@manuscript{ivanova_elements_2024,
        title = {Elements of {World} {Knowledge} ({EWOK}): {A} cognition-inspired framework for evaluating basic world knowledge in language models},
        url = {https://arxiv.org/abs/2405.09605},
        abstract = {The ability to build and leverage world models is essential for a general-purpose AI agent. Testing such capabilities is hard, in part because the building blocks of world models are ill-defined. We present Elements of World Knowledge (EWOK), a framework for evaluating world modeling in language models by testing their ability to use knowledge of a concept to match a target text with a plausible/implausible context. EWOK targets specific concepts from multiple knowledge domains known to be vital for world modeling in humans. Domains range from social interactions (help/hinder) to spatial relations (left/right). Both, contexts and targets are minimal pairs. Objects, agents, and locations in the items can be flexibly filled in enabling easy generation of multiple controlled datasets. We then introduce EWOK-CORE-1.0, a dataset of 4,374 items covering 11 world knowledge domains. We evaluate 20 openweights large language models (1.3B--70B parameters) across a battery of evaluation paradigms along with a human norming study comprising 12,480 measurements. The overall performance of all tested models is worse than human performance, with results varying drastically across domains. These data highlight simple cases where even large models fail and present rich avenues for targeted research on LLM world modeling capabilities.},
        author = {Ivanova, Anna A. and Sathe, Aalok and Lipkin, Benjamin and Kumar, Unnathi and Radkani, Setayesh and Clark, Thomas H. and Kauf, Carina and Hu, Jennifer and Pramod, R. T. and Grand, Gabriel and Paulun, Vivian and Ryskina, Maria and Akyurek, Ekin and Wilcox, Ethan and Rashid, Nafisa and Choshen, Leshem and Levy, Roger and Fedorenko, Evelina and Tenenbaum, Joshua and Andreas, Jacob},
        year = {2024},
      code = {https://github.com/ewok-core/ewok}
    }

@manuscript{zaslavsky_rate--distortion_2020,
      author = {Zaslavsky, Noga and Hu, Jennifer and Levy, Roger},
      title = {A Rate--Distortion view of human pragmatic reasoning},
      year = {2020},
      url = {https://arxiv.org/abs/2005.06641},
      abstract = {What computational principles underlie human pragmatic reasoning? A prominent approach to pragmatics is the Rational Speech Act (RSA) framework, which formulates pragmatic reasoning as probabilistic speakers and listeners recursively reasoning about each other. While RSA enjoys broad empirical support, it is not yet clear whether the dynamics of such recursive reasoning may be governed by a general optimization principle. Here, we present a novel analysis of the RSA framework that addresses this question. First, we show that RSA recursion implements an alternating maximization for optimizing a tradeoff between expected utility and communicative effort. On that basis, we study the dynamics of RSA recursion and disconfirm the conjecture that expected utility is guaranteed to improve with recursion depth. Second, we show that RSA can be grounded in Rate-Distortion theory, while maintaining a similar ability to account for human behavior and avoiding a bias of RSA toward random utterance production. This work furthers the mathematical understanding of RSA models, and suggests that general information-theoretic principles may give rise to human pragmatic reasoning.}
    }

@inproceedings{hu_auxiliary_2024,
      title={Auxiliary task demands mask the capabilities of smaller language models}, 
      author={Jennifer Hu and Michael C. Frank},
      booktitle={Proceedings of the Conference on Language Modeling},
      year={2024},
      url={https://arxiv.org/abs/2404.02418},
      code={https://github.com/jennhu/lm-task-demands}
    }

@article{hu_language_2024,
        title = {Language models align with human judgments on key grammatical constructions},
        volume = {121},
        url = {https://doi.org/10.1073/pnas.2400917121},
        doi = {10.1073/pnas.2400917121},
        number = {36},
        urldate = {2024-08-29},
        journal = {Proceedings of the National Academy of Sciences},
        author = {Hu, Jennifer and Mahowald, Kyle and Lupyan, Gary and Ivanova, Anna and Levy, Roger},
        month = sep,
        year = {2024},
        note = {Publisher: Proceedings of the National Academy of Sciences},
        pages = {e2400917121},
      code = {https://github.com/jennhu/response-to-DGL}
    }

