Thailand

This paper describes our solution of the first subtask from the AXOLOTL-24 shared task on Semantic Change Modeling. The goal of this subtask is to distribute a given set of usages of an ambiguous word from a newer time period between senses of this word from an older time period given as a set of sense definitions and some undefined number of clusters that should represent gained senses of this word. We propose and experiment with three new methods solving this task. Our methods achieve SOTA results according to both official metrics of the shared task. Additionally, we develop a model that can tell if a given word usage is not described by any of the provided sense definitions. This model serves as a component in one of our methods, but can potentially be useful on its own.

ACL 2024

Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modeling

novel sense detection

lexical semantic change detection

word sense induction

word sense disambiguation

workshop paper

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Computational and human perception are often considered separate approaches for studying sound changes over time; few works have touched on the intersection of both. To fill this research gap, we provide a pioneering review contrasting computational with human perception from the perspectives of methods and tasks. Overall, computational approaches rely on computer-driven models to perceive historical sound changes on etymological datasets, while human approaches use listener-driven models to perceive ongoing sound changes on recording corpora. Despite their differences, both approaches complement each other on phonetic and acoustic levels, showing the potential to achieve a more comprehensive perception of sound change. Moreover, we call for a comparative study on the datasets used by both approaches to investigate the influence of historical sound changes on ongoing changes. Lastly, we discuss the applications of sound change in computational linguistics, and point out that perceiving sound change alone is insufficient, as many processes of language change are complex, with entangled changes at syntactic, semantic, and phonetic levels.

Exploring Sound Change Over Time: A Review of Computational and Human Perception

Lexical Semantic Change Detection (LSCD) aims to detect language change from a diachronic corpus over time. We can see that over the last two decades there has been a surge in research dealing with the LSC Detection. Recently, a series of methods especially contextualized word embeddings have been widely established to address this task. While several studies have investigated LSCD using large language models (LLMs), an evaluation of prompt engineering techniques, such as few-shot learning with different in-context examples for improving the LSCD performance is required. In this study, we examine the few-shot learning ability of GPT-4 to detect semantic changes in the Chinese language change evaluation dataset ChiWUG. We show that our LLM-based solution improves the GCD evaluation metric on the ChiWUG benchmark compared to the previously top-performing pre-trained system. The result suggests that using GPT-4 with three-shot learning with hand-picked demonstrations achieves the best performance among our different prompts.

A Few-shot Learning Approach for Lexical Semantic Change Detection Using GPT-4

Children from bilingual backgrounds benefit from interactions with parents and teachers to re-acquire their heritage language. In this paper, we investigate how this insight from behavioral study can be incorporated into the learning of small-scale language models. We introduce BAMBINO-LM, a continual pre-training strategy for BabyLM that uses a novel combination of alternation and PPO-based perplexity reward induced from a parent Italian model. Upon evaluation on zero-shot classification tasks for English and Italian, BAMBINO-LM improves the Italian language capability of a BabyLM baseline. Our ablation analysis demonstrates that employing both the alternation strategy and PPO-based modeling is key to this effectiveness gain. We also show that, as a side effect, the proposed method leads to a similar degradation in L1 effectiveness as human children would have had in an equivalent learning scenario. Through its modeling and findings, BAMBINO-LM makes a focused contribution to the pre-training of small-scale language models by first developing a human-inspired strategy for pre-training and then showing that it results in behaviours similar to that of humans.

BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM

Recent psycholinguistic theories emphasize the interdependence between linguistic expectations and memory limitations in human language processing. We modify the self-attention mechanism of a transformer model to simulate a lossy context representation, biasing the model's predictions to give additional weight to the local linguistic context. We show that surprisal estimates from our locally-biased model generally provide a better fit to human psychometric data, underscoring the sensitivity of the human parser to local linguistic information.

