# Neural Constituency Parsing of Speech Transcripts

arXiv: https://arxiv.org/abs/1904.08535 · HTML: https://mlsanity.com/paper/1904.08535/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment](https://mlsanity.com/paper/2305.12260/) (2023)
- [LARD: Large-scale Artificial Disfluency Generation](https://mlsanity.com/paper/2201.05041/) (2022)
- [Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks](https://mlsanity.com/paper/2402.03494/) (2024)
- [Assessing the Use of Prosody in Constituency Parsing of Imperfect Transcripts](https://mlsanity.com/paper/2106.07794/) (2021)
- [Audio-Visual Neural Syntax Acquisition](https://mlsanity.com/paper/2310.07654/) (2023)
- [Z-Scores: A Metric for Linguistically Assessing Disfluency Removal](https://mlsanity.com/paper/2509.20319/) (2025)
- [Improved POS tagging for spontaneous, clinical speech using data augmentation](https://mlsanity.com/paper/2307.05796/) (2023)
- [End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining](https://mlsanity.com/paper/2309.04516/) (2023)
- [Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech](https://mlsanity.com/paper/2406.12621/) (2024)
- [Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models](https://mlsanity.com/paper/2504.11431/) (2025)

## Abstract (arXiv)

This paper studies the performance of a neural self-attentive parser on transcribed speech. Speech presents parsing challenges that do not appear in written text, such as the lack of punctuation and the presence of speech disfluencies (including filled pauses, repetitions, corrections, etc.). Disfluencies are especially problematic for conventional syntactic parsers, which typically fail to find any EDITED disfluency nodes at all. This motivated the development of special disfluency detection systems, and special mechanisms added to parsers specifically to handle disfluencies. However, we show here that neural parsers can find EDITED disfluency nodes, and the best neural parsers find them with an accuracy surpassing that of specialized disfluency detection systems, thus making these specialized mechanisms unnecessary. This paper also investigates a modified loss function that puts more weight on EDITED nodes. It also describes tree-transformations that simplify the disfluency detection task by providing alternative encodings of disfluencies and syntactic information.