Unsupervised Deep Keyphrase Generation
- URL: http://arxiv.org/abs/2104.08729v1
- Date: Sun, 18 Apr 2021 05:53:19 GMT
- Title: Unsupervised Deep Keyphrase Generation
- Authors: Xianjie Shen, Yinghan Wang, Rui Meng, Jingbo Shang
- Abstract summary: Keyphrase generation aims to summarize long documents with a collection of salient phrases.
Deep neural models have demonstrated a remarkable success in this task, capable of predicting keyphrases that are even absent from a document.
We present a novel method for keyphrase generation, AutoKeyGen, without the supervision of any human annotation.
- Score: 14.544869226959612
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Keyphrase generation aims to summarize long documents with a collection of
salient phrases. Deep neural models have demonstrated a remarkable success in
this task, capable of predicting keyphrases that are even absent from a
document. However, such abstractiveness is acquired at the expense of a
substantial amount of annotated data. In this paper, we present a novel method
for keyphrase generation, AutoKeyGen, without the supervision of any human
annotation. Motivated by the observation that an absent keyphrase in one
document can appear in other places, in whole or in part, we first construct a
phrase bank by pooling all phrases in a corpus. With this phrase bank, we then
draw candidate absent keyphrases for each document through a partial matching
process. To rank both types of candidates, we combine their lexical- and
semantic-level similarities to the input document. Moreover, we utilize these
top-ranked candidates as to train a deep generative model for more absent
keyphrases. Extensive experiments demonstrate that AutoKeyGen outperforms all
unsupervised baselines and can even beat strong supervised methods in certain
cases.
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) - Neural Keyphrase Generation: Analysis and Evaluation [47.004575377472285]
We study various tendencies exhibited by three strong models: T5 (based on a pre-trained transformer), CatSeq-Transformer (a non-pretrained Transformer), and ExHiRD (based on a recurrent neural network)
We propose a novel metric framework, SoftKeyScore, to evaluate the similarity between two sets of keyphrases.
arXiv Detail & Related papers (2023-04-27T00:10:21Z) - Applying Transformer-based Text Summarization for Keyphrase Generation [2.28438857884398]
Keyphrases are crucial for searching and systematizing scholarly documents.
In this paper, we experiment with popular transformer-based models for abstractive text summarization.
We show that summarization models are quite effective in generating keyphrases in the terms of the full-match F1-score and BERT.Score.
We also investigate several ordering strategies to target keyphrases.
arXiv Detail & Related papers (2022-09-08T13:01:52Z) - KPDrop: An Approach to Improving Absent Keyphrase Generation [26.563045686728135]
Keyphrase generation is the task of generating phrases (keyphrases) that summarize the main topics of a given document.
We propose an approach, called keyphrase dropout (or KPDrop) to improve absent keyphrase generation.
arXiv Detail & Related papers (2021-12-02T18:25:56Z) - Deep Keyphrase Completion [59.0413813332449]
Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval.
We propose textitkeyphrase completion (KPC) to generate more keyphrases for document (e.g. scientific publication) taking advantage of document content along with a very limited number of known keyphrases.
We name it textitdeep keyphrase completion (DKPC) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework
arXiv Detail & Related papers (2021-10-29T07:15:35Z) - 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) - UCPhrase: Unsupervised Context-aware Quality Phrase Tagging [63.86606855524567]
UCPhrase is a novel unsupervised context-aware quality phrase tagger.
We induce high-quality phrase spans as silver labels from consistently co-occurring word sequences.
We show that our design is superior to state-of-the-art pre-trained, unsupervised, and distantly supervised methods.
arXiv Detail & Related papers (2021-05-28T19:44:24Z) - 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.