Human processing of nonlocal syntactic dependencies requires the engagement of limited working memory for encoding, maintenance, and retrieval. This process creates an evolutionary pressure for language to be structured in a way that keeps the subparts of a dependency closer to each other, an efficiency principle termed dependency locality. The current study proposes that such a dependency locality pressure can be modulated by the surprisal of the antecedent, defined as the first part of a dependency, due to strategic allocation of working memory. In particular, antecedents with novel and unpredictable information are prioritized for memory encoding, receiving more robust representation against memory interference and decay, and thus are more capable of handling longer dependency length. We examine this claim by analyzing dependency corpora of 11 languages, with word surprisal generated from GPT-3 language model. In support of our hypothesis, we find evidence for a positive correlation between dependency length and the antecedent surprisal in most of the languages in our analyses. A closer look into the dependencies with core arguments shows that this correlation consistently holds for subject relations but not for object relations.

Chomsky and others have very directly claimed that large language models (LLMs) are equally capable of learning languages that are possible and impossible for humans to learn. However, there is very little published experimental evidence to support such a claim. Here, we develop a set of synthetic impossible languages of differing complexity, each designed by systematically altering English data with unnatural word orders and grammar rules. These languages lie on an impossibility continuum: at one end are languages that are inherently impossible, such as random and irreversible shuffles of English words, and on the other, languages that may not be intuitively impossible but are often considered so in linguistics, particularly those with rules based on counting word positions. We report on a wide range of evaluations to assess the capacity of GPT-2 small models to learn these uncontroversially impossible languages, and crucially, we perform these assessments at various stages throughout training to compare the learning process for each language. Our core finding is that GPT-2 struggles to learn impossible languages when compared to English as a control, challenging the core claim. More importantly, we hope our approach opens up a productive line of inquiry in which different LLM architectures are tested on a variety of impossible languages in an effort to learn more about how LLMs can be used as tools for these cognitive and typological investigations.

We apply a continuous relaxation of L₀ regularization (Louizos et al., 2017), which induces sparsity, to study the inductive biases of LSTMs. In particular, we are interested in the patterns of formal languages which are readily learned and expressed by LSTMs. Across a wide range of tests we find sparse LSTMs prefer subregular languages over regular languages and the strength of this preference increases as we increase the pressure for sparsity. Furthermore LSTMs which are trained on subregular languages have fewer non-zero parameters. We conjecture that this subregular bias in LSTMs is related to the cognitive bias for subregular language observed in human phonology which are both downstream of a simplicity bias in a suitable description language.

The advancement of Large Language Models (LLMs) has led to their widespread use across a broad spectrum of tasks, including decision-making. Prior studies have compared the decision-making abilities of LLMs with those of humans from a psychological perspective. However, these studies have not always properly accounted for the sensitivity of LLMs’ behavior to hyperparameters and variations in the prompt. In this study, we examine LLMs’ performance on the Horizon decision-making task studied by Binz and Schulz (2023), analyzing how LLMs respond to variations in prompts and hyperparameters. By experimenting on three OpenAI language models possessing different capabilities, we observe that the decision-making abilities fluctuate based on the input prompts and temperature settings. Contrary to previous findings, language models display a human-like exploration–exploitation tradeoff after simple adjustments to the prompt.

In psycholinguistics, surprisal theory posits that the amount of online processing effort expended by a human comprehender per word positively correlates with the surprisal of that word given its preceding context. In addition to this overall correlation, more importantly, the specific quantitative form taken by the processing effort as a function of surprisal offers insights into the underlying cognitive mechanisms of language processing. Focusing on English, previous studies have looked into the linearity of surprisal on reading times. Here, we extend the investigation by examining eyetracking corpora of seven languages: Danish, Dutch, English, German, Japanese, Mandarin, and Russian. We find evidence for superlinearity in some languages, but the results are highly sensitive to which language model is used to estimate surprisal.

