David R. Mortensen

Nathaniel R. Robinson, Perez Ogayo, David R. Mortensen et al. · cmu

Large language models (LLMs) implicitly learn to perform a range of language tasks, including machine translation (MT). Previous studies explore aspects of LLMs' MT capabilities. However, there exist a wide variety of languages for which recent LLM MT performance has never before been evaluated. Without published experimental evidence on the matter, it is difficult for speakers of the world's diverse languages to know how and whether they can use LLMs for their languages. We present the first experimental evidence for an expansive set of 204 languages, along with MT cost analysis, using the FLORES-200 benchmark. Trends reveal that GPT models approach or exceed traditional MT model performance for some high-resource languages (HRLs) but consistently lag for low-resource languages (LRLs), under-performing traditional MT for 84.1% of languages we covered. Our analysis reveals that a language's resource level is the most important feature in determining ChatGPT's relative ability to translate it, and suggests that ChatGPT is especially disadvantaged for LRLs and African languages.

Xinjian Li, Florian Metze, David R Mortensen et al. · cmu

Most recent speech recognition models rely on large supervised datasets, which are unavailable for many low-resource languages. In this work, we present a speech recognition pipeline that does not require any audio for the target language. The only assumption is that we have access to raw text datasets or a set of n-gram statistics. Our speech pipeline consists of three components: acoustic, pronunciation, and language models. Unlike the standard pipeline, our acoustic and pronunciation models use multilingual models without any supervision. The language model is built using n-gram statistics or the raw text dataset. We build speech recognition for 1909 languages by combining it with Crubadan: a large endangered languages n-gram database. Furthermore, we test our approach on 129 languages across two datasets: Common Voice and CMU Wilderness dataset. We achieve 50% CER and 74% WER on the Wilderness dataset with Crubadan statistics only and improve them to 45% CER and 69% WER when using 10000 raw text utterances.

Kalvin Chang, Yi-Hui Chou, Jiatong Shi et al. · cmu

Underperformance of ASR systems for speakers of African American Vernacular English (AAVE) and other marginalized language varieties is a well-documented phenomenon, and one that reinforces the stigmatization of these varieties. We investigate whether or not the recent wave of Self-Supervised Learning (SSL) speech models can close the gap in ASR performance between AAVE and Mainstream American English (MAE). We evaluate four SSL models (wav2vec 2.0, HuBERT, WavLM, and XLS-R) on zero-shot Automatic Speech Recognition (ASR) for these two varieties and find that these models perpetuate the bias in performance against AAVE. Additionally, the models have higher word error rates on utterances with more phonological and morphosyntactic features of AAVE. Despite the success of SSL speech models in improving ASR for low resource varieties, SSL pre-training alone may not bridge the gap between AAVE and MAE. Our code is publicly available at https://github.com/cmu-llab/s3m-aave.

Young Min Kim, Kalvin Chang, Chenxuan Cui et al. · cmu

Protoform reconstruction is the task of inferring what morphemes or words appeared like in the ancestral languages of a set of daughter languages. Meloni et al. (2021) achieved the state-of-the-art on Latin protoform reconstruction with an RNN-based encoder-decoder with attention model. We update their model with the state-of-the-art seq2seq model: the Transformer. Our model outperforms their model on a suite of different metrics on two different datasets: their Romance data of 8,000 cognates spanning 5 languages and a Chinese dataset (Hou 2004) of 800+ cognates spanning 39 varieties. We also probe our model for potential phylogenetic signal contained in the model. Our code is publicly available at https://github.com/cmu-llab/acl-2023.

Nathaniel Robinson, Perez Ogayo, Swetha Gangu et al. · cmu

Developing Automatic Speech Recognition (ASR) for low-resource languages is a challenge due to the small amount of transcribed audio data. For many such languages, audio and text are available separately, but not audio with transcriptions. Using text, speech can be synthetically produced via text-to-speech (TTS) systems. However, many low-resource languages do not have quality TTS systems either. We propose an alternative: produce synthetic audio by running text from the target language through a trained TTS system for a higher-resource pivot language. We investigate when and how this technique is most effective in low-resource settings. In our experiments, using several thousand synthetic TTS text-speech pairs and duplicating authentic data to balance yields optimal results. Our findings suggest that searching over a set of candidate pivot languages can lead to marginal improvements and that, surprisingly, ASR performance can by harmed by increases in measured TTS quality. Application of these findings improves ASR by 64.5\% and 45.0\% character error reduction rate (CERR) respectively for two low-resource languages: Guaraní and Suba.

