Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified assurprisal. Traditionally, surprisal theory treats words as distinct entities, overlooking any potential similarity between them. Giulianelli et al. (2023) address this limitation by introducing information value, a measure of predictability designed to account for similarities between communicative units. Our work leverages Ricotta and Szeidl’s (2006) diversity index to extend surprisal into a metric that we term similarity-adjusted surprisal, exposing a mathematical relationship between surprisal and information value. Similarity-adjusted surprisal aligns with information value when considering graded similarities and reduces to standard surprisal when words are treated as distinct. Experimental results with reading time data indicate that similarity-adjusted surprisal adds predictive power beyond standard surprisal for certain datasets, suggesting it serves as a complementary measure of comprehension effort.

Language models are widely used in computational psycholinguistics to test theories that relate the negative log probability (the surprisal) of a region of interest (a substring of characters) under a language model to its cognitive cost experienced by readers, as operationalized, for example, by gaze duration on the region. However, the application of modern language models to psycholinguistic studies is complicated by the practice of using tokenization as an intermediate step in training a model. Doing so results in a language model over *token* strings rather than one over character strings. Vexingly, regions of interest are generally misaligned with these token strings. The paper argues that token-level language models should be (approximately) marginalized into character-level language models before they are used in psycholinguistic studies to compute the surprisal of a region of interest; then, the marginalized character-level language model can be used to compute the surprisal of an arbitrary character substring, which we term a focal area, that the experimenter may wish to use as a predictor. Our proposal of marginalizing a token-level model into a character-level one solves this misalignment issue independently of the tokenization scheme. Empirically, we discover various focal areas whose surprisal is a better psychometric predictor than the surprisal of the region of interest itself.

The Uniform Information Density (UID) hypothesis posits that speakers tend to distribute information evenly across linguistic units to achieve efficient communication. Of course, information rate in texts and discourses is not perfectly uniform. While these fluctuations can be viewed as theoretically uninteresting noise on top of a uniform target, another explanation is that UID is not the only functional pressure regulating information content in a language. Speakers may also seek to maintain interest, adhere to writing conventions, and build compelling arguments. In this paper, we propose one such functional pressure; namely that speakers modulate information rate based on location within a hierarchically-structured model of discourse. We term this the Structured Context Hypothesis and test it by predicting the surprisal contours of naturally occurring discourses extracted from large language models using predictors derived from discourse structure. We find that hierarchical predictors are significant predictors of a discourse’s information contour and that deeply nested hierarchical predictors are more predictive than shallow ones. This work takes an initial step beyond UID to propose testable hypotheses for why the information rate fluctuates in predictable ways.

We introduce a generalization of classic information-theoretic measures of predictive uncertainty in online language processing, based on the simulation of expected continuations of incremental linguistic contexts. Our framework provides a formal definition of anticipatory and responsive measures, and it equips experimenters with the tools to define new, more expressive measures beyond standard next-symbol entropy and surprisal. While extracting these standard quantities from language models is convenient, we demonstrate that using Monte Carlo simulation to estimate alternative responsive and anticipatory measures pays off empirically: New special cases of our generalized formula exhibit enhanced predictive power compared to surprisal for human cloze completion probability as well as ELAN, LAN, and N400 amplitudes, and greater complementarity with surprisal in predicting reading times.

Agent interaction has long been a key topic in psychology, philosophy, and artificial intelligence, and it is now gaining traction in large language model (LLM) research. This experimental study seeks to lay the groundwork for our understanding of dialogue-based interaction between LLMs: Do persona-prompted LLMs show consistent personality and language use in interaction? We condition GPT-3.5 on asymmetric personality profiles to create a population of LLM agents, administer personality tests and submit the agents to a collaborative writing task. We find different profiles exhibit different degrees of personality consistency and linguistic alignment in interaction.

We investigate the roles that efficiency and effectiveness play in speakers’ repetition of shared word sequences, or constructions, in task-oriented dialogue. We find that repeating constructions has negative effects on information rate and positive effects on rate of delivery, that information rate managing strategies are predictive of task success, and that this varies by the communicative function of the constructions being repeated. More effective dialogue is characterised by greater levels of shared construction usage and more efficient task-related repetition; while task-agnostic repetition can seem redundant, it can serve important efficiency and effectiveness functions. Our results provide a nuanced picture of the importance of repetition and of developing a shared lexicon for both efficiency and effectiveness in task-oriented dialogue.