@inproceedings{chu_creative_2024,
      title={The Task Task: Creative problem generation in humans and language models}, 
      author={Junyi Chu and Jennifer Hu and Tomer Ullman},
      year={2024},
      booktitle={Proceedings of the Cognitive Science Society}
    }

@inproceedings{hu_shades_2024,
      title={Shades of Zero: Distinguishing impossibility from inconceivability}, 
      author={Jennifer Hu and Felix Sosa and Tomer Ullman},
      year={2024},
      booktitle={Proceedings of the Cognitive Science Society}
    }

@inproceedings{hu_prompting_2023,
      author = {Hu, Jennifer and Levy, Roger},
      title = {Prompting is not a substitute for probability measurements in large language models},
      booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
      url = {https://arxiv.org/abs/2305.13264},
      year = {2023},
      abstract = {Prompting is now a dominant method for evaluating the linguistic knowledge of large language models (LLMs). While other methods directly read out models' probability distributions over strings, prompting requires models to access this internal information by processing linguistic input, thereby implicitly testing a new type of emergent ability: metalinguistic judgment. In this study, we compare metalinguistic prompting and direct probability measurements as ways of measuring models' linguistic knowledge. Broadly, we find that LLMs' metalinguistic judgments are inferior to quantities directly derived from representations. Furthermore, consistency gets worse as the prompt query diverges from direct measurements of next-word probabilities. Our findings suggest that negative results relying on metalinguistic prompts cannot be taken as conclusive evidence that an LLM lacks a particular linguistic generalization. Our results also highlight the value that is lost with the move to closed APIs where access to probability distributions is limited.},
      code = {https://github.com/jennhu/metalinguistic-prompting}
    }

@inproceedings{fried_pragmatics_2023,
        title = {Pragmatics in {Grounded} {Language} {Learning}: {Phenomena}, {Tasks}, and {Modeling} {Approaches}},
        url = {https://arxiv.org/abs/2211.08371},
        author = {Fried, Daniel and Tomlin, Nicholas and Hu, Jennifer and Patel, Roma and Nematzadeh, Aida},
      booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},
        year = {2023},
      abstract = {People rely heavily on context to enrich meaning beyond what is literally said, enabling concise but effective communication. To interact successfully and naturally with people, user-facing artificial intelligence systems will require similar skills in pragmatics: relying on various types of context -- from shared linguistic goals and conventions, to the visual and embodied world -- to use language effectively. We survey existing grounded settings and pragmatic modeling approaches and analyze how the task goals, environmental contexts, and communicative affordances in each work enrich linguistic meaning. We present recommendations for future grounded task design to naturally elicit pragmatic phenomena, and suggest directions that focus on a broader range of communicative contexts and affordances.}
    }

@article{hu_expectations_2023,
      author = {Hu, Jennifer and Levy, Roger and Degen, Judith and Schuster, Sebastian},
      title = {Expectations over unspoken alternatives predict pragmatic inferences},
      journal = {Transactions of the Association for Computational Linguistics},
      url = {https://doi.org/10.1162/tacl_a_00579},
      year = {2023},
      code = {https://github.com/jennhu/expectations-over-alternatives}
    }