Leonie Weissweiler, Taiqi He, Naoki Otani et al. · cmu

Construction Grammar (CxG) has recently been used as the basis for probing studies that have investigated the performance of large pretrained language models (PLMs) with respect to the structure and meaning of constructions. In this position paper, we make suggestions for the continuation and augmentation of this line of research. We look at probing methodology that was not designed with CxG in mind, as well as probing methodology that was designed for specific constructions. We analyse selected previous work in detail, and provide our view of the most important challenges and research questions that this promising new field faces.

Leonie Weissweiler, Valentin Hofmann, Anjali Kantharuban et al. · cmu, oxford

Large language models (LLMs) have recently reached an impressive level of linguistic capability, prompting comparisons with human language skills. However, there have been relatively few systematic inquiries into the linguistic capabilities of the latest generation of LLMs, and those studies that do exist (i) ignore the remarkable ability of humans to generalize, (ii) focus only on English, and (iii) investigate syntax or semantics and overlook other capabilities that lie at the heart of human language, like morphology. Here, we close these gaps by conducting the first rigorous analysis of the morphological capabilities of ChatGPT in four typologically varied languages (specifically, English, German, Tamil, and Turkish). We apply a version of Berko's (1958) wug test to ChatGPT, using novel, uncontaminated datasets for the four examined languages. We find that ChatGPT massively underperforms purpose-built systems, particularly in English. Overall, our results -- through the lens of morphology -- cast a new light on the linguistic capabilities of ChatGPT, suggesting that claims of human-like language skills are premature and misleading.

Aditi Chaudhary, Zaid Sheikh, David R Mortensen et al. · cmu

Each language has its own complex systems of word, phrase, and sentence construction, the guiding principles of which are often summarized in grammar descriptions for the consumption of linguists or language learners. However, manual creation of such descriptions is a fraught process, as creating descriptions which describe the language in "its own terms" without bias or error requires both a deep understanding of the language at hand and linguistics as a whole. We propose an automatic framework AutoLEX that aims to ease linguists' discovery and extraction of concise descriptions of linguistic phenomena. Specifically, we apply this framework to extract descriptions for three phenomena: morphological agreement, case marking, and word order, across several languages. We evaluate the descriptions with the help of language experts and propose a method for automated evaluation when human evaluation is infeasible.

Yanlin Feng, Adithya Pratapa, David R Mortensen · cmu

Ultra-fine entity typing plays a crucial role in information extraction by predicting fine-grained semantic types for entity mentions in text. However, this task poses significant challenges due to the massive number of entity types in the output space. The current state-of-the-art approaches, based on standard multi-label classifiers or cross-encoder models, suffer from poor generalization performance or inefficient inference. In this paper, we present CASENT, a seq2seq model designed for ultra-fine entity typing that predicts ultra-fine types with calibrated confidence scores. Our model takes an entity mention as input and employs constrained beam search to generate multiple types autoregressively. The raw sequence probabilities associated with the predicted types are then transformed into confidence scores using a novel calibration method. We conduct extensive experiments on the UFET dataset which contains over 10k types. Our method outperforms the previous state-of-the-art in terms of F1 score and calibration error, while achieving an inference speedup of over 50 times. Additionally, we demonstrate the generalization capabilities of our model by evaluating it in zero-shot and few-shot settings on five specialized domain entity typing datasets that are unseen during training. Remarkably, our model outperforms large language models with 10 times more parameters in the zero-shot setting, and when fine-tuned on 50 examples, it significantly outperforms ChatGPT on all datasets. Our code, models and demo are available at https://github.com/yanlinf/CASENT.

Vilém Zouhar, Kalvin Chang, Chenxuan Cui et al. · cmu, eth-zurich

Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop three methods that use articulatory features to build phonetically informed word embeddings. To address the inconsistent evaluation of existing phonetic word embedding methods, we also contribute a task suite to fairly evaluate past, current, and future methods. We evaluate both (1) intrinsic aspects of phonetic word embeddings, such as word retrieval and correlation with sound similarity, and (2) extrinsic performance on tasks such as rhyme and cognate detection and sound analogies. We hope our task suite will promote reproducibility and inspire future phonetic embedding research.