We propose using automatically generated natural language definitions of contextualised word usages as interpretable word and word sense representations. Given a collection of usage examples for a target word, and the corresponding data-driven usage clusters (i.e., word senses), a definition is generated for each usage with a specialised Flan-T5 language model, and the most prototypical definition in a usage cluster is chosen as the sense label. We demonstrate how the resulting sense labels can make existing approaches to semantic change analysis more interpretable, and how they can allow users — historical linguists, lexicographers, or social scientists — to explore and intuitively explain diachronic trajectories of word meaning. Semantic change analysis is only one of many possible applications of the ‘definitions as representations’ paradigm. Beyond being human-readable, contextualised definitions also outperform token or usage sentence embeddings in word-in-context semantic similarity judgements, making them a new promising type of lexical representation for NLP.

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it is a key component of dialogue. Humans use local and partner specific repetitions; these are preferred by human users and lead to more successful communication in dialogue. In this study, we evaluate (a) whether language models produce human-like levels of repetition in dialogue, and (b) what are the processing mechanisms related to lexical re-use they use during comprehension. We believe that such joint analysis of model production and comprehension behaviour can inform the development of cognitively inspired dialogue generation systems.

Dialogue participants may have varying levels of knowledge about the topic under discussion. In such cases, it is essential for speakers to adapt their utterances by taking their audience into account. Yet, it is an open question how such adaptation can be modelled in computational agents. In this paper, we model a visually grounded referential game between a knowledgeable speaker and a listener with more limited visual and linguistic experience. Inspired by psycholinguistic theories, we endow our speaker with the ability to adapt its referring expressions via a simulation module that monitors the effectiveness of planned utterances from the listener’s perspective. We propose an adaptation mechanism building on plug-and-play approaches to controlled language generation, where utterance generation is steered on the fly by the simulator without finetuning the speaker’s underlying language model. Our results and analyses show that our approach is effective: the speaker’s utterances become closer to the listener’s domain of expertise, which leads to higher communicative success.

We present information value, a measure which quantifies the predictability of an utterance relative to a set of plausible alternatives. We introduce a method to obtain interpretable estimates of information value using neural text generators, and exploit their psychometric predictive power to investigate the dimensions of predictability that drive human comprehension behaviour. Information value is a stronger predictor of utterance acceptability in written and spoken dialogue than aggregates of token-level surprisal and it is complementary to surprisal for predicting eye-tracked reading times.

In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically, syntactically, and semantically across four NLG tasks, connecting human production variability to aleatoric or data uncertainty. We then inspect the space of output strings shaped by a generation system’s predicted probability distribution and decoding algorithm to probe its uncertainty. For each test input, we measure the generator’s calibration to human production variability. Following this instance-level approach, we analyse NLG models and decoding strategies, demonstrating that probing a generator with multiple samples and, when possible, multiple references, provides the level of detail necessary to gain understanding of a model’s representation of uncertainty.

Morphological and syntactic changes in word usage — as captured, e.g., by grammatical profiles — have been shown to be good predictors of a word’s meaning change. In this work, we explore whether large pre-trained contextualised language models, a common tool for lexical semantic change detection, are sensitive to such morphosyntactic changes. To this end, we first compare the performance of grammatical profiles against that of a multilingual neural language model (XLM-R) on 10 datasets, covering 7 languages, and then combine the two approaches in ensembles to assess their complementarity. Our results show that ensembling grammatical profiles with XLM-R improves semantic change detection performance for most datasets and languages. This indicates that language models do not fully cover the fine-grained morphological and syntactic signals that are explicitly represented in grammatical profiles. An interesting exception are the test sets where the time spans under analysis are much longer than the time gap between them (for example, century-long spans with a one-year gap between them). Morphosyntactic change is slow so grammatical profiles do not detect in such cases. In contrast, language models, thanks to their access to lexical information, are able to detect fast topical changes.

This position paper proposes a conceptual framework for the design of Natural Language Generation (NLG) systems that follow efficient and effective production strategies in order to achieve complex communicative goals. In this general framework, efficiency is characterised as the parsimonious regulation of production and comprehension costs while effectiveness is measured with respect to task-oriented and contextually grounded communicative goals. We provide concrete suggestions for the estimation of goals, costs, and utility via modern statistical methods, demonstrating applications of our framework to the classic pragmatic task of visually grounded referential games and to abstractive text summarisation, two popular generation tasks with real-world applications. In sum, we advocate for the development of NLG systems that learn to make pragmatic production decisions from experience, by reasoning about goals, costs, and utility in a human-like way.

We investigate the extent to which pre-trained language models acquire analytical and deductive logical reasoning capabilities as a side effect of learning word prediction. We present AnaLog, a natural language inference task designed to probe models for these capabilities, controlling for different invalid heuristics the models may adopt instead of learning the desired generalisations. We test four languagemodels on AnaLog, finding that they have all learned, to a different extent, to encode information that is predictive of entailment beyond shallow heuristics such as lexical overlap and grammaticality. We closely analyse the best performing language model and show that while it performs more consistently than other language models across logical connectives and reasoning domains, it still is sensitive to lexical and syntactic variations in the realisation of logical statements.