@inproceedings{hu_fine-grained_2023,
        title = {A fine-grained comparison of pragmatic language understanding in humans and language models},
        url = {https://aclanthology.org/2023.acl-long.230/},
      code = {https://github.com/jennhu/lm-pragmatics},
        author = {Hu, Jennifer and Floyd, Sammy and Jouravlev, Olessia and Fedorenko, Evelina and Gibson, Edward},
        year = {2023},
      booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics},
      abstract = {Pragmatics is an essential part of communication, but it remains unclear what mechanisms underlie human pragmatic communication and whether NLP systems capture pragmatic language understanding. To investigate both these questions, we perform a fine-grained comparison of language models and humans on seven pragmatic phenomena, using zero-shot prompting on an expert-curated set of English materials. We ask whether models (1) select pragmatic interpretations of speaker utterances, (2) make similar error patterns as humans, and (3) use similar linguistic cues as humans to solve the tasks. We find that the largest models achieve high accuracy and match human error patterns: within incorrect responses, models favor the literal interpretation of an utterance over heuristic-based distractors. We also find evidence that models and humans are sensitive to similar linguistic cues. Our results suggest that even paradigmatic pragmatic phenomena may be solved without explicit representations of other agents' mental states, and that artificial models can be used to gain mechanistic insights into human pragmatic processing. }
    }

@inproceedings{zhou_ai_2023,
        title = {I Cast Detect Thoughts: {L}earning to Converse and Guide with Intents and {T}heory-of-{M}ind in {D}ungeons and {D}ragons},
        url = {https://aclanthology.org/2023.acl-long.624/},
      booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics},
        author = {Zhou, Pei and Zhu, Andrew and Hu, Jennifer and Pujara, Jay and Ren, Xiang and Callison-Burch, Chris and Choi, Yejin and Ammanabrolu, Prithviraj},
      abstract = {We propose a novel task, G4C (Goal-driven Guidance Generation in Grounded Communication), for studying goal-driven and grounded natural language interactions. Specifically, we choose Dungeons and Dragons (D&D) -- a role-playing game consisting of multiple player characters and a Dungeon Master (DM) who collaborate to achieve a set of goals that are beneficial to the players -- as a testbed for this task. Here, each of the player characters is a student, with their own personas and abilities, and the DM is the teacher, an arbitrator of the rules of the world and responsible for assisting and guiding the students towards a global goal. We propose a theory-of-mind-inspired methodology for training such a DM with reinforcement learning (RL), where a DM: (1) learns to predict how the players will react to its utterances using a dataset of D&D dialogue transcripts; and (2) uses this prediction as a reward function providing feedback on how effective these utterances are at guiding the players towards a goal. Human and automated evaluations show that a DM trained with RL to generate guidance by incorporating a theory-of-mind of the players significantly improves the players' ability to achieve goals grounded in their shared world.},
        year = {2023}
    }

@incollection{wilcox_learning_2023,
        title = {Learning syntactic structures from string input},
        booktitle = {Algebraic {Structures} in {Natural} {Language}},
        publisher = {Taylor \& Francis},
        author = {Wilcox, Ethan and Gauthier, Jon and Hu, Jennifer and Qian, Peng and Levy, Roger},
        editor = {Lappin, Shalom and Bernardy, Jean-Philippe},
        year = {2023},
        url = {https://lingbuzz.net/lingbuzz/007271}
    }

@abstract{hu_predicting_2022b,
      author = {Hu, Jennifer and Levy, Roger and Schuster, Sebastian},
      title = {Predicting scalar diversity with context-driven expectations},
      booktitle = {Proceedings of the Experimental Pragmatics Conference (XPRAG)},
      year = {2022},
    }

@inproceedings{zhou_teasing_2022,
      author     = {Zhou, Irene and Hu, Jennifer and Levy, Roger and Zaslavsky, Noga},
      title      = {Teasing apart models of pragmatics using optimal reference game design},
      booktitle  = CogSci,
      url = {https://escholarship.org/uc/item/7mr9809j},
      year       = {2022},
      abstract   = {How do humans produce and comprehend language in pragmatic ways? A variety of models of pragmatic inferences have been proposed, and these models are typically evaluated on their ability to account for human inferences in reference game experiments. However, these experiments are not tailored to target theoretical differences between models or clearly tease apart model predictions. We propose an optimal experiment design approach to systematically construct reference games that can optimally differentiate between models of human pragmatic reasoning. We demonstrate this approach and apply it to four models that have been debated in the literature: Grammar-based, Iterated Best Response (IBR), Rational Speech Act (RSA), and a recent variant of RSA grounded in rate-distortion theory (RD-RSA). Using these optimal reference game experiments, we find empirical evidence favoring iterated rationality models over the grammar-based model, as well as support for the relevance of rate-distortion theory to human pragmatic inferences. These results suggest that our optimal reference game design framework may help adjudicate between computational theories of pragmatic reasoning.}
    }