Brendon Boldt, David Mortensen · cmu

We introduce the Emergent Language Corpus Collection (ELCC): a collection of corpora generated from open source implementations of emergent communication systems across the literature. These systems include a variety of signalling game environments as well as more complex environments like a social deduction game and embodied navigation. Each corpus is annotated with metadata describing the characteristics of the source system as well as a suite of analyses of the corpus (e.g., size, entropy, average message length, performance as transfer learning data). Currently, research studying emergent languages requires directly running different systems which takes time away from actual analyses of such languages, makes studies which compare diverse emergent languages rare, and presents a barrier to entry for researchers without a background in deep learning. The availability of a substantial collection of well-documented emergent language corpora, then, will enable research which can analyze a wider variety of emergent languages, which more effectively uncovers general principles in emergent communication rather than artifacts of particular environments. We provide some quantitative and qualitative analyses with ELCC to demonstrate potential use cases of the resource in this vein.

Nathaniel R. Robinson, Cameron J. Hogan, Nancy Fulda et al. · cmu

Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translation that transfer effectiveness is correlated with amount of training data and relationships between knowledge-sharing languages. Our experiments suggest that for some languages beyond a threshold of authentic data, back-translation augmentation methods are counterproductive, while cross-lingual transfer from a sufficiently related language is preferred. We complement this finding by contributing a rule-based French-Haitian orthographic and syntactic engine and a novel method for phonological embedding. When used with multilingual techniques, orthographic transformation makes statistically significant improvements over conventional methods. And in very low-resource Jamaican MT, code-switching with a transfer language for orthographic resemblance yields a 6.63 BLEU point advantage.

Eunjung Yeo, Julie M. Liss, Visar Berisha et al. · cmu

The growing prevalence of neurological disorders associated with dysarthria motivates the need for automated intelligibility assessment methods that are applicalbe across languages. However, most existing approaches are either limited to a single language or fail to capture language-specific factors shaping intelligibility. We present a multilingual phoneme-production assessment framework that integrates universal phone recognition with language-specific phoneme interpretation using contrastive phonological feature distances for phone-to-phoneme mapping and sequence alignment. The framework yields three metrics: phoneme error rate (PER), phonological feature error rate (PFER), and a newly proposed alignment-free measure, phoneme coverage (PhonCov). Analysis on English, Spanish, Italian, and Tamil show that PER benefits from the combination of mapping and alignment, PFER from alignment alone, and PhonCov from mapping. Further analyses demonstrate that the proposed framework captures clinically meaningful patterns of intelligibility degradation consistent with established observations of dysarthric speech.

Brendon Boldt, David Mortensen · cmu

Emergent language is unique among fields within the discipline of machine learning for its open-endedness, not obviously presenting well-defined problems to be solved. As a result, the current research in the field has largely been exploratory: focusing on establishing new problems, techniques, and phenomena. Yet after these problems have been established, subsequent progress requires research which can measurably demonstrate how it improves on prior approaches. This type of research is what we call systematic research; in this paper, we illustrate this mode of research specifically for emergent language. We first identify the overarching goals of emergent language research, categorizing them as either science or engineering. Using this distinction, we present core methodological elements of science and engineering, analyze their role in current emergent language research, and recommend how to apply these elements.

Brendon Boldt, David Mortensen · cmu

We formulate a stochastic process, FiLex, as a mathematical model of lexicon entropy in deep learning-based emergent language systems. Defining a model mathematically allows it to generate clear predictions which can be directly and decisively tested. We empirically verify across four different environments that FiLex predicts the correct correlation between hyperparameters (training steps, lexicon size, learning rate, rollout buffer size, and Gumbel-Softmax temperature) and the emergent language's entropy in 20 out of 20 environment-hyperparameter combinations. Furthermore, our experiments reveal that different environments show diverse relationships between their hyperparameters and entropy which demonstrates the need for a model which can make well-defined predictions at a precise level of granularity.

Brendon Boldt, David Mortensen · cmu

We introduce FiLex, a self-reinforcing stochastic process which models finite lexicons in emergent language experiments. The central property of FiLex is that it is a self-reinforcing process, parallel to the intuition that the more a word is used in a language, the more its use will continue. As a theoretical model, FiLex serves as a way to both explain and predict the behavior of the emergent language system. We empirically test FiLex's ability to capture the relationship between the emergent language's hyperparameters and the lexicon's Shannon entropy.

