Keyphrase extraction from documents is useful to a variety of applications such as information retrieval and document summarization. This paper presents an end-to-end method called DivGraphPointer for extracting a set of diversified keyphrases from a document. DivGraphPointer combines the advantages of traditional graph-based ranking methods and recent neural network-based approaches. Specifically, given a document, a word graph is constructed from the document based on word proximity and is encoded with graph convolutional networks, which effectively capture document-level word salience by modeling long-range dependency between words in the document and aggregating multiple appearances of identical words into one node. Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process. Experimental results on five benchmark data sets show that our proposed method significantly outperforms the existing state-of-the-art approaches.

DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases

Generating absent keyphrases, which do not appear in the input document, is challenging in the keyphrase prediction task. Most previous works treat the problem as an autoregressive sequence-to-sequence generation task, which demonstrates promising results for generating grammatically correct and fluent absent keyphrases. However, such an end-to-end process with a complete data-driven manner is unconstrained, which is prone to generate keyphrases inconsistent with the input document. In addition, the existing autoregressive decoding method makes the generation of keyphrases must be done from left to right, leading to slow speed during inference. In this paper, we propose a constrained absent keyphrase generation method in a prompt-based learning fashion. Specifically, the prompt will be created firstly based on the keywords, which are defined as the overlapping words between absent keyphrase and document. Then, a mask-predict decoder is used to complete the absent keyphrase on the constraint of prompt. Experiments on keyphrase generation benchmarks have demonstrated the effectiveness of our approach. In addition, we evaluate the performance of constrained absent keyphrases generation from an information retrieval perspective. The result shows that our approach can generate more consistent keyphrases, which can improve document retrieval performance. What’s more, with a non-autoregressive decoding manner, our model can speed up the absent keyphrase generation by 8.67× compared with the autoregressive method.

/pdf/fast-and-constrained-absent-keyphrase-generation-by-prompt-1iq0ck0r.pdf

Fast and Constrained Absent Keyphrase Generation by Prompt-Based Learning

Keyphrase extraction is a fundamental task in natural language processing that aims to extract a set of phrases with important information from a source document. Identifying important keyphrases is the central component of keyphrase extraction, and its main challenge is learning to represent information comprehensively and discriminate importance accurately. In this paper, to address the above issues, we design a new hyperbolic matching model (HyperMatch) to explore keyphrase extraction in hyperbolic space. Concretely, to represent information comprehensively, HyperMatch first takes advantage of the hidden representations in the middle layers of RoBERTa and integrates them as the word embeddings via an adaptive mixing layer to capture the hierarchical syntactic and semantic structures. Then, considering the latent structure information hidden in natural languages, HyperMatch embeds candidate phrases and documents in the same hyperbolic space via a hyperbolic phrase encoder and a hyperbolic document encoder. To discriminate importance accurately, HyperMatch estimates the importance of each candidate phrase by explicitly modeling the phrase-document relevance via the Poincaré distance and optimizes the whole model by minimizing the hyperbolic margin-based triplet loss. Extensive experiments are conducted on six benchmark datasets and demonstrate that HyperMatch outperforms the recent state-of-the-art baselines.

Hyperbolic Relevance Matching for Neural Keyphrase Extraction

In this paper we provide modification of approaches for extraction of keyphrases from single textual document (without external information) based on the hierarchical concepts created upon the text of particular document. For the creation of hierarchical concepts method from area of Formal Concept Analysis (FCA) is used, which organizes objects into concept lattice (structure of hierarchically organized clusters known as formal concepts) based on the similarity of their attributes. In our case FCA is applied as follows. Input document is preprocessed, extracted objects are sentences or paragraphs and attributes are frequencies of terms in particular objects. For this input data conceptual model is created using FCA-based algorithm known as generalized one-sided concept lattice. Hierarchical concepts from this model are used for extraction of keyphrases for document. Our approach is experimentally tested on selected manually annotated documents and compared to standard keyphrase extraction methods, which beneficially improved their results thanks to usage of hierarchical concepts from concept-based analysis.

http://ieeexplore.ieee.org/iel7/7419133/7422973/07422988.pdf

Extraction of keyphrases from single document based on hierarchical concepts

This paper proposes a keyword extraction process, based on the PageRank algorithm, to reduce noise of input data for measuring semantic similarity. This paper will introduce several features related to implementation and discuss their effects. It will also discuss experimental results which showed significantly improved document retrieval performance with this extraction process in place.

Julia Otmakhova

Papers

Applying Graph-based Keyword Extraction to Document Retrieval