computational-linguistics
Filtering by topic computational-linguistics(3)Clear all filters
- PaperarXiv — Language & NLP (cs.CL)13 Jul 2026
Globally Consistent Coloring Schemes for Language Identification
Moses Charikar, Jon Kleinberg, Chirag Pabbaraju
The paper shows that a single terminal bit per string is sufficient to identify any countable collection of infinite languages in Gold's language identification model. The authors construct a global two-color terminal coloring using transfinite recursion, but prove that no Borel-definable finite coloring can achieve the same result.
Original abstract
We study how little extra information is needed to make adversarial language learning possible. In Gold's model of language identification in the limit, a learner is given an enumeration of the strings from an unknown language chosen from a countable language collection. The learner guesses the identity of the language over the course of the enumeration, and it succeeds if, eventually, all of its guesses are the correct language. Classical results of Gold and Angluin show that many natural collections cannot be learned in this way. Recent work on trace colorings, motivated by the success of thinking-trace strategies in language learning, overcomes this obstruction by annotating every symbol of every string with a color. We ask whether the learner really needs this whole sequence of colors, or whether one color at the end of each string (a terminal coloring) is enough for language identification. We show that just one terminal bit per string is enough for every countable collection of infinite languages. In fact, the colorings can be chosen collection-independently: there is a single assignment of a two-color terminal coloring to every infinite language such that the same preassigned colorings identify every countable subcollection. Thus, in this model, an entire color trace can be compressed to one bit attached to the end of each example. Our global construction uses transfinite recursion, and we prove that this kind of nonconstructivity is unavoidable for any bounded number of colors. As a notion of constructivity, we use the formalism of Borel maps (a regularity condition satisfied by natural explicit constructions); we show that no global terminal coloring with a finite number of colors defined by a Borel map can identify all countable subcollections. By contrast, known trace-coloring constructions are Borel when encoded as terminal colorings, but require infinitely many colors.
- PaperarXiv — Language & NLP (cs.CL)17 Jun 2026
Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition
Shiho Matta, Yin Jou Huang, Fei Cheng, Takashi Kodama et al.
A new 1.8B-parameter large language model called Dango was developed to study L1-to-L2 (Japanese-to-English) transfer in second language acquisition. The model uses a filtering method to remove English contamination from its Japanese-only pretraining corpus, then fine-tunes on LLM-generated L2 lessons. Evaluations show Dango produces human-like L2 production patterns, outperforming unfiltered and multilingual baselines.
Original abstract
We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA). While previous studies have explored SLA in language models, they have predominantly relied on smaller or non-decoder models, limiting their ability to generate open-ended text and reducing their suitability as practical L2 simulators. We identify a key challenge when scaling models to this size: L2 contamination within the "monolingual" pretraining corpus used for L1 acquisition. To address this, we propose a filtering method to reduce premature exposure to English while preserving realistic, minimal exposure. We then fine-tune the model on LLM-generated L2-learning lessons to simulate the L2 acquisition process. Our evaluations confirm that Dango develops human-like L2 production patterns, outperforming both unfiltered and standard multilingual baselines. We release the model, data, and code to facilitate reproducible computational SLA research and learner-facing applications.
- PaperarXiv — Language & NLP (cs.CL)12 May 2026
Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition
Francesca Padovani, Jaap Jumelet, Yevgen Matusevych, Arianna Bisazza
Using neural language models trained on child-directed versus adult-directed language, researchers found that verb meaning acquisition is more resilient to syntactic disruption in spoken language, especially child-directed speech, but the advantage is largely attributable to the spoken register rather than unique properties of child-directed language.
Original abstract
Is child-directed language (CDL) optimized to support language learning, and which aspects of linguistic development does it facilitate? We investigate this question using neural language models trained on CDL versus adult-directed language (ADL). We selectively remove syntactic or lexical co-occurrence information from the model training data, and evaluate the impact of these manipulations on verb meaning acquisition. While disrupting syntax impairs learning across all datasets, models trained on CDL and spoken ADL show significantly higher resilience than those trained on written input. Tracking semantic and syntactic performance over training, we observe a semantic-first trajectory, with verb meanings emerging prior to robust syntactic proficiency, an asynchrony most pronounced in the spoken domain, especially CDL. These results suggest that the advantage for verb learning previously attributed to CDL may instead reflect broader properties of the spoken register, rather than a uniquely CDL-specific optimization.