Learning Rich Representation of Keyphrases from Text

• URL: http://arxiv.org/abs/2112.08547v1
• Date: Thu, 16 Dec 2021 01:09:51 GMT
• Title: Learning Rich Representation of Keyphrases from Text
• Authors: Mayank Kulkarni, Debanjan Mahata, Ravneet Arora, Rajarshi Bhowmik
• Abstract summary: We show how to learn task-specific language models aimed towards learning rich representation of keyphrases from text documents. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR) In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases related to the input text in the CatSeq format.
• Score: 12.698835743464313
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we explore how to learn task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 9.26 points in F1) over SOTA, when LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases related to the input text in the CatSeq format, instead of the denoised original input. This also led to gains in performance (upto 4.33 points in F1@M) over SOTA for keyphrase generation. Additionally, we also fine-tune the pre-trained language models on named entity recognition (NER), question answering (QA), relation extraction (RE), abstractive summarization and achieve comparable performance with that of the SOTA, showing that learning rich representation of keyphrases is indeed beneficial for many other fundamental NLP tasks.

Related papers

• A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus [71.77214818319054]
  Natural language inference is a proxy for natural language understanding. There is no publicly available NLI corpus for the Romanian language. We introduce the first Romanian NLI corpus (RoNLI) comprising 58K training sentence pairs.
  arXiv  Detail & Related papers  (2024-05-20T08:41:15Z)
• 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)
• Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition [20.926163659469587]
  We propose a new memory augmented lookup dictionary based Transformer architecture for LM. The newly introduced lookup dictionary incorporates rich contextual information in training set, which is vital to correctly predict long-tail tokens. Our proposed method is proved to outperform the baseline Transformer LM by a great margin on both word/character error rate and tail tokens error rate.
  arXiv  Detail & Related papers  (2022-12-30T22:26:57Z)
• Language Model Pre-Training with Sparse Latent Typing [66.75786739499604]
  We propose a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge.
  arXiv  Detail & Related papers  (2022-10-23T00:37:08Z)
• PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction [0.6767885381740952]
  We present PatternRank, which pretrained language models and part-of-speech for unsupervised keyphrase extraction from single documents. Our experiments show PatternRank achieves higher precision, recall and F1-scores than previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-10-11T08:23:54Z)
• 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)
• Representation Learning for Resource-Constrained Keyphrase Generation [78.02577815973764]
  We introduce salient span recovery and salient span prediction as guided denoising language modeling objectives. We show the effectiveness of the proposed approach for low-resource and zero-shot keyphrase generation.
  arXiv  Detail & Related papers  (2022-03-15T17:48:04Z)
• Improving Joint Layer RNN based Keyphrase Extraction by Using Syntactical Features [0.6724914680904501]
  We propose to modify the input layer of JRNN to extract more than one sequence of keywords. Our method achieved.9597 in accuracy and.7691 in F1.
  arXiv  Detail & Related papers  (2020-09-15T14:20:04Z)
• Pre-training via Paraphrasing [96.79972492585112]
  We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual paraphrasing objective. We show it is possible to jointly learn to do retrieval and reconstruction, given only a random initialization. For example, with no additional task-specific training we achieve BLEU scores of up to 35.8 for document translation.
  arXiv  Detail & Related papers  (2020-06-26T14:43:43Z)
• BURT: BERT-inspired Universal Representation from Twin Structure [89.82415322763475]
  BURT (BERT inspired Universal Representation from Twin Structure) is capable of generating universal, fixed-size representations for input sequences of any granularity. Our proposed BURT adopts the Siamese network, learning sentence-level representations from natural language inference dataset and word/phrase-level representations from paraphrasing dataset. We evaluate BURT across different granularities of text similarity tasks, including STS tasks, SemEval2013 Task 5(a) and some commonly used word similarity tasks.
  arXiv  Detail & Related papers  (2020-04-29T04:01:52Z)
• Keyphrase Prediction With Pre-trained Language Model [16.06425973336514]
  We propose to divide the keyphrase prediction into two subtasks, i.e., present keyphrase extraction (PKE) and absent keyphrase generation (AKG) For PKE, we tackle this task as a sequence labeling problem with the pre-trained language model BERT. For AKG, we introduce a Transformer-based architecture, which fully integrates the present keyphrase knowledge learned from PKE by the fine-tuned BERT.
  arXiv  Detail & Related papers  (2020-04-22T09:35:02Z)

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.