@workshoppaper{hu_predicting_2022a,
      author = {Hu, Jennifer and Levy, Roger and Schuster, Sebastian},
      title = {Predicting scalar diversity with context-driven uncertainty over alternatives},
      booktitle = {ACL Workshop on Cognitive Modeling and Computational Linguistics},
      year = {2022},
      abstract = {Scalar implicature (SI) arises when a speaker uses an expression (e.g., "some") that is semantically compatible with a logically stronger alternative on the same scale (e.g., "all"), leading the listener to infer that they did not intend to convey the stronger meaning. Prior work has demonstrated that SI rates are highly variable across scales, raising the question of what factors determine the SI strength for a particular scale. Here, we test the hypothesis that SI rates depend on the listener's confidence in the underlying scale, which we operationalize as uncertainty over the distribution of possible alternatives conditioned on the context. We use a T5 model fine-tuned on a text infilling task to estimate the distribution over context-conditioned alternatives. We measure uncertainty both over the sampled alternatives themselves and over latent clusters among alternatives in sentence embedding space. We find that both scale uncertainty measures predict human SI rates, suggesting that SI depends on listeners' context-driven uncertainty over alternatives.},
      url = {https://openreview.net/forum?id=rTzgPQtx8-9}
    }

@article{hu_language_2022,
      author = {Hu, Jennifer and Small, Hannah and Kean, Hope and Takahashi, Atsushi and Zelekman, Leo and Kleinman, Daniel and Ryan, Elizabeth and Nieto-Castañón, Alfonso and Ferreira, Victor and Fedorenko, Evelina},
      title = {Precision fMRI reveals that the language-selective network supports both phrase-structure building and lexical access during language production},
      year = {2022},
      journal = {Cerebral Cortex},
      url = {https://academic.oup.com/cercor/advance-article-abstract/doi/10.1093/cercor/bhac350/6706753},
      code = {https://github.com/jennhu/LanguageProduction/},
      abstract = {A fronto-temporal brain network has long been implicated in language comprehension. However, this network’s role in language production remains debated. In particular, it remains unclear whether all or only some language regions contribute to production, and which aspects of production these regions support. Across three fMRI experiments that rely on robust individual-subject analyses, we characterize the language network’s response to high-level production demands. We report three novel results. First, sentence production, spoken or typed, elicits a strong response throughout the language network. Second, the language network responds to both phrase-structure building and lexical access demands, although the response to phrase-structure building is stronger and more spatially extensive, present in every language region. Finally, contra some proposals, we find no evidence of brain regions—within or outside the language network—that selectively support phrase-structure building in production relative to comprehension. Instead, all language regions respond more strongly during production than comprehension, suggesting that production incurs a greater cost for the language network. Together, these results align with the idea that language comprehension and production draw on the same knowledge representations, which are stored in a distributed manner within the language-selective network and are used to both interpret and generate linguistic utterances.}
    }

@abstract{wang_facilitative_2022,
      author = {Wang, Yiwen and Hu, Jennifer and Levy, Roger and Qian, Peng},
      title = {Facilitative Effect Induced by Classifier-Noun Mismatch in Mandarin Chinese},
      year = {2022},
      booktitle = {The 35th Annual Conference on Human Sentence Processing},
    }