While natural languages differ widely in both canonical word order and word order flexibility, their word orders still follow shared cross-linguistic statistical patterns, often attributed to functional pressures. In the effort to identify these pressures, prior work has compared real and counterfactual word orders. Yet one functional pressure has been overlooked in such investigations: The uniform information density (UID) hypothesis, which holds that information should be spread evenly throughout an utterance. Here, we ask whether a pressure for UID may have influenced word order patterns cross-linguistically. To this end, we use computational models to test whether real orders lead to greater information uniformity than counterfactual orders. In our empirical study of 10 typologically diverse languages, we find that: (i) among SVO languages, real word orders consistently have greater uniformity than reverse word orders, and (ii) only linguistically implausible counterfactual orders consistently exceed the uniformity of real orders. These findings are compatible with a pressure for information uniformity in the development and usage of natural languages.1

The literature on adjective ordering abounds with proposals meant to account for why certain adjectives appear before others in multi-adjective strings (e.g., the small brown box). However, these proposals have been developed and tested primarily in isolation and based on English; few researchers have looked at the combined performance of multiple factors in the determination of adjective order, and few have evaluated predictors across multiple languages. The current work approaches both of these objectives by using technologies and datasets from natural language processing to look at the combined performance of existing proposals across 32 languages. Comparing this performance with both random and idealized baselines, we show that the literature on adjective ordering has made significant meaningful progress across its many decades, but there remains quite a gap yet to be explained.

We investigate how to use pretrained static word embeddings to deliver improved estimates of bilexical co-occurrence probabilities: conditional probabilities of one word given a single other word in a specific relationship. Such probabilities play important roles in psycholinguistics, corpus linguistics, and usage-based cognitive modeling of language more generally. We propose a log-bilinear model taking pretrained vector representations of the two words as input, enabling generalization based on the distributional information contained in both vectors. We show that this model outperforms baselines in estimating probabilities of adjectives given nouns that they attributively modify, and probabilities of nominal direct objects given their head verbs, given limited training data in Arabic, English, Korean, and Spanish.

Because meaning can often be inferred from lexical semantics alone, word order is often a redundant cue in natural language. For example, the words chopped, chef, and onion are more likely used to convey “The chef chopped the onion,” not “The onion chopped the chef.” Recent work has shown large language models to be surprisingly word order invariant, but crucially has largely considered natural prototypical inputs, where compositional meaning mostly matches lexical expectations. To overcome this confound, we probe grammatical role representation in English BERT and GPT-2, on instances where lexical expectations are not sufficient, and word order knowledge is necessary for correct classification. Such non-prototypical instances are naturally occurring English sentences with inanimate subjects or animate objects, or sentences where we systematically swap the arguments to make sentences like “The onion chopped the chef”. We find that, while early layer embeddings are largely lexical, word order is in fact crucial in defining the later-layer representations of words in semantically non-prototypical positions. Our experiments isolate the effect of word order on the contextualization process, and highlight how models use context in the uncommon, but critical, instances where it matters.

Using data from Nintemann et al. (2020), we explore the variability in complexity and informativity across spatial demonstrative systems using spatial deictic lexicons from 223 languages. We argue from an information-theoretic perspective (Shannon, 1948) that spatial deictic lexicons are efficient in communication, balancing informativity and complexity. Specifically, we find that under an appropriate choice of cost function and need probability over meanings, among all the 21146 theoretically possible spatial deictic lexicons, those adopted by real languages lie near an efficient frontier. Moreover, we find that the conditions that the need probability and the cost function need to satisfy are consistent with the cognitive science literature regarding the source-goal asymmetry. We also show that the data are better explained by introducing a notion of systematicity, which is not currently accounted for in Information Bottleneck approaches to linguistic efficiency.

Formal constraints on crossing dependencies have played a large role in research on the formal complexity of natural language grammars and parsing. Here we ask whether the apparent evidence for constraints on crossing dependencies in treebanks might arise because of independent constraints on trees, such as low arity and dependency length minimization. We address this question using two sets of experiments. In Experiment 1, we compare the distribution of formal properties of crossing dependencies, such as gap degree, between real trees and baseline trees matched for rate of crossing dependencies and various other properties. In Experiment 2, we model whether two dependencies cross, given certain psycholinguistic properties of the dependencies. We find surprisingly weak evidence for constraints originating from the mild context-sensitivity literature (gap degree and well-nestedness) beyond what can be explained by constraints on rate of crossing dependencies, topological properties of the trees, and dependency length. However, measures that have emerged from the parsing literature (e.g., edge degree, end-point crossings, and heads’ depth difference) differ strongly between real and random trees. Modeling results show that cognitive metrics relating to information locality and working-memory limitations affect whether two dependencies cross or not, but they do not fully explain the distribution of crossing dependencies in natural languages. Together these results suggest that crossing constraints are better characterized by processing pressures than by mildly context-sensitive constraints.