Locally Biased Transformers Better Align with Human Reading Times

It is unclear whether large language models (LLMs) develop humanlike characteristics in language use. We subjected ChatGPT and Vicuna to 12 pre-registered psycholinguistic experiments ranging from sounds to dialogue. ChatGPT and Vicuna replicated the human pattern of language use in 10 and 7 out of the 12 experiments, respectively. The models associated unfamiliar words with different meanings depending on their forms, continued to access recently encountered meanings of ambiguous words, reused recent sentence structures, attributed causality as a function of verb semantics, and accessed different meanings and retrieved different words depending on an interlocutor’s identity. In addition, ChatGPT, but not Vicuna, nonliterally interpreted implausible sentences that were likely to have been corrupted by noise, drew reasonable inferences, and overlooked semantic fallacies in a sentence. Finally, unlike humans, neither model preferred using shorter words to convey less informative content, nor did they use context to resolve syntactic ambiguities. We discuss how these convergences and divergences may result from the transformer architecture. Overall, these experiments demonstrate that LLMs such as ChatGPT (and Vicuna to a lesser extent) are humanlike in many aspects of human language processing.

Do large language models resemble humans in language use?

Natural language has the universal properties of being compositional and grounded in reality. The emergence of linguistic properties is often investigated through simulations of emergent communication in referential games. However, these experiments have yielded mixed results compared to similar experiments addressing linguistic properties of human language. Here we address representational alignment as a potential contributing factor to these results. Specifically, we assess the representational alignment between agent image representations and between agent representations and input images. Doing so, we confirm that the emergent language does not appear to encode human-like conceptual visual features, since agent image representations drift away from inputs whilst inter-agent alignment increases. We moreover identify a strong relationship between inter-agent alignment and topographic similarity, a common metric for compositionality, and address its consequences. To address these issues, we introduce an alignment penalty that prevents representational drift but interestingly does not improve performance on a compositional discrimination task. Together, our findings emphasise the key role representational alignment plays in simulations of language emergence.

The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication

Language models (LMs) are a meeting point for cognitive modeling and computational linguistics. How should they be designed to serve as adequate cognitive models? To address this question, this study contrasts two Transformer-based LMs that share the same architecture. Only one of them analyzes sentences in terms of explicit hierarchical structure. Evaluating the two LMs against fMRI time series via the surprisal complexity metric, the results implicate the superior temporal gyrus. These findings underline the need for hierarchical sentence structures in word-by-word models of human language comprehension.

Hierarchical syntactic structure in human-like language models

Understanding human perception of nonsense words is helpful to devise product and character names that match their characteristics. Previous studies have suggested the usefulness of Large Language Models (LLMs) for estimating such human perception, but they did not focus on its emotional aspects. Hence, this study aims to elucidate the relationship of emotions evoked by nonsense words between humans and LLMs. Using a representative LLM, GPT-4, we reproduce the procedure of an existing study to analyze evoked emotions of humans for nonsense words. A positive correlation of 0.40 was found between the emotion intensity scores reproduced by GPT-4 and those manually annotated by humans. Although the correlation is not very high, this demonstrates that GPT-4 may agree with humans on emotional associations to nonsense words. Considering that the previous study reported that the correlation among human annotators was about 0.68 on average and that between a regression model trained on the annotations for real words and humans was 0.17, GPT-4's agreement with humans is notably strong.

Do LLMs Agree with Humans on Emotional Associations to Nonsense Words?

Recent studies have claimed that large language models (LLMs) are capable of drawing pragmatic inferences (Qiu et al., 2023; Hu et al., 2022; Barattieri di San Pietro et al., 2023). The present paper sets out to test LLM's abilities on atypicality inferences, a type of pragmatic inference that is triggered through informational redundancy. We test several state-of-the-art LLMs in a zero-shot setting and find that LLMs fail to systematically fail to derive atypicality inferences. Our robustness analysis indicates that when inferences are seemingly derived in a few-shot settings, these results can be attributed to shallow pattern matching and not pragmatic inferencing. We also analyse the performance of the LLMs at the different derivation steps required for drawing atypicality inferences – our results show that models have access to script knowledge and can use it to identify redundancies and accommodate the atypicality inference. The failure instead seems to stem from not reacting to the subtle maxim of quantity violations introduced by the informationally redundant utterances.

Large language models fail to derive atypicality inferences in a human-like manner

Large language models have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy) recordings of activations during listening or reading, from which we can extract similar representations of words and phrases. Here we study the extent to which the geometries induced by these representations, share similarities in the context of brain decoding. We find that the larger neural language models get, the more their representations are structurally similar to neural response measurements from brain imaging.

Premium content

Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modeling

Next from ACL 2024

Exploring Sound Change Over Time: A Review of Computational and Human Perception

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES