The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Dialog context language modeling with recurrent neural networks
Open accessAbstract
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog. Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms conventional single turn based RNN language model by 3.3% on perplexity. The proposed models also demonstrate advantageous performance over other competitive contextual language models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A generalization beyond task-specific dialogue systems is to classify speech and feedback as dialogue acts.
“A generalization of this, that moves beyond task-specific dialogue systems, is to classify speech and feedback as dialogue acts instead (Liu and Lane, 2017; Ortega and Vu, 2017).”
From Modeling Feedback in Interaction With Conversational Agents—A Review (2022) · cites this paper as Liu and Lane, 2017
Section 4.1 says the Switchboard corpus has turn- and utterance-level dialogue-act tags, and Table 3 includes feedback-like tags such as Acknowledge and Agree/Accept. But the paper develops dialogue-context language models, not a method for classifying speech and feedback as dialogue acts, and it does not describe that classification as a generalization beyond task-specific systems. (LLM, conf=0.82)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Flagged first, then by citations
Research works printed but not linked: 16
- david, 2003, Latent dirichlet allocation, Journal of Machine Learning Research, 3, 993
- wang, 2015, Larger-context language modelling, arXiv preprint arXiv 1511 05271
- ji, 0, Document context language models, arXiv preprint arXiv 1511 06434 2015
- 10.1037/10096-006 · DOI · Paper page
- 10.18653/v1/D15-1106 · DOI
- hung, 2016, Inter-document contextual language model, Proceedings of NAACL-HLT, 762
- 10.3115/981863.981904 · DOI
- mikolov, 0, Distributed representations of words and phrases and their compositionality, Advances in Neural Information Processing Systems 2013
- zaremba, 0, Recurrent neural network regularization, ar Xiv preprint arXiv 1409 2329 2014
- 10.3115/v1/D14-1179 · DOI · Paper page
- peter, 1990, A statistical approach to machine translation, Computational Linguistics, 16, 79
- 10.1109/ICASSP.2011.5947611 · DOI
- mikolov, 0, Recurrent neural network based language model, INTERSPEECH 2010, 2, 3
- sundermeyer, 2012, Lstm neural networks for language modeling., InterSpeech, 194
- 10.1109/ICASSP.2016.7472621 · DOI · Paper page
- 10.1109/SLT.2012.6424228 · DOI
Cited by
Sorted by citations
Modeling Feedback in Interaction With Conversational Agents—A Review
Axelsson, A., Buschmeier, H., & Skantze, G. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2022.744574 · Cited by 45
Metadata
- Authors
- Liu, B., & Lane, I.
- Affiliations
- Carnegie Mellon University (US)
- ORCID
- Liu, Bing
- Venue
- 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2017-03
- Pages
- 5715-5719
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2573537087
- Cited by
- 26
- References
- 2
- Citations by year
- 2025: 2 · 2024: 1 · 2023: 2 · 2022: 4 · 2021: 3 · 2020: 2 · 2019: 5 · 2018: 4 · 2017: 3
- FWCI
- 1.71
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- contextual language models, recurrent neural networks, perplexity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