@inproceedings{wang_controlled_2021,
      author = {Wang, Yiwen and Hu, Jennifer and Levy, Roger and Qian, Peng},
      title = {Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models},
      booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
      year = {2021},
      url = {https://aclanthology.org/2021.emnlp-main.454/},
      code = {https://github.com/yiwenwang03/syntactic-generalization-mandarin},
      abstract = {Prior work has shown that structural supervision helps English language models learn generalizations about syntactic phenomena such as subject-verb agreement. However, it remains unclear if such an inductive bias would also improve language models' ability to learn grammatical dependencies in typologically different languages. Here we investigate this question in Mandarin Chinese, which has a logographic, largely syllable-based writing system, different word order, and sparser morphology than English. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and Transformer-parameterized generative parsing models on two Mandarin Chinese datasets of different sizes. We evaluate the models' ability to learn different aspects of Mandarin grammar that assess syntactic and semantic relationships. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings, suggesting that the benefits of hierarchical inductive biases in acquiring dependency relationships may extend beyond English.}
    }

@workshoppaper{hu_scalable_2021,
      author = {Hu, Jennifer and Levy, Roger and Zaslavsky, Noga},
      title = {Scalable pragmatic communication via self-supervision},
      booktitle = {ICML Workshop on Self-Supervised Learning for Reasoning and Perception},
      year = {2021},
      abstract = {Models of context-sensitive communication often use the Rational Speech Act framework (RSA; Frank & Goodman, 2012), which formulates listeners and speakers in a cooperative reasoning process. However, the standard RSA formulation can only be applied to small domains, and large-scale applications have relied on imitating human behavior. Here, we propose a new approach to scalable pragmatics, building upon recent theoretical results (Zaslavsky et al., 2020) that characterize pragmatic reasoning in terms of general information-theoretic principles. Specifically, we propose an architecture and learning process in which agents acquire pragmatic policies via self-supervision instead of imitating human data. This work suggests a new principled approach for equipping artificial agents with pragmatic skills via self-supervision, which is grounded both in pragmatic theory and in information theory.},
      url = {https://arxiv.org/abs/2108.05799}
    }

@inproceedings{hu_competition_2021,
      author     = {Hu, Jennifer and Zaslavsky, Noga and Levy, Roger},
      title      = {Competition from novel features drives scalar inferences in reference games},
      booktitle  = CogSci,
      year       = {2021},
      code       = {https://github.com/jennhu/nonce-SI},
      url        = {https://escholarship.org/uc/item/8jx5h8sn},
      abstract   = {Scalar implicatures, one of the signatures of pragmatic reasoning, are believed to arise from competing alternative utterances, which the listener knows that the speaker could have used to express a strengthened meaning. But do scalar implicatures also arise in the presence of nonce objects, for which no alternative name is known? We conduct a series of experiments assessing the degree of scalar strengthening driven by familiar and nonce objects. We find that nonce objects can derive scalar implicatures as strongly as familiar objects in simple reference games. Our experiments also reveal an asymmetry in the relative strengths of familiar- and nonce-driven inferences: relative to the prior, participants preferentially interpret the name of a shared feature as referring to an object with an additional nonce feature over an object with an additional familiar feature, suggesting that familiar alternatives exert greater scalar pressure than nonce alternatives. We also present exploratory model simulations suggesting that our results may be explained by rationally reasoning about a high-cost description of the novel object. Our findings support the idea that novel lexical entries may be generated from one-shot encounters and spontaneously used in pragmatic inference.}
    }

@abstract{zhou_empirical_2021,
      author = {Zhou, Irene and Hu, Jennifer and Levy, Roger and Zaslavsky, Noga},
      title = {Empirical support for a Rate--Distortion account of pragmatic reasoning},
      year = {2021},
      booktitle = CogSci,
      Note = {Member abstract}
    }

@abstract{zaslavsky_rate--distortion_2021,
      author = {Zaslavsky, Noga and Hu, Jennifer and Levy, Roger},
      title = {A Rate--Distortion view of human pragmatic reasoning},
      year = {2021},
      booktitle = SCiL
    }

