CoChat

Learning Language Games through Interaction

Open access
Wang, Sida I., Liang, Percy, Manning, Christopher D. · 2016 · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Abstract

We introduce a new language learning setting relevant to building adaptive natural language interfaces.It is inspired by Wittgenstein's language games: a human wishes to accomplish some task (e.g., achieving a certain configuration of blocks), but can only communicate with a computer, who performs the actual actions (e.g., removing all red blocks).The computer initially knows nothing about language and therefore must learn it from scratch through interaction, while the human adapts to the computer's capabilities.We created a game called SHRDLURN in a blocks world and collected interactions from 100 people playing it.First, we analyze the humans' strategies, showing that using compositionality and avoiding synonyms correlates positively with task performance.Second, we compare computer strategies, showing that modeling pragmatics on a semantic parsing model accelerates learning for more strategic players.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/p16-1224

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The SHRDLURN game: the objective is to transform the start state into the goal state. The human types in an utterance, and the computer (which does not know the goal state) tries to interpret the utterance and perform the corresponding action. The computer initially knows nothing about the language, but through the human's feedback, learns the human's language while making progress towards the game goal.
Figure 1 The SHRDLURN game: the objective is to transform the start state into the goal state. The human types in an utterance, and the computer (which does not know the goal state) tries to interpret the utterance and perform the corresponding action. The computer initially knows nothing about the language, but through the human's feedback, learns the human's language while making progress towards the game goal.CC-BY · From the PDF
Figure 2 Pragmatics improve online accuracy. In these plots, each marker is a player. red o: players who ranked 1-20 in terms of minimizing number of scrolls, green x: players 20-50; blue +: lower than 50 (includes spam players). Marker sizes correspond to player rank, where better players are depicted with larger markers. 2a : online accuracies with and without pragmatics on the full model; 2b : same for the half model.
Figure 2 Pragmatics improve online accuracy. In these plots, each marker is a player. red o: players who ranked 1-20 in terms of minimizing number of scrolls, green x: players 20-50; blue +: lower than 50 (includes spam players). Marker sizes correspond to player rank, where better players are depicted with larger markers. 2a : online accuracies with and without pragmatics on the full model; 2b : same for the half model.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 29 references

Research works printed but not linked: 6

  1. J. Berant, A. Chou, R. Frostig, and P. Liang. 2013. Semantic parsing on Freebase from question- answer pairs. In Empirical Methods in Natural Language Processing (EMNLP).
  2. N. Cesa-Bianchi and G. Lugosi. 2006. Predic- tion, learning, and games. Cambridge Univer- sity Press.
  3. J. Duchi, E. Hazan, and Y. Singer. 2010. Adap- tive subgradient methods for online learning and stochastic optimization. In Conference on Learning Theory (COLT).
  4. D. Golland, P. Liang, and D. Klein. 2010. A game- theoretic approach to generating spatial descrip- tions. In Empirical Methods in Natural Lan- guage Processing (EMNLP).
  5. N. Goodman and D. Lassiter. 2015. Probabilistic Semantics and Pragmatics: Uncertainty in Lan- guage and Thought. The Handbook of Contem- porary Semantic Theory, 2nd Edition Wiley- Blackwell.
  6. T. Kwiatkowski, L. Zettlemoyer, S. Goldwater, and M. Steedman. 2010. Inducing probabilistic CCG grammars from logical form with higher- order unification. In Empirical Methods in Natural Language Processing (EMNLP). pages 1223-1233.

Cited by

See all 159

Metadata

Authors
Wang, S. I., Liang, P., & Manning, C. D.
Affiliations
Stanford University (US)
Venue
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Published
2016
Pages
2368-2378
ISSN
0736-587X (ISSN-L)
OpenAlex
W2410540304
Cited by
132
References
27
Citations by year
2026: 2 · 2024: 2 · 2023: 5 · 2022: 16 · 2021: 20 · 2020: 23 · 2019: 21 · 2018: 23 · 2017: 18 · 2016: 2
FWCI
11.50
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Defense Advanced Research Projects Agency
  • Natural Sciences and Engineering Research Council of Canada
  • Army Research Office (W911NF-15-1-, W911NF)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
Keywords
language games, Wittgenstein, natural language interfaces, blocks world, human-computer interaction, compositionality, pragmatics, semantic parsing, task performance, human strategies

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Learning Language Games through Interaction. https://app.cochat.ai/papers/10.18653/v1/p16-1224
The paper
Wang, S. I., Liang, P., & Manning, C. D. (2016). Learning Language Games through Interaction. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/p16-1224

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.