Papers with language acquisition
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) (N18-2)
Copied to clipboard
| Challenge: | NAACL HLT 2018 is the biggest NAAPL conference to date . this year's conference highlights the vibrancy and vitality of the field . |
| Approach: | a new review form and an opportunity for authors to review the reviewers were introduced at this year's conference . the test-of-time awards are named in memory of Aravind Joshi, who died this year . |
| Outcome: | the biggest NAACL conference to date features a new review form and the Test-of-Time awards . the industrial track features papers that focus on scalable, interpretable, reliable and customer facing methods for industrial applications . |
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) (N18-1)
Copied to clipboard
| Challenge: | NAACL HLT 2018 is the biggest NAAPL conference to date . this year's conference highlights the vibrancy and vitality of the field . |
| Approach: | a new review form and an opportunity for authors to review the reviewers were introduced at this year's conference . the test-of-time awards are named in memory of Aravind Joshi, who died this year . |
| Outcome: | the biggest NAACL conference to date features a new review form and the Test-of-Time awards . the industrial track features papers that focus on scalable, interpretable, reliable and customer facing methods for industrial applications . |
Word Acquisition in Neural Language Models (2022.tacl-1)
Copied to clipboard
| Challenge: | Language models acquire individual words during training, based on unigram token frequencies, before transitioning loosely to bigram probabilities, eventually converging on more nuanced predictions. |
| Approach: | They examine how neural language models acquire individual words during training, extracting learning curves and ages of acquisition for over 600 words on the MacArthur-Bates Communicative Development Inventory. |
| Outcome: | The models follow consistent patterns during training for both unidirectional and bidirectional models, and for both LSTM and Transformer architectures. |
Beyond the Gold Standard in Analytic Automated Essay Scoring (2025.acl-srw)
Copied to clipboard
| Challenge: | Automated Essay Scoring (AES) is a new approach to assessing writing practice . traditional holistic scoring methods are not reliable and lack formative feedback in the classroom. |
| Approach: | They propose to combine analytic and holistic AES to create a system that learns from individual raters instead of gold standard labels. |
| Outcome: | The proposed system learns from individual raters instead of gold standard labels. |
Language Acquisition through Intention Reading and Pattern Finding (2022.coling-1)
Copied to clipboard
| Challenge: | a faithful computational operationalisation of the underlying mechanisms is still lacking. |
| Approach: | They propose a mechanistic model of intention reading and its integration with pattern finding capacities to model the intention reading process and their model of pattern finding. |
| Outcome: | The proposed model integrates intention reading and pattern finding processes with linguistic schemata that generalise over form and meaning. |
Investigating Critical Period Effects in Language Acquisition through Neural Language Models (2025.tacl-1)
Copied to clipboard
| Challenge: | Scholars of human development have long debated whether these phenomena are predetermined by innately encoded developmental changes in the maturing brain or natural consequences of increased experience. |
| Approach: | They use language models to test whether CP effects are peculiar to humans . they find that LMs do not show CP when L2 exposure is delayed . scholars have long debated whether innate maturation changes predetermine CP . |
| Outcome: | The proposed model does not show CP effects when the age of exposure of L2 is delayed. |
Language Learning and Processing in People and Machines (N19-5)
Copied to clipboard
| Challenge: | This tutorial introduces different stages of language acquisition and their parallel problems in NLP. |
| Approach: | This tutorial introduces different stages of language acquisition and their parallel problems in NLP. |
| Outcome: | This tutorial introduces different stages of language acquisition and their parallel problems in NLP. |
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders (N19-1)
Copied to clipboard
| Challenge: | Xitsonga and English are typologically unrelated languages . phonological features are not directly observed by humans . |
| Approach: | They deploy binary stochastic neural autoencoder networks as models of infant language learning in two typologically unrelated languages. |
| Outcome: | The proposed model is well represented in both languages, while others are less so. |
Using Classifier Features to Determine Language Transfer on Morphemes (N18-4)
Copied to clipboard
| Challenge: | Using native English data, we identify an English learner’s native language background based solely on the learner's English writing samples. |
| Approach: | They perform a Native Language Identification task where they identify an English learner’s native language background based only on the learner's English writing samples. |
| Outcome: | The proposed task is connected to a position in second language acquisition research that holds all learners acquire English grammatical morphemes in the same order, regardless of native language background. |