Morphological systems across languages vary when it comes to the relation between form and meaning. In some languages, a single meaning feature corresponds to a single morpheme, whereas in other languages, multiple meaning features are bundled together into one morpheme. The two types of languages have been called agglutinative and fusional, respectively, but this distinction does not capture the graded nature of the phenomenon. We provide a mathematically precise way of characterizing morphological systems using partial information decomposition, a framework for decomposing mutual information into three components: unique, redundant, and synergistic information. We show that highly fusional languages are characterized by high levels of synergy.

We introduce a simple and highly general phonotactic learner which induces a probabilistic finite-state automaton from word-form data. We describe the learner and show how to parameterize it to induce unrestricted regular languages, as well as how to restrict it to certain subregular classes such as Strictly k-Local and Strictly k-Piecewise languages. We evaluate the learner on its ability to learn phonotactic constraints in toy examples and in datasets of Quechua and Navajo. We find that an unrestricted learner is the most accurate overall when modeling attested forms not seen in training; however, only the learner restricted to the Strictly Piecewise language class successfully captures certain nonlocal phonotactic constraints. Our learner serves as a baseline for more sophisticated methods.

We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sensitivity. The sensitivity of a function, given a distribution over input sequences, quantifies the number of disjoint subsets of the input sequence that can each be individually changed to change the output. We argue that standard sequence classification methods are biased towards learning low-sensitivity functions, so that tasks requiring high sensitivity are more difficult. To that end, we show analytically that simple lexical classifiers can only express functions of bounded sensitivity, and we show empirically that low-sensitivity functions are easier to learn for LSTMs. We then estimate sensitivity on 15 NLP tasks, finding that sensitivity is higher on challenging tasks collected in GLUE than on simple text classification tasks, and that sensitivity predicts the performance both of simple lexical classifiers and of vanilla BiLSTMs without pretrained contextualized embeddings. Within a task, sensitivity predicts which inputs are hard for such simple models. Our results suggest that the success of massively pretrained contextual representations stems in part because they provide representations from which information can be extracted by low-sensitivity decoders.

We investigate how Multilingual BERT (mBERT) encodes grammar by examining how the high-order grammatical feature of morphosyntactic alignment (how different languages define what counts as a “subject”) is manifested across the embedding spaces of different languages. To understand if and how morphosyntactic alignment affects contextual embedding spaces, we train classifiers to recover the subjecthood of mBERT embeddings in transitive sentences (which do not contain overt information about morphosyntactic alignment) and then evaluate them zero-shot on intransitive sentences (where subjecthood classification depends on alignment), within and across languages. We find that the resulting classifier distributions reflect the morphosyntactic alignment of their training languages. Our results demonstrate that mBERT representations are influenced by high-level grammatical features that are not manifested in any one input sentence, and that this is robust across languages. Further examining the characteristics that our classifiers rely on, we find that features such as passive voice, animacy and case strongly correlate with classification decisions, suggesting that mBERT does not encode subjecthood purely syntactically, but that subjecthood embedding is continuous and dependent on semantic and discourse factors, as is proposed in much of the functional linguistics literature. Together, these results provide insight into how grammatical features manifest in contextual embedding spaces, at a level of abstraction not covered by previous work.

Linguistic typology generally divides synthetic languages into groups based on their morphological fusion. However, this measure has long been thought to be best considered a matter of degree. We present an information-theoretic measure, called informational fusion, to quantify the degree of fusion of a given set of morphological features in a surface form, which naturally provides such a graded scale. Informational fusion is able to encapsulate not only concatenative, but also nonconcatenative morphological systems (e.g. Arabic), abstracting away from any notions of morpheme segmentation. We then show, on a sample of twenty-one languages, that our measure recapitulates the usual linguistic classifications for concatenative systems, and provides new measures for nonconcatenative ones. We also evaluate the long-standing hypotheses that more frequent forms are more fusional, and that paradigm size anticorrelates with degree of fusion. We do not find evidence for the idea that languages have characteristic levels of fusion; rather, the degree of fusion varies across part-of-speech within languages.

