"I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities

• URL: http://arxiv.org/abs/2412.19102v1
• Date: Thu, 26 Dec 2024 07:43:18 GMT
• Title: "I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities
• Authors: Jiawei Yu, Xiang Geng, Yuang Li, Mengxin Ren, Wei Tang, Jiahuan Li, Zhibin Lan, Min Zhang, Hao Yang, Shujian Huang, Jinsong Su,
• Abstract summary: Spoken named entity recognition (NER) aims to identify named entities from speech. New named entities appear every day, however, annotating their Spoken NER data is costly. We propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs.
• Score: 59.22329574700317
• License:
• Abstract: Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.

Related papers

• ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models [9.886819209498514]
  ReverseNER is a method aimed at overcoming the limitation of large language models in zero-shot named entity recognition tasks. It generates an example library composed of dozens of entity-labeled sentences, generated through the reverse process of NER. We propose an entity-level self-consistency scoring mechanism to improve NER performance with LLMs.
  arXiv  Detail & Related papers  (2024-11-01T12:08:08Z)
• Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation [67.89838237013078]
  Named entity recognition (NER) models often struggle with noisy inputs. We propose a more realistic setting in which only noisy text and its NER labels are available. We employ a multi-view training framework that improves robust NER without retrieving text during inference.
  arXiv  Detail & Related papers  (2024-07-26T07:30:41Z)
• Named Entity Recognition for Address Extraction in Speech-to-Text Transcriptions Using Synthetic Data [0.0]
  This paper introduces an approach for building a Named Entity Recognition (NER) model built upon a Bidirectional Representations from Transformers (BERT) architecture. This NER model extracts address parts from data acquired from speech-to-text transcriptions. The performance of our NER model, trained solely on synthetic data, is evaluated using small real test dataset.
  arXiv  Detail & Related papers  (2024-02-08T10:29:11Z)
• ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER [47.32935969127478]
  We present ACLM Attention-map aware keyword selection for Conditional Language Model fine-tuning. ACLM alleviates the context-entity mismatch issue, a problem existing NER data augmentation techniques suffer from. We demonstrate the effectiveness of ACLM both qualitatively and quantitatively on monolingual, cross-lingual, and multilingual complex NER.
  arXiv  Detail & Related papers  (2023-06-01T17:33:04Z)
• Disambiguation of Company names via Deep Recurrent Networks [101.90357454833845]
  We propose a Siamese LSTM Network approach to extract -- via supervised learning -- an embedding of company name strings. We analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline.
  arXiv  Detail & Related papers  (2023-03-07T15:07:57Z)
• Prompt-based Text Entailment for Low-Resource Named Entity Recognition [21.017890579840145]
  We propose Prompt-based Text Entailment (PTE) for low-resource named entity recognition. The proposed method achieves competitive performance on the CoNLL03 dataset.
  arXiv  Detail & Related papers  (2022-11-06T06:13:38Z)
• AsNER -- Annotated Dataset and Baseline for Assamese Named Entity recognition [7.252817150901275]
  The proposed NER dataset is likely to be a significant resource for deep neural based Assamese language processing. We benchmark the dataset by training NER models and evaluating using state-of-the-art architectures for supervised named entity recognition. The highest F1-score among all baselines achieves an accuracy of 80.69% when using MuRIL as a word embedding method.
  arXiv  Detail & Related papers  (2022-07-07T16:45:55Z)
• AISHELL-NER: Named Entity Recognition from Chinese Speech [54.434118596263126]
  We introduce a new dataset AISEHLL-NER for NER from Chinese speech. The results demonstrate that the performance could be improved by combining-aware ASR and pretrained NER tagger.
  arXiv  Detail & Related papers  (2022-02-17T09:18:48Z)
• On the Use of External Data for Spoken Named Entity Recognition [40.93448412171246]
  Recent advances in self-supervised speech representations have made it feasible to consider learning models with limited labeled data. We draw on a variety of approaches, including self-training, knowledge distillation, and transfer learning, and consider their applicability to both end-to-end models and pipeline approaches.
  arXiv  Detail & Related papers  (2021-12-14T18:49:26Z)
• End-to-end Named Entity Recognition from English Speech [51.22888702264816]
  We introduce a first publicly available NER annotated dataset for English speech and present an E2E approach, which jointly optimize the ASR and NER tagger components. We also discuss how NER from speech can be used to handle out of vocabulary (OOV) words in an ASR system.
  arXiv  Detail & Related papers  (2020-05-22T13:39:14Z)

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.