Speakers repeat constructions frequently in dialogue. Due to their peculiar information-theoretic properties, repetitions can be thought of as a strategy for cost-effective communication. In this study, we focus on the repetition of lexicalised constructions—i.e., recurring multi-word units—in English open-domain spoken dialogues. We hypothesise that speakers use construction repetition to mitigate information rate, leading to an overall decrease in utterance information content over the course of a dialogue. We conduct a quantitative analysis, measuring the information content of constructions and that of their containing utterances, estimating information content with an adaptive neural language model. We observe that construction usage lowers the information content of utterances. This facilitating effect (i) increases throughout dialogues, (ii) is boosted by repetition, (iii) grows as a function of repetition frequency and density, and (iv) is stronger for repetitions of referential constructions.

Semantics, morphology and syntax are strongly interdependent. However, the majority of computational methods for semantic change detection use distributional word representations which encode mostly semantics. We investigate an alternative method, grammatical profiling, based entirely on changes in the morphosyntactic behaviour of words. We demonstrate that it can be used for semantic change detection and even outperforms some distributional semantic methods. We present an in-depth qualitative and quantitative analysis of the predictions made by our grammatical profiling system, showing that they are plausible and interpretable.

Speakers are thought to use rational information transmission strategies for efficient communication (Genzel and Charniak, 2002; Aylett and Turk, 2004; Jaeger and Levy, 2007). Previous work analysing these strategies in sentence production has failed to take into account how the information content of sentences varies as a function of the available discourse context. In this study, we estimate sentence information content within discourse context. We find that speakers transmit information at a stable rate—i.e., rationally—in English newspaper articles but that this rate decreases in spoken open domain and written task-oriented dialogues. We also observe that speakers’ choices are not oriented towards local uniformity of information, which is another hypothesised rational strategy. We suggest that a more faithful model of communication should explicitly include production costs and goal-oriented rewards.

The Uniform Information Density principle states that speakers plan their utterances to reduce fluctuations in the density of the information transmitted. In this paper, we test whether, and within which contextual units this principle holds in task-oriented dialogues. We show that there is evidence supporting the principle in written dialogues where participants play a cooperative reference game as well as in spoken dialogues involving instruction giving and following. Our study underlines the importance of identifying the relevant contextual components, showing that information content increases particularly within topically and referentially related contextual units.

We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of two contextualising architectures (BERT and ELMo) and three change detection algorithms. We find that the most effective algorithms rely on the cosine similarity between averaged token embeddings and the pairwise distances between token embeddings. They outperform strong baselines by a large margin (in the post-evaluation phase, we have the best Subtask 2 submission for SemEval-2020 Task 1), but interestingly, the choice of a particular algorithm depends on the distribution of gold scores in the test set.

This paper presents the first unsupervised approach to lexical semantic change that makes use of contextualised word representations. We propose a novel method that exploits the BERT neural language model to obtain representations of word usages, clusters these representations into usage types, and measures change along time with three proposed metrics. We create a new evaluation dataset and show that the model representations and the detected semantic shifts are positively correlated with human judgements. Our extensive qualitative analysis demonstrates that our method captures a variety of synchronic and diachronic linguistic phenomena. We expect our work to inspire further research in this direction.

Dialogue participants often refer to entities or situations repeatedly within a conversation, which contributes to its cohesiveness. Subsequent references exploit the common ground accumulated by the interlocutors and hence have several interesting properties, namely, they tend to be shorter and reuse expressions that were effective in previous mentions. In this paper, we tackle the generation of first and subsequent references in visually grounded dialogue. We propose a generation model that produces referring utterances grounded in both the visual and the conversational context. To assess the referring effectiveness of its output, we also implement a reference resolution system. Our experiments and analyses show that the model produces better, more effective referring utterances than a model not grounded in the dialogue context, and generates subsequent references that exhibit linguistic patterns akin to humans.

How do neural language models keep track of number agreement between subject and verb? We show that ‘diagnostic classifiers’, trained to predict number from the internal states of a language model, provide a detailed understanding of how, when, and where this information is represented. Moreover, they give us insight into when and where number information is corrupted in cases where the language model ends up making agreement errors. To demonstrate the causal role played by the representations we find, we then use agreement information to influence the course of the LSTM during the processing of difficult sentences. Results from such an intervention reveal a large increase in the language model’s accuracy. Together, these results show that diagnostic classifiers give us an unrivalled detailed look into the representation of linguistic information in neural models, and demonstrate that this knowledge can be used to improve their performance.