Automatically Suggesting Diverse Example Sentences for L2 Japanese Learners Using Pre-Trained Language Models (2024.acl-srw)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are used to produce examples sentences targeting L2 learners. |
| Approach: | They propose to use pre-trained language models to produce diverse examples of Japanese sentences that are aligned with learners’ proficiency levels. |
| Outcome: | The proposed method is adaptable to other languages with minor adjustments. |
A Visuospatial Dataset for Naturalistic Verb Learning (2020.starsem-1)
Copied to clipboard
| Challenge: | a new dataset is available for training and evaluating grounded language models . our data is designed to emulate the quality of language data a pre-verbal child would have access to . |
| Approach: | They propose a dataset for training and evaluating grounded language models . they use naturalistic, spontaneous speech paired with richly grounded visuospatial context . |
| Outcome: | The proposed dataset compares two distributional semantics models with one that does not. |
Learning a Grammar Inducer from Massive Uncurated Instructional Videos (2022.emnlp-main)
Copied to clipboard
| Challenge: | aims to find more accurate syntactic grammars for accompanying text using video data. |
| Approach: | They build a video-aided grammar induction model that can learn video-span correlation without manual features. |
| Outcome: | The proposed model can learn video-span correlation without manual features adopted by previous systems. |
Aligning Sentence Simplification with ESL Learner’s Proficiency for Language Acquisition (2025.naacl-long)
Copied to clipboard
| Challenge: | Text simplification is crucial for improving accessibility and comprehension for English as a Second Language (ESL) learners. |
| Approach: | They propose to simplify complex sentences to appropriate levels while also increasing vocabulary coverage of the target level. |
| Outcome: | The proposed method can increase frequency and diversity of vocabulary of the target level by more than 20% compared to baseline models, while maintaining high simplification quality. |
Grounding as a Collaborative Process (2021.eacl-main)
Copied to clipboard
| Challenge: | a new study shows that dialog requires a collaborative grounding approach to ground meaning . the problem is that dialog partners are not able to ground themselves . |
| Approach: | They argue that it is missing from current deep learning approaches to dialog . they argue that making mistakes and being able to recover from them is key . |
| Outcome: | The proposed model is based on the language acquisition and dialog systems literature . it shows that making mistakes and being able to recover from them is key . |
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes (2024.naacl-long)
Copied to clipboard
| Challenge: | Modern neural language models (LMs) require distinctly un-human-like ways to achieve these results. |
| Approach: | They train a diverse set of LM architectures with and without auxiliary visual supervision on datasets of varying scales. |
| Outcome: | The proposed models exhibit better learning of syntactic categories, lexical relations, semantic features, word similarity and alignment with human neural representations. |
A Framework for Representing Language Acquisition in a Population Setting (P18-1)
Copied to clipboard
| Challenge: | Existing approaches to model language acquisition and social structure are ineffective because nobody can travel back in time or fit entire natural environments into a lab. |
| Approach: | They propose a new analytic framework which combines previous network models' ability to capture realistic social structure with more elegant computational properties. |
| Outcome: | The proposed framework is able to capture real social structure and integrate with existing models while being modular and extensible. |
Does Vision Accelerate Hierarchical Generalization in Neural Language Learners? (2025.coling-main)
Copied to clipboard
| Challenge: | Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective. |
| Approach: | They investigate the advantage of grounded language acquisition over visual input to improve syntactic generalization. |
| Outcome: | The proposed model is less efficient than humans in language acquisition . it shows that visual input helps syntactic generalization, but not vision . |
Visually Grounded Continual Learning of Compositional Phrases (2020.emnlp-main)
Copied to clipboard
| Challenge: | Modern NLP systems rely on offline training and are inefficient for new tasks. |
| Approach: | They propose a visually grounded ContinuaL learning task which simulates the continual acquisition of compositional phrases from streaming visual scenes. |
| Outcome: | The proposed system improves on existing systems, but it's infeasible to store all possible compositions. |
Automatic Annotation of Grammaticality in Child-Caregiver Conversations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for analyzing child language acquisition have been tedious and inconsistent. |
| Approach: | They propose a coding scheme for context-dependent grammaticality in child-caregiver conversations and annotate 4,000 utterances from a large corpus of transcribed conversations. |