Chenxuan Cui, Katherine J. Zhang, David R. Mortensen · cmu

Coordinate compounds (CCs) and elaborate expressions (EEs) are coordinate constructions common in languages of East and Southeast Asia. Mortensen (2006) claims that (1) the linear ordering of EEs and CCs in Hmong, Lahu, and Chinese can be predicted via phonological hierarchies and (2) these phonological hierarchies lack a clear phonetic rationale. These claims are significant because morphosyntax has often been seen as in a feed-forward relationship with phonology, and phonological generalizations have often been assumed to be phonetically "natural". We investigate whether the ordering of CCs and EEs can be learned empirically and whether computational models (classifiers and sequence labeling models) learn unnatural hierarchies similar to those posited by Mortensen (2006). We find that decision trees and SVMs learn to predict the order of CCs/EEs on the basis of phonology, with DTs learning hierarchies strikingly similar to those proposed by Mortensen. However, we also find that a neural sequence labeling model is able to learn the ordering of elaborate expressions in Hmong very effectively without using any phonological information. We argue that EE ordering can be learned through two independent routes: phonology and lexical distribution, presenting a more nuanced picture than previous work. [ISO 639-3:hmn, lhu, cmn]

Shikhar Bharadwaj, Chin-Jou Li, Yoonjae Kim et al.

Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis. Despite prolonged efforts in developing PR systems, current evaluations only measure surface-level transcription accuracy. We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception through intrinsic and extrinsic evaluation of PR systems. PRiSM standardizes transcription-based evaluation and assesses downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. We find that diverse language exposure during training is key to PR performance, encoder-CTC models are the most stable, and specialized PR models still outperform Large Audio Language Models. PRiSM releases code, recipes, and datasets to move the field toward multilingual speech models with robust phonetic ability: https://github.com/changelinglab/prism.

Brendon Boldt, David Mortensen · cmu

Emergent communication, or emergent language, is the field of research which studies how human language-like communication systems emerge de novo in deep multi-agent reinforcement learning environments. The possibilities of replicating the emergence of a complex behavior like language have strong intuitive appeal, yet it is necessary to complement this with clear notions of how such research can be applicable to other fields of science, technology, and engineering. This paper comprehensively reviews the applications of emergent communication research across machine learning, natural language processing, linguistics, and cognitive science. Each application is illustrated with a description of its scope, an explication of emergent communication's unique role in addressing it, a summary of the extant literature working towards the application, and brief recommendations for near-term research directions.

Maria Ryskina, Matthew R. Gormley, Kyle Mahowald et al. · mit

Living languages are shaped by a host of conflicting internal and external evolutionary pressures. While some of these pressures are universal across languages and cultures, others differ depending on the social and conversational context: language use in newspapers is subject to very different constraints than language use on social media. Prior distributional semantic work on English word emergence (neology) identified two factors correlated with creation of new words by analyzing a corpus consisting primarily of historical published texts (Ryskina et al., 2020, arXiv:2001.07740). Extending this methodology to contextual embeddings in addition to static ones and applying it to a new corpus of Twitter posts, we show that the same findings hold for both domains, though the topic popularity growth factor may contribute less to neology on Twitter than in published writing. We hypothesize that this difference can be explained by the two domains favouring different neologism formation mechanisms.

Brendon Boldt, David Mortensen · cmu

In this paper, we introduce a benchmark for evaluating the overall quality of emergent languages using data-driven methods. Specifically, we interpret the notion of the "quality" of an emergent language as its similarity to human language within a deep learning framework. We measure this by using the emergent language as pretraining data for a downstream NLP tasks in human language -- the better the downstream performance, the better the emergent language. We implement this benchmark as an easy-to-use Python package that only requires a text file of utterances from the emergent language to be evaluated. Finally, we empirically test the benchmark's validity using human, synthetic, and emergent language baselines.

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi et al.

Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly.

David R. Mortensen, Valentina Izrailevitch, Yunze Xiao et al. · cmu

Lexical-syntactic flexibility, in the form of conversion (or zero-derivation) is a hallmark of English morphology. In conversion, a word with one part of speech is placed in a non-prototypical context, where it is coerced to behave as if it had a different part of speech. However, while this process affects a large part of the English lexicon, little work has been done to establish the degree to which language models capture this type of generalization. This paper reports the first study on the behavior of large language models with reference to conversion. We design a task for testing lexical-syntactic flexibility -- the degree to which models can generalize over words in a construction with a non-prototypical part of speech. This task is situated within a natural language inference paradigm. We test the abilities of five language models -- two proprietary models (GPT-3.5 and GPT-4), three open-source models (Mistral 7B, Falcon 40B, and Llama 2 70B). We find that GPT-4 performs best on the task, followed by GPT-3.5, but that the open source language models are also able to perform it and that the 7B parameter Mistral displays as little difference between its baseline performance on the natural language inference task and the non-prototypical syntactic category task, as the massive GPT-4.

