---
title: "Modeling Long-Range Context for Concurrent Dialogue Acts Recognition — paper by Yu et al. (2019)"
description: "The paper addresses Concurrent Dialogue Acts (CDA) recognition, a setting in which one forum post or dialogue turn can… 4.7 points. Cited by 3 papers here."
authors: ["Yue Yu", "Siyao Peng", "Grace Hui Yang"]
year: 2019
venue: "arXiv:1909.00521"
source: "https://arxiv.org/abs/1909.00521"
doi: "10.1145/3357384.3358145"
arxiv: "1909.00521"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yu-2019-modeling-long-range-context-concurrent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2019-modeling-long-range-context-concurrent/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/6/) / Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

# Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

**Authors:** [Yue Yu](https://md.research.elamur.ai/free/en/authors/yue-yu/), [Siyao Peng](https://md.research.elamur.ai/free/en/authors/siyao-peng/) and Grace Hui Yang · **Year:** 2019 · **Venue:** [arXiv:1909.00521](https://md.research.elamur.ai/free/en/venues/acm-international-conference-on-information-and-knowledge-management-cikm/) ([CIKM 2019](https://md.research.elamur.ai/free/en/venues/acm-international-conference-on-information-and-knowledge-management-cikm/2019/)) · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://doi.org/10.1145/3357384.3358145) · [PDF](https://arxiv.org/pdf/1909.00521) · [DOI 10.1145/3357384.3358145](https://doi.org/10.1145/3357384.3358145) · [arXiv 1909.00521](https://arxiv.org/abs/1909.00521) · [OpenAlex](https://openalex.org/W2971770322)

**Citations:** 11 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/yu-2019-modeling-long-range-context-concurrent/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper addresses Concurrent Dialogue Acts (CDA) recognition, a setting in which one forum post or dialogue turn can carry several dialogue acts at once, such as thanking someone and confirming that a fix worked. Earlier work fell short in one of two ways. Some models handled whole dialogue sequences but assumed a single act per utterance, typically through a CRF output layer. Others allowed multiple labels but considered only a small fixed window of neighbouring turns.

The authors adapt a Convolutional Recurrent Neural Network (CRNN) to cover both needs:
- a CNN encodes each utterance;
- a bidirectional LSTM/GRU runs across the whole dialogue to collect distant context;
- independent sigmoid outputs with binary cross-entropy produce the multi-label decisions.

Two refinements are added. A highway link carries the utterance's own CNN features straight to the output layer, and dynamic k-max pooling handles long posts.

On MSDialog-Intent, a tech-support forum corpus, the full model beats the previous best system (CNN-CR) by about 4.7 points of accuracy and 3.1 points of micro-F1. This shows that modelling long-range context matters when utterances are long and serve several functions.

## Key points
- MSDialog-Intent has 10,020 utterances labelled with a subset of 12 dialogue acts (e.g., GG, PA, FD, OQ, PF, IR). Utterances average about 72 tokens and 1.83 acts each, and roughly 60% have more than one label.
- The authors kept every label combination. Qu et al. had dropped some labels and collapsed rare combinations into the 32 most frequent, so the authors re-ran CNN-CR on the unsimplified data for a fair comparison.
- The best model, CRNN (v3) with LSTM, reached 0.6822 accuracy and 0.7337 micro-F1, against 0.6354 and 0.7029 for CNN-CR. The GRU variant of v3 scored the highest precision (0.7358).
- Setup:
  - GloVe embeddings (Wikipedia + Gigaword 5);
  - 8:1:1 train/validation/test split;
  - 100 CNN filters, 2 recurrent layers of 900 units, k=2;
  - Adam with learning rate 0.001.
- Evaluation and ablation:
  - The main metrics are Hamming-style label accuracy and micro-F1.
  - Paired t-tests are run only on accuracy, because it is the only metric computed per utterance.
  - Each addition (highway connection, then dynamic k-max pooling) improved results step by step.

## Interesting ideas
- Treat each dialogue act as its own yes/no decision, using sigmoid outputs and binary cross-entropy instead of one softmax or CRF choice, so a single turn can be both a greeting and an answer.
- A highway path sends an utterance's local features past the context layer, so surrounding turns add information without washing out what the utterance itself says.
- Dynamic k-max pooling splits a long text into p segments and keeps the strongest signal from each, rather than a single global maximum, so a long post can express several functions in different places.
- Context is not limited to a fixed window, because a reply in a thread may target any earlier turn, as when a potential answer addresses the very first question.
- The evaluation refuses to simplify the label space and breaks accuracy down by how many gold labels an item has, which shows whether a model really handles the multi-label cases.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): the prag speech-act layer could assign a set of acts per utterance, each backed by its own explainable evidence, instead of forcing one winning act.
- **I2** (frames): when discourse context refines a speech-act or implicature reading, keep the sentence-internal cues as a separate, inspectable input that the final decision can always fall back on.
- **I3** (answer): when reading long fables or test passages, collect evidence segment by segment so each answer can point to where in the text its support came from.
- **I4** (world): the world-of-text model should keep the whole dialogue or story history available for linking states and events, instead of looking back only a few sentences.
- **I5** (learn): evaluation of acts or frames could be stratified by item complexity (one versus several gold labels), with baselines re-run on the same unsimplified data so gains are not artefacts of an easier test.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Georgetown University](https://md.research.elamur.ai/free/en/universities/georgetown-university/) — University, Washington, United States · 69 works · 4,417 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (2): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 401 works · [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 160 works

## Cite

Cite as: Yue Yu, Siyao Peng and Grace Hui Yang. 2019. Modeling Long-Range Context for Concurrent Dialogue Acts Recognition. arXiv:1909.00521.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{yu2019modeling,
  title = {{Modeling Long-Range Context for Concurrent Dialogue Acts Recognition}},
  author = {Yue Yu, Siyao Peng and Grace Hui Yang},
  year = {2019},
  doi = {10.1145/3357384.3358145},
  eprint = {1909.00521},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3357384.3358145}
}
```

- [← previous An Annotated Corpus of Reference Resolution for Interpreting Common Grounding](https://md.research.elamur.ai/free/en/papers/udagawa-2019-annotated-corpus-reference-resolution-interpreting/)
- [next → Wait Signals Predict Sarcasm in Online Debates](https://md.research.elamur.ai/free/en/papers/arcey-2019-wait-signals-predict-sarcasm-online/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/6/)

*Updated 24 October 2026*