| Outcome: | The proposed method achieves human inter-annotation agreement levels and is faster and reproducible than manual methods. |
A Computational Acquisition Model for Multimodal Word Categorization (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent advances in self-supervised modeling of text and images open new opportunities for computational models of child language acquisition. |
| Approach: | They propose a multimodal language acquisition model trained from image-caption pairs on naturalistic data using cross-modal self-supervision. |
| Outcome: | The proposed model learns word categories and object recognition abilities, the authors show . their model is trained from image-caption pairs on naturalistic data using cross-modal self-supervision . |
IndoCL: Benchmarking Indonesian Language Development Assessment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent interest has surged in applying natural language processing (NLP) and machine learning (ML) to evaluate language development in both first (L1) and second (L2) language acquisition. |
| Approach: | They propose to use an Indonesian corpus as a benchmark for LDA tasks and to use existing large-scale language models to improve performance. |
| Outcome: | The proposed model extracts language-independent features, relieving laborious computation and reliance on specific language. |
Grounding language acquisition by training semantic parsers using captioned videos (D18-1)
Copied to clipboard
| Challenge: | a new method for parsing sentences using captioned videos is being developed . we use video clips to ground the semantics of language, but without annotations . |
| Approach: | They develop a semantic parser that is trained in a grounded setting using captioned videos . they use a corpus of sentences paired with videos without other annotations to train it . |
| Outcome: | The proposed parser recovers the meaning of English sentences despite no annotations . learning a grounded semantic parsers can expand the range of data that parseurs can be trained on . |
Action Verb Corpus (L18-1)
Copied to clipboard
| Challenge: | a corpus of 390 simple actions is based on multimodal data of 12 humans . the dataset is annotated with orthographic transcriptions of utterances and part-of-speech tags . |
| Approach: | They present a multimodal corpus of 12 humans performing 390 simple actions . they also propose an algorithm for segmenting words into utterances and aligning visual information and speech . |
| Outcome: | The presented dataset includes 390 simple actions performed by 12 humans . it includes transcriptions of utterances, part-of-speech tags, lemmata, and hand touches . |
Automatically Building a Multilingual Lexicon of False Friends With No Supervision (2020.lrec-1)
Copied to clipboard
| Challenge: | a method to detect false friends from cognates is developed . cognates are words in genetically related languages with a common proto-word . in some cases, cognates have diverged from the common etymon and their meanings became different from each other. |
| Approach: | They propose an automatic method to detect false friends from a set of cognates . cognates are words in genetically related languages which derive from etymons . authors propose a measure of "falseness" of a false friends pair based on cross-lingual word embeddings based in the system . |
| Outcome: | The proposed method can be extended to any language pair, with monolingual corpora and a bilingual dictionary. |
Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on LMs have focused on linguistic generalizations and representations from developmentally plausible data. |
| Approach: | They propose to use phoneme- and grapheme-based language models to learn linguistic units at and below the word level. |
| Outcome: | The proposed models can achieve strong performance on syntactic and novel benchmarks and match grapheme-based models in standard tasks and novel evaluations. |
Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models possess general linguistic abilities comparable to humans but their efficiency in language acquisition remains far inferior. |
| Approach: | They propose a method that initially constrains working memory during the early stages of training and gradually relaxes this constraint as learning progresses. |
| Outcome: | The proposed method outperforms conventional methods without memory constraints or with static memory constraints. |
Transformer-based Speech Model Learns Well as Infants and Encodes Abstractions through Exemplars in the Poverty of the Stimulus Environment (2025.coling-main)
Copied to clipboard
| Challenge: | Existing theories of language learning for infants are inadequate, according to Chomsky . infants learn language in impoverished environments, according a new study . |
| Approach: | They designed a series of tasks, scenarios, and metrics to simulate the POS . they found that the emerging speech model wav2vec2.0 can learn well in noisy Mandarin environments. |
| Outcome: | The proposed model can learn in noisy and sparse Mandarin environments. |
Semantic Parsing for English as a Second Language (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies on domain adaptation in NLP focus on learning challenges at the syntax-semantics interface during second language acquisition. |
| Approach: | They propose to use English Resource Grammar and TLE to parse ESL data using a reranking model to evaluate the quality of the annotations. |