We take up the scientific question of what determines the preferred order of adjectives in English, in phrases such as big blue box where multiple adjectives modify a following noun. We implement and test four quantitative theories, all of which are theoretically motivated in terms of efficiency in human language production and comprehension. The four theories we test are subjectivity (Scontras et al., 2017), information locality (Futrell, 2019), integration cost (Dyer, 2017), and information gain, which we introduce. We evaluate theories based on their ability to predict orders of unseen adjectives in hand-parsed and automatically-parsed dependency treebanks. We find that subjectivity, information locality, and information gain are all strong predictors, with some evidence for a two-factor account, where subjectivity and information gain reflect a factor involving semantics, and information locality reflects collocational preferences.

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce this behavior in English and evaluate the effect of structural supervision on learning outcomes. First, we assess few-shot learning capabilities by developing controlled experiments that probe models’ syntactic nominal number and verbal argument structure generalizations for tokens seen as few as two times during training. Second, we assess invariance properties of learned representation: the ability of a model to transfer syntactic generalizations from a base context (e.g., a simple declarative active-voice sentence) to a transformed context (e.g., an interrogative sentence). We test four models trained on the same dataset: an n-gram baseline, an LSTM, and two LSTM-variants trained with explicit structural supervision. We find that in most cases, the neural models are able to induce the proper syntactic generalizations after minimal exposure, often from just two examples during training, and that the two structurally supervised models generalize more accurately than the LSTM model. All neural models are able to leverage information learned in base contexts to drive expectations in transformed contexts, indicating that they have learned some invariance properties of syntax.

Word order flexibility is one of the distinctive features of SOV languages. In this work, we investigate whether the order and relative distance of preverbal dependents in Hindi, an SOV language, is affected by factors motivated by efficiency considerations during comprehension/production. We investigate the influence of Head–Dependent Mutual Information (HDMI), similarity-based interference, accessibility and case-marking. Results show that preverbal dependents remain close to the verbal head when the HDMI between the verb and its dependent is high. This demonstrates the influence of locality constraints on dependency distance and word order in an SOV language. Additionally, dependency distance were found to be longer when the dependent was animate, when it was case-marked and when it was semantically similar to other preverbal dependents. Together the results highlight the crosslinguistic generalizability of these factors and provide evidence for a functionally motivated account of word order in SOV languages such as Hindi.

We investigate the extent to which the behavior of neural network language models reflects incremental representations of syntactic state. To do so, we employ experimental methodologies which were originally developed in the field of psycholinguistics to study syntactic representation in the human mind. We examine neural network model behavior on sets of artificial sentences containing a variety of syntactically complex structures. These sentences not only test whether the networks have a representation of syntactic state, they also reveal the specific lexical cues that networks use to update these states. We test four models: two publicly available LSTM sequence models of English (Jozefowicz et al., 2016; Gulordava et al., 2018) trained on large datasets; an RNN Grammar (Dyer et al., 2016) trained on a small, parsed dataset; and an LSTM trained on the same small corpus as the RNNG. We find evidence for basic syntactic state representations in all models, but only the models trained on large datasets are sensitive to subtle lexical cues signaling changes in syntactic state.

State-of-the-art LSTM language models trained on large corpora learn sequential contingencies in impressive detail, and have been shown to acquire a number of non-local grammatical dependencies with some success. Here we investigate whether supervision with hierarchical structure enhances learning of a range of grammatical dependencies, a question that has previously been addressed only for subject-verb agreement. Using controlled experimental methods from psycholinguistics, we compare the performance of word-based LSTM models versus Recurrent Neural Network Grammars (RNNGs) (Dyer et al. 2016) which represent hierarchical syntactic structure and use neural control to deploy it in left-to-right processing, on two classes of non-local grammatical dependencies in English—Negative Polarity licensing and Filler-Gap Dependencies—tested in a range of configurations. Using the same training data for both models, we find that the RNNG outperforms the LSTM on both types of grammatical dependencies and even learns many of the Island Constraints on the filler-gap dependency. Structural supervision thus provides data efficiency advantages over purely string-based training of neural language models in acquiring human-like generalizations about non-local grammatical dependencies.