Kalvin Chang, Nathaniel R. Robinson, Anna Cai et al. · cmu

We describe a set of new methods to partially automate linguistic phylogenetic inference given (1) cognate sets with their respective protoforms and sound laws, (2) a mapping from phones to their articulatory features and (3) a typological database of sound changes. We train a neural network on these sound change data to weight articulatory distances between phones and predict intermediate sound change steps between historical protoforms and their modern descendants, replacing a linguistic expert in part of a parsimony-based phylogenetic inference algorithm. In our best experiments on Tukanoan languages, this method produces trees with a Generalized Quartet Distance of 0.12 from a tree that used expert annotations, a significant improvement over other semi-automated baselines. We discuss potential benefits and drawbacks to our neural approach and parsimony-based tree prediction. We also experiment with a minimal generalization learner for automatic sound law induction, finding it comparably effective to sound laws from expert annotation. Our code is publicly available at https://github.com/cmu-llab/aiscp.

Atharva Naik, Darsh Agrawal, Hong Sng et al. · cmu

Historical linguists have long written "programs" that convert reconstructed words in an ancestor language into their attested descendants via ordered string rewrite functions (called sound laws) However, writing these programs is time-consuming, motivating the development of automated Sound Law Induction (SLI) which we formulate as Programming by Examples (PBE) with Large Language Models (LLMs) in this paper. While LLMs have been effective for code generation, recent work has shown that PBE is challenging but improvable by fine-tuning, especially with training data drawn from the same distribution as evaluation data. In this paper, we create a conceptual framework of what constitutes a "similar distribution" for SLI and propose four kinds of synthetic data generation methods with varying amounts of inductive bias to investigate what leads to the best performance. Based on the results we create a SOTA open-source model for SLI as PBE (+6% pass rate with a third of the parameters of the second-best LLM) and also highlight exciting future directions for PBE research.

Kwanghee Choi, Eunjung Yeo, Cheol Jun Cho et al.

Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study across 96 languages to analyze the underlying structure of S3M representations, with particular attention to phonological vectors. We first show that there exist linear directions within the model's representation space that correspond to phonological features. We further demonstrate that the scale of these phonological vectors correlate to the degree of acoustic realization of their corresponding phonological features in a continuous manner. For example, the difference between [d] and [t] yields a voicing vector: adding this vector to [p] produces [b], while scaling it results in a continuum of voicing. Together, these findings indicate that S3Ms encode speech using phonologically interpretable and compositional vectors, demonstrating phonological vector arithmetic. All code and interactive demos are available at https://github.com/juice500ml/phonetic-arithmetic .

Atharva Naik, Prakam, Darsh Agrawal et al. · cmu

Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from domain specifics to examine reasoning as a capability in and of itself. We contribute a novel type of benchmark evaluating the inductive reasoning capabilities of LLMs that is inspired by the forward reconstruction task from historical linguistics but is formulated in an extremely simple, general way (in the form of Programming by Examples). The task involves generating a cascade of simple string rewrite programs to transform a given list of input strings into a list of desired output strings. We present a fully automated pipeline that programmatically generates problems of this type with controllable difficulty, enabling scalable evaluation of reasoning models while avoiding contamination. Using this approach, we construct two benchmarks: PBEBench-Lite, which efficiently stratifies models of varying capabilities, and PBEBench, which requires models to induce programs similar in complexity to those constructed by historical linguists. Our experiments reveal a substantial performance gap between models that leverage test-time compute or LCoT (long chain-of-thought) reasoning and those that do not. Moreover, although recent models show promise, the solve rate for both of them drops below 5% for hard instances of the PBEBench dataset (ground truth cascade lengths of 20 and 30, respectively), falling well short of realistic historical linguistics requirements even with computationally expensive, popular scaling techniques from the PBE and reasoning literature. Additionally, we also study the effectiveness of different scaling strategies and the impact of various hyperparameters on the difficulty of the generated data using gpt-oss-120b, the best-performing open-source model.

Jimin Sohn, Haeji Jung, Alex Cheng et al.

Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language, which is impractical for low-resource languages. In this paper, we propose a novel approach to NER using phonemic representation based on the International Phonetic Alphabet (IPA) to bridge the gap between representations of different languages. Our experiments show that our method significantly outperforms baseline models in extremely low-resource languages, with the highest average F1 score (46.38%) and lowest standard deviation (12.67), particularly demonstrating its robustness with non-Latin scripts. Our codes are available at https://github.com/Gabriel819/zeroshot_ner.git

Shijia Zhou, Leonie Weissweiler, Taiqi He et al. · cmu

In this paper, we make a contribution that can be understood from two perspectives: from an NLP perspective, we introduce a small challenge dataset for NLI with large lexical overlap, which minimises the possibility of models discerning entailment solely based on token distinctions, and show that GPT-4 and Llama 2 fail it with strong bias. We then create further challenging sub-tasks in an effort to explain this failure. From a Computational Linguistics perspective, we identify a group of constructions with three classes of adjectives which cannot be distinguished by surface features. This enables us to probe for LLM's understanding of these constructions in various ways, and we find that they fail in a variety of ways to distinguish between them, suggesting that they don't adequately represent their meaning or capture the lexical properties of phrasal heads.

Kwanghee Choi, Eunjung Yeo, Kalvin Chang et al. · cmu

Allophony refers to the variation in the phonetic realization of a phoneme based on its phonetic environment. Modeling allophones is crucial for atypical pronunciation assessment, which involves distinguishing atypical from typical pronunciations. However, recent phoneme classifier-based approaches often simplify this by treating various realizations as a single phoneme, bypassing the complexity of modeling allophonic variation. Motivated by the acoustic modeling capabilities of frozen self-supervised speech model (S3M) features, we propose MixGoP, a novel approach that leverages Gaussian mixture models to model phoneme distributions with multiple subclusters. Our experiments show that MixGoP achieves state-of-the-art performance across four out of five datasets, including dysarthric and non-native speech. Our analysis further suggests that S3M features capture allophonic variation more effectively than MFCCs and Mel spectrograms, highlighting the benefits of integrating MixGoP with S3M features.

Liang Lu, Jingzhi Wang, David R. Mortensen · cmu

Protolanguage reconstruction is central to historical linguistics. The comparative method, one of the most influential theoretical and methodological frameworks in the history of the language sciences, allows linguists to infer protoforms (reconstructed ancestral words) from their reflexes (related modern words) based on the assumption of regular sound change. Not surprisingly, numerous computational linguists have attempted to operationalize comparative reconstruction through various computational models, the most successful of which have been supervised encoder-decoder models, which treat the problem of predicting protoforms given sets of reflexes as a sequence-to-sequence problem. We argue that this framework ignores one of the most important aspects of the comparative method: not only should protoforms be inferable from cognate sets (sets of related reflexes) but the reflexes should also be inferable from the protoforms. Leveraging another line of research -- reflex prediction -- we propose a system in which candidate protoforms from a reconstruction model are reranked by a reflex prediction model. We show that this more complete implementation of the comparative method allows us to surpass state-of-the-art protoform reconstruction methods on three of four Chinese and Romance datasets.

Niyati Bafna, Tianjian Li, Kenton Murray et al.

Multilingual generation with large language models (LLMs) is often of poor quality for mid- to low-resource languages, but the causes for this are not well-understood. We first demonstrate the existence of an implicit task-solving-->translation pipeline for generation, whereby the model first solves the required task in a largely target-language-agnostic manner, and subsequently translates answer concepts into the intended target language. We hypothesize that the failure of the translation stage, despite task-solving success, is an important culprit for the observed low quality of final outputs, and formalize this as the translation barrier hypothesis. We quantify the extent to which either stage in the pipeline is responsible for final failure for a word translation task across 108 language pairs, and find that the translation barrier explains a dominant portion of error for a majority of language pairs, and is especially severe for low-resource target languages. Our results highlight an important bottleneck for end-to-end multilingual generation, relevant for future work seeking to improve multilinguality in LLMs.

Jian Zhu, Farhan Samir, Eleanor Chodroff et al. · cmu

We present ZIPA, a family of efficient speech models that advances the state-of-the-art performance of crosslinguistic phone recognition. We first curated IPAPack++, a large-scale multilingual speech corpus with 17,132 hours of normalized phone transcriptions and a novel evaluation set capturing unseen languages and sociophonetic variation. With the large-scale training data, ZIPA, including transducer (ZIPA-T) and CTC-based (ZIPA-CR) variants, leverage the efficient Zipformer backbones and