The importance of fillers for text representations of speech transcripts
Not on the map. Why?
Abstract (arXiv)
While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks - predicting a speaker's stance and expressed confidence.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Sep 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 4; 2023: 4; 2024: 0; 2025: 1.
15 papers.
Sort:
- 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
- 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
- 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
- 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
- 2021Improving Multimodal fusion via Mutual Dependency Maximisationcited by 15
- 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
- 2022Learning Disentangled Textual Representations via Statistical Measures of Similaritycited by 14
- 2023Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarkscited by 14
- 2021Beam Search with Bidirectional Strategies for Neural Response Generationcited by 12
- 2021Code-switched inspired losses for generic spoken dialog representationscited by 10
- 2023Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectivescited by 5
- 2022Beyond Mahalanobis-Based Scores for Textual OOD Detectioncited by 3
- 2025LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams24 Apr 2025
- 2023A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification21 Oct 2023
- 2023Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks17 May 2023
- 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detection20 Feb 2023
- 2023Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives25 Jan 2023
- 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data18 Dec 2022
- 2022Beyond Mahalanobis-Based Scores for Textual OOD Detection24 Nov 2022
- 2022Learning Disentangled Textual Representations via Statistical Measures of Similarity7 May 2022
- 2022What are the best systems? New perspectives on NLP Benchmarking8 Feb 2022
- 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation2 Dec 2021
- 2021Beam Search with Bidirectional Strategies for Neural Response Generation7 Oct 2021
- 2021Improving Multimodal fusion via Mutual Dependency Maximisation31 Aug 2021
- 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
- 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
- 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
- 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
- 2021Improving Multimodal fusion via Mutual Dependency Maximisationcited by 15
- 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
- 2022Learning Disentangled Textual Representations via Statistical Measures of Similaritycited by 14
- 2023Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarkscited by 14
- 2021Beam Search with Bidirectional Strategies for Neural Response Generationcited by 12
- 2021Code-switched inspired losses for generic spoken dialog representationscited by 10
- 2023Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectivescited by 5
- 2022Beyond Mahalanobis-Based Scores for Textual OOD Detectioncited by 3
12 most cited of 15 All 15 (JSON)
- 2025LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams24 Apr 2025
- 2023A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification21 Oct 2023
- 2023Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks17 May 2023
- 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detection20 Feb 2023
- 2023Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives25 Jan 2023
- 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data18 Dec 2022
- 2022Beyond Mahalanobis-Based Scores for Textual OOD Detection24 Nov 2022
- 2022Learning Disentangled Textual Representations via Statistical Measures of Similarity7 May 2022
- 2022What are the best systems? New perspectives on NLP Benchmarking8 Feb 2022
- 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation2 Dec 2021
- 2021Beam Search with Bidirectional Strategies for Neural Response Generation7 Oct 2021
- 2021Improving Multimodal fusion via Mutual Dependency Maximisation31 Aug 2021
12 newest of 15 All 15 (JSON)