A systematic investigation of learnability from single child linguistic input
Center for Data Science（数据科学中心）；New York University（纽约大学）
Yulu Qin, Wentao Wang, Brenden M. Lake
备注：
Please cite as Qin, Y., Wang, W., and Lake, B. M. (2024). A systematic investigation of learnability from single child linguistic input. In Proceedings of the 46th Annual Conference of the Cognitive Science Society
Language models (LMs) have demonstrated remarkable proficiency in generating linguistically coherent text, sparking discussions about their relevance to understanding human language learnability. However, a significant gap exists between the training data for these models and the linguistic input a child receives. LMs are typically trained on data that is orders of magnitude larger and fundamentally different from child-directed speech (Warstadt and Bowman, 2022; Warstadt et al., 2023; Frank, 2023a). Addressing this discrepancy, our research focuses on training LMs on subsets of a single child's linguistic input. Previously, Wang, Vong, Kim, and Lake (2023) found that LMs trained in this setting can form syntactic and semantic word clusters and develop sensitivity to certain linguistic phenomena, but they only considered LSTMs and simpler neural networks trained from just one single-child dataset. Here, to examine the robustness of learnability from single-child input, we systematically train six different model architectures on five datasets (3 single-child and 2 baselines). We find that the models trained on single-child datasets showed consistent results that matched with previous work, underscoring the robustness of forming meaningful syntactic and semantic representations from a subset of a child's linguistic input.
Employing self-supervised learning models for cross-linguistic child speech maturity classification
Dept. of Computer Science, UCLA, USA（UCLA计算机科学系）；Dept. of Linguistics, UCLA, USA（UCLA语言学系）；Dept. of Linguistics, Stanford University, USA（斯坦福大学语言学系）；Dept. of Communication, UCLA, USA（UCLA传播学系）；Department of Computer Science George Washington University, USA（乔治华盛顿大学计算机科学系）；Département d’études cognitives, ENS, France（法兰西综合理工学院认知研究系）
Assessing the alignment between infants' visual and linguistic experience using multimodal language models
Department of Psychology, Stanford University（心理学系，斯坦福大学）；Department of Psychology, University of California, San Diego（心理学系，加州大学圣地亚哥分校）；Department of Psychology, Tsinghua University（心理学系，清华大学）
Speech directed to children differs from adult-directed speech in linguistic aspects such as repetition, word choice, and sentence length, as well as in aspects of the speech signal itself, such as prosodic and phonemic variation. Human language acquisition research indicates that child-directed speech helps language learners. This study explores the effect of child-directed speech when learning to extract semantic information from speech directly. We compare the task performance of models trained on adult-directed speech (ADS) and child-directed speech (CDS). We find indications that CDS help…
MIT（麻省理工学院）；Duke University（杜克大学）；University of Chicago（芝加哥大学）
How do adults understand children's speech? Children's productions over the course of language development often bear little resemblance to typical adult pronunciations, yet caregivers nonetheless reliably recover meaning from them. Here, we employ a suite of Bayesian models of spoken word recognition to understand how adults overcome the noisiness of child language, showing that communicative success between children and adults relies heavily on adult inferential processes. By evaluating competing models on phonetically-annotated corpora, we show that adults' recovered meanings are best predi…
University of Washington（华盛顿大学）；University of Colorado（科罗拉多大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
While recurrent neural networks have found success in a variety of natural language processing applications, they are general models of sequential data. We investigate how the properties of natural language data affect an LSTM's ability to learn a nonlinguistic task: recalling elements from its input. We find that models trained on natural language data are able to recall tokens from much longer sequences than models trained on non-language sequential data. Furthermore, we show that the LSTM learns to solve the memorization task by explicitly using a subset of its neurons to count timesteps in…
Evaluating LLMs on Generating Age-Appropriate Child-Like Conversations
Department of Holistic Systems, SimulaMet（整体系统系，SimulaMet）；Department of Computer Science, Oslo Metropolitan University（计算机科学系，奥斯陆 Metropolitan 大学）；Department of Behavioural Sciences, Oslo Metropolitan University（行为科学系，奥斯陆 Metropolitan 大学）；Department of Psychology, Harvard University（心理学系，哈佛大学）；Department of Informatics, University of Oslo（信息学系，奥斯陆大学）；Norwegian Computing Center（挪威计算中心）
NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication
Faculty of Electronic and Information Engineering, Xi’an Jiaotong University（西安交通大学电子与信息工程学院）；Leiden Institute of Advanced Computer Science, Leiden University（莱顿大学高级计算机科学研究所）；Center for Language and Cognition, University of Groningen（格罗宁根大学语言与认知中心）
Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
University of Chinese Academy of Sciences（中国科学院大学）；Department of Computer Science, University of California Santa Barbara（加州大学圣塔芭芭拉分校计算机科学系）；WeChat Search Application Department, Tencent（腾讯微信搜索应用部）
Massachusetts Institute of Technology（麻省理工学院）；University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）
Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received linguistic input, robust spoken word recognition -- and language processing more generally -- relies heavily on listeners' prior knowledge to evaluate whether candidate interpretations of that input are more or less likely. Here we compare several broad-coverage probabilistic generative language models in their ability to capture human linguistic expectations. Serial reproductio…
University of Edinburgh（爱丁堡大学）；University of New Mexico（新墨西哥大学）
Languages emerge and change over time at the population level though interactions between individual speakers. It is, however, hard to directly observe how a single speaker's linguistic innovation precipitates a population-wide change in the language, and many theoretical proposals exist. We introduce a very general mathematical model that encompasses a wide variety of individual-level linguistic behaviours and provides statistical predictions for the population-level changes that result from them. This model allows us to compare the likelihood of empirically-attested changes in definite and i…
Learning and communication pressures in neural networks: Lessons from emergent communication
Centre for Machine Learning（机器学习中心）；University of Southern Denmark (SDU)（南丹麦大学）；Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所）；University of Glasgow（格拉斯哥大学）
BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories
School of Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程学院，中国沈阳）；NiuTrans Research, Shenyang, China（NiuTrans研究院，中国沈阳）
Johns Hopkins University（约翰斯·霍普金斯大学）；Yale University（耶鲁大学）；New York University（纽约大学）
Relations between words are governed by hierarchical structure rather than linear ordering. Sequence-to-sequence (seq2seq) models, despite their success in downstream NLP applications, often fail to generalize in a hierarchy-sensitive manner when performing syntactic transformations - for example, transforming declarative sentences into questions. However, syntactic evaluations of seq2seq models have only observed models that were not pre-trained on natural language data before being trained to perform syntactic transformations, in spite of the fact that pre-training has been found to induce h…
This paper presents BAMBI (BAby language Models Boostrapped for Italian), a series of Baby Language Models (BabyLMs) trained on data that mimic the linguistic input received by a five-year-old Italian-speaking child. The BAMBI models are tested using a benchmark specifically designed to evaluate language models, which takes into account the amount of training input the models received. The BAMBI models are compared against a large language model (LLM) and a multimodal language model (VLM) to study the contribution of extralinguistic information for language acquisition. The results of our eval…
