks for Keyphrase Generation [13.841525616800908]
We propose a novel graph-based method that can capture explicit knowledge from related references.
Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references.
To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both the source document and its references.
arXiv Detail & Related papers (2021-09-10T07:17:07Z) - Keyphrase Extraction with Dynamic Graph Convolutional Networks and
Diversified Inference [50.768682650658384]
Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document.
Recent Sequence-to-Sequence (Seq2Seq) based generative framework is widely used in KE task, and it has obtained competitive performance on various benchmarks.
In this paper, we propose to adopt the Dynamic Graph Convolutional Networks (DGCN) to solve the above two problems simultaneously.
arXiv Detail & Related papers (2020-10-24T08:11:23Z) - Persian Keyphrase Generation Using Sequence-to-Sequence Models [1.192436948211501]
Keyphrases are a summary of an input text and provide the main subjects discussed in the text.
In this paper, we try to tackle the problem of keyphrase generation and extraction from news articles using deep sequence-to-sequence models.
arXiv Detail & Related papers (2020-09-25T14:40:14Z) - Select, Extract and Generate: Neural Keyphrase Generation with
Layer-wise Coverage Attention [75.44523978180317]
We propose emphSEG-Net, a neural keyphrase generation model that is composed of two major components.
The experimental results on seven keyphrase generation benchmarks from scientific and web documents demonstrate that SEG-Net outperforms the state-of-the-art neural generative methods by a large margin.
arXiv Detail & Related papers (2020-08-04T18:00:07Z) - Exclusive Hierarchical Decoding for Deep Keyphrase Generation [63.357895318562214]
Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases.
Previous work in this setting employs a sequential decoding process to generate keyphrases.
We propose an exclusive hierarchical decoding framework that includes a hierarchical decoding process and either a soft or a hard exclusion mechanism.
arXiv Detail & Related papers (2020-04-18T02:58:00Z) - Keyphrase Extraction with Span-based Feature Representations [13.790461555410747]
Keyphrases are capable of providing semantic metadata characterizing documents.
Three approaches to address keyphrase extraction: (i) traditional two-step ranking method, (ii) sequence labeling and (iii) generation using neural networks.
In this paper, we propose a novelty Span Keyphrase Extraction model that extracts span-based feature representation of keyphrase directly from all the content tokens.
arXiv Detail & Related papers (2020-02-13T09:48:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.