@abstract{hu_distributed_2020,
      author = {Hu, Jennifer and Small, Hannah and Kean, Hope and Takahashi, Atsushi and Zekelman, Leo and Kleinman, Daniel and Ryan, Elizabeth and Ferreira, Victor and Fedorenko, Evelina},
      title = {Distributed and overlapping neural mechanisms for lexical access and syntactic encoding during language production},
      booktitle = {Proceedings of the Society for the Neurobiology of Language},
      year = {2020}
    }

@inproceedings{wilcox_predictive_2020,
      author = {Wilcox, Ethan and Gauthier, Jon and Hu, Jennifer and Qian, Peng and Levy, Roger},
      title = {On the predictive power of neural language models for human real-time comprehension behavior},
      booktitle = CogSci,
      year = {2020},
      url = {https://arxiv.org/abs/2006.01912},
      code = {https://github.com/wilcoxeg/neural-networks-read-times}
    }

@abstract{wilcox_benchmarking_2020,
      author = {Wilcox, Ethan and Gauthier, Jon and Hu, Jennifer and Qian, Peng and Levy, Roger},
      title = {Benchmarking neural networks as models of human language processing},
      booktitle = {Proceedings of the 26th Architectures and Mechanisms for Language Processing Conference},
      year = {2020},
    }

@inproceedings{hu-etal-2020-systematic,
        title = "A Systematic Assessment of Syntactic Generalization in Neural Language Models",
        author = "Hu, Jennifer and Gauthier, Jon and Qian, Peng and Wilcox, Ethan and Levy, Roger",
        booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
        month = jul,
        year = "2020",
        address = "Online",
        publisher = "Association for Computational Linguistics",
        url = "https://www.aclweb.org/anthology/2020.acl-main.158",
        pages = "1725--1744",
        abstract = "While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, existing work has not provided a clear picture about the model properties required to produce proper syntactic generalizations. We present a systematic evaluation of the syntactic knowledge of neural language models, testing 20 combinations of model types and data sizes on a set of 34 English-language syntactic test suites. We find substantial differences in syntactic generalization performance by model architecture, with sequential models underperforming other architectures. Factorially manipulating model architecture and training dataset size (1M-40M words), we find that variability in syntactic generalization performance is substantially greater by architecture than by dataset size for the corpora tested in our experiments. Our results also reveal a dissociation between perplexity and syntactic generalization performance.",
      code = {https://github.com/cpllab/syntactic-generalization}
    }

@inproceedings{gauthier-etal-2020-syntaxgym,
        title = "{S}yntax{G}ym: An Online Platform for Targeted Evaluation of Language Models",
        author = "Gauthier, Jon and Hu, Jennifer and Wilcox, Ethan and Qian, Peng and Levy, Roger",
        booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
        month = jul,
        year = "2020",
        address = "Online",
        publisher = "Association for Computational Linguistics",
        url = "https://www.aclweb.org/anthology/2020.acl-demos.10",
        pages = "70--76",
        abstract = "Targeted syntactic evaluations have yielded insights into the generalizations learned by neural network language models. However, this line of research requires an uncommon confluence of skills: both the theoretical knowledge needed to design controlled psycholinguistic experiments, and the technical proficiency needed to train and deploy large-scale language models. We present SyntaxGym, an online platform designed to make targeted evaluations accessible to both experts in NLP and linguistics, reproducible across computing environments, and standardized following the norms of psycholinguistic experimental design. This paper releases two tools of independent value for the computational linguistics community: 1. A website, syntaxgym.org, which centralizes the process of targeted syntactic evaluation and provides easy tools for analysis and visualization; 2. Two command-line tools, {`}syntaxgym{`} and {`}lm-zoo{`}, which allow any user to reproduce targeted syntactic evaluations and general language model inference on their own machine.",
      website = "http://syntaxgym.org/"
    }

@abstract{wilcox_evaluating_2020,
      author = {Wilcox, Ethan and Gauthier, Jon and Qian, Peng and Hu, Jennifer and Levy, Roger},
      title = {Evaluating the effect of model inductive bias and training data in predicting human reading times},
      booktitle = {Proceedings of the 33rd Annual CUNY Human Sentence Processing Conference},
      year = {2020},
    }

@abstract{zaslavsky_emergence_2020,
      author = {Zaslavsky, Noga and Hu, Jennifer and Levy, Roger},
      title = {Emergence of pragmatic reasoning from least-effort optimization},
      booktitle = {Proceedings of Evolution of Language International Conferences},
      year = {2020},
    }

@inproceedings{hu_closer_2020,
      author = {Hu, Jennifer and Chen, Sherry Yong and Levy, Roger},
      title = {A closer look at the performance of neural language models on reflexive anaphor licensing},
      booktitle = SCiL,
      Volume = {3},
      Pages = {382-392},
      year = {2020},
      url = {https://scholarworks.umass.edu/scil/vol3/iss1/37/},
      Code = {https://github.com/jennhu/reflexive-anaphor-licensing}
    }

@inproceedings{hu_separating_2019,
      author = {Hu, Jennifer and Traer, James and McDermott, Josh H.},
      title = {Separating object resonance and room reverberation in impact sounds},
      booktitle = CogSci,
      year = {2019},
      abstract = {Everyday hearing requires inferring the causal factors that produce a sound, as when we separate the acoustic effects of the environment (reverberation) from those of sound sources. Here we consider perceptual inferences from impact sounds, in which the resonance of a struck object provides cues to its material, but via acoustic effects that might be nontrivial to disentangle from reverberation. We investigated whether and how humans separate the effects of object resonance and reverberation in a material classification task. For comparison, we implemented a Bayesian observer that inferred material from a generative model of object sounds without reverberation. Humans were robust to reverberation, whereas the model was not. However, human robustness was specific to reverberation consistent with the statistics of natural environments. The results suggest that humans use internal models of room and object acoustics to determine their respective contributions to sound, providing an example of causal inference in audition.}
    }

@inproceedings{monroe-etal-2018-generating,
        title = "Generating Bilingual Pragmatic Color References",
        author = "Monroe, Will  and
          Hu, Jennifer  and
          Jong, Andrew  and
          Potts, Christopher",
        booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
        month = jun,
        year = "2018",
        address = "New Orleans, Louisiana",
        publisher = "Association for Computational Linguistics",
        url = "https://aclanthology.org/N18-1196",
        doi = "10.18653/v1/N18-1196",
        pages = "2155--2165",
        abstract = "Contextual influences on language often exhibit substantial cross-lingual regularities; for example, we are more verbose in situations that require finer distinctions. However, these regularities are sometimes obscured by semantic and syntactic differences. Using a newly-collected dataset of color reference games in Mandarin Chinese (which we release to the public), we confirm that a variety of constructions display the same sensitivity to contextual difficulty in Chinese and English. We then show that a neural speaker agent trained on bilingual data with a simple multitask learning approach displays more human-like patterns of context dependence and is more pragmatically informative than its monolingual Chinese counterpart. Moreover, this is not at the expense of language-specific semantic understanding: the resulting speaker model learns the different basic color term systems of English and Chinese (with noteworthy cross-lingual influences), and it can identify synonyms between the two languages using vector analogy operations on its output layer, despite having no exposure to parallel data.",
        Code = {https://github.com/futurulus/colors-in-context},
        data = {https://cocolab.stanford.edu/datasets/colors.html},
    }

@abstract{LSA2018,
      author = {Hu, Jennifer},
      title = {A graph-theoretic approach to comparing typologies in {P}arallel {OT} and {H}armonic {S}erialism},
      booktitle = {Proceedings of the 92nd Annual Meeting of the Linguistic Society of America},
      year = {2018},
      Address = {Salt Lake City, UT}
    }