| Outcome: | The proposed model can obtain a very promising quality in comparison to human annotations. |
SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT (2023.acl-long)
Copied to clipboard
| Challenge: | NLP literature has not given enough attention to the phenomenon of negative transfer . positive transfer refers to the facilitating effects of one language in acquiring another and negative transfer refer to the negative effects between the learner's native [L1] and target [L2] languages. |
| Approach: | They build a Mutlilingual Age Ordered CHILDES dataset to understand the degree to which native Child-Directed Speech (CDS) can help or conflict with English language acquisition. |
| Outcome: | The proposed model enables us to understand the degree to which native Child-Directed Speech (CDS) can help or conflict with English language acquisition. |
Searching for Structure: Investigating Emergent Communication with Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Human languages have evolved to be structured through repeated language learning and use. |
| Approach: | They propose to use large language models to optimise for implicit biases that shape languages to improve communicative efficiency. |
| Outcome: | The proposed models can be used to study language evolution and open possibilities for human-machine interactions. |
Language acquisition: do children and language models follow similar learning stages? (2023.findings-acl)
Copied to clipboard
| Challenge: | During language acquisition, children follow a typical sequence of learning stages, whereby they first learn to categorize phonemes before they develop their lexicon and eventually master complex syntactic structures. |
| Approach: | They train 48 GPT-2 models from scratch and evaluate their syntactic and semantic abilities at each training step using 96 probes curated from the BLiMP, Zorro and BIG-Bench benchmarks. |
| Outcome: | The proposed model exhibits similar learning trajectories to human children aged between 18 months and 6 years. |
Second Language Acquisition of Neural Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | a recent study examined the cross-lingual transferability of neural language models . previous studies focused on their first language acquisition . |
| Approach: | They propose to pretrain bilingual LMs with a scenario similar to human L2 acquisition . they find that pretraining accelerated their linguistic generalization in L2 . |
| Outcome: | The results show that pretraining bilingual LMs accelerates their linguistic generalizations . the results clarify their (non-)human-like L2 acquisition in particular aspects . |
Modeling Overregularization in Children with Small Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing research has analyzed regularization in language acquisition only by modeling word inflection directly, which is unnatural in light of human language acquisition. |
| Approach: | They hypothesize that language models that imitate errors children make during language acquisition have a learning process more similar to humans. |
| Outcome: | The proposed model shows child-like U-shaped learning curves clearly for certain verbs, but the preferences for types of overgeneralization did not fully match the observations in children. |
Learning Bidirectional Morphological Inflection like Humans (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent research has focused on whether neural models can acquire morphological inflection like humans. |
| Approach: | They propose to use a recurrent neural network with attention and the transformer to train a symbolic model under a human-like learning environment to evaluate their models. |
| Outcome: | The proposed models did not accurately inflect verbs in the same manner as humans in terms of morphological inflection direction. |
Can Language Models Induce Grammatical Knowledge from Indirect Evidence? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in language models have shown remarkable progress in various tasks. |
| Approach: | They introduce a dataset that incorporates wug words and inject them into pretraining data and evaluate them on evaluation data. |
| Outcome: | The proposed model does not induce grammatical knowledge even after repeated exposure to instances with the same structure but differing only in lexical items from evaluation instances in certain language phenomena. |
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)
Copied to clipboard
Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang
| Challenge: | Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand. |
| Approach: | They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages. |
| Outcome: | Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages. |
Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints? (2026.findings-acl)
Copied to clipboard
| Challenge: | Language models lack language-specific biases, yet still posit some important syntactic generalizations. |
| Approach: | They applied Distributed Alignment Search to checkpoints of a language model from the BabyLM challenge to evaluate whether representations of filler-gap dependencies transfer between wh-questions and topicalization. |
| Outcome: | The results suggest shared, yet item-sensitive mechanisms may develop with limited training data. |