The goal of this tutorial is to bring the fields of computational linguistics and computational cognitive science closer: we will introduce different stages of language acquisition and their parallel problems in NLP. As an example, one of the early challenges children face is mapping the meaning of word labels (such as “cat”) to their referents (the furry animal in the living room). Word learning is similar to the word alignment problem in machine translation. We explain the current computational models of language acquisition, their limitations, and how the insights from these models can be incorporated into NLP applications. Moreover, we discuss how we can take advantage of the cognitive science of language in computational linguistics: for example, by designing cognitively-motivated evaluations task or buildings language-learning inductive biases into our models.

Work using artificial languages as training input has shown that LSTMs are capable of inducing the stack-like data structures required to represent context-free and certain mildly context-sensitive languages — formal language classes which correspond in theory to the hierarchical structures of natural language. Here we present a suite of experiments probing whether neural language models trained on linguistic data induce these stack-like data structures and deploy them while incrementally predicting words. We study two natural language phenomena: center embedding sentences and syntactic island constraints on the filler–gap dependency. In order to properly predict words in these structures, a model must be able to temporarily suppress certain expectations and then recover those expectations later, essentially pushing and popping these expectations on a stack. Our results provide evidence that models can successfully suppress and recover expectations in many cases, but do not fully recover their previous grammatical state.

RNN language models have achieved state-of-the-art perplexity results and have proven useful in a suite of NLP tasks, but it is as yet unclear what syntactic generalizations they learn. Here we investigate whether state-of-the-art RNN language models represent long-distance filler–gap dependencies and constraints on them. Examining RNN behavior on experimentally controlled sentences designed to expose filler–gap dependencies, we show that RNNs can represent the relationship in multiple syntactic positions and over large spans of text. Furthermore, we show that RNNs learn a subset of the known restrictions on filler–gap dependencies, known as island constraints: RNNs show evidence for wh-islands, adjunct islands, and complex NP islands. These studies demonstrates that state-of-the-art RNN models are able to learn and generalize about empty syntactic positions.

We use the noisy-channel theory of human sentence comprehension to develop an incremental processing cost model that unifies and extends key features of expectation-based and memory-based models. In this model, which we call noisy-context surprisal, the processing cost of a word is the surprisal of the word given a noisy representation of the preceding context. We show that this model accounts for an outstanding puzzle in sentence comprehension, language-dependent structural forgetting effects (Gibson and Thomas, 1999; Vasishth et al., 2010; Frank et al., 2016), which are previously not well modeled by either expectation-based or memory-based approaches. Additionally, we show that this model derives and generalizes locality effects (Gibson, 1998; Demberg and Keller, 2008), a signature prediction of memory-based models. We give corpus-based evidence for a key assumption in this derivation.

We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a language. Unlike most computational models of phonotactics (Hayes and Wilson, 2008; Goldsmith and Riggle, 2012), we take a fully generative approach, modeling a process where forms are built up out of subparts by phonologically-informed structure building operations. We learn an inventory of subparts by applying stochastic memoization (Johnson et al., 2007; Goodman et al., 2008) to a generative process for phonemes structured as an and-or graph, based on concepts of feature hierarchy from generative phonology (Clements, 1985; Dresher, 2009). Subparts are combined in a way that allows tier-based feature interactions. We evaluate our models’ ability to capture phonotactic distributions in the lexicons of 14 languages drawn from the WOLEX corpus (Graff, 2012). Our full model robustly assigns higher probabilities to held-out forms than a sophisticated N-gram model for all languages. We also present novel analyses that probe model behavior in more detail.

Studies on the role of memory as a predictor of reading time latencies (1) differ in their predictions about when memory effects should occur in processing and (2) have had mixed results, with strong positive effects emerging from isolated constructed stimuli and weak or even negative effects emerging from naturally-occurring stimuli. Our study addresses these concerns by comparing several implementations of prominent sentence processing theories on an exploratory corpus and evaluating the most successful of these on a confirmatory corpus, using a new self-paced reading corpus of seemingly natural narratives constructed to contain an unusually high proportion of memory-intensive constructions. We show highly significant and complementary broad-coverage latency effects both for predictors based on the Dependency Locality Theory and for predictors based on a left-corner parsing model of sentence processing. Our results indicate that memory access during sentence processing does take time, but suggest that stimuli requiring many memory access events may be necessary in order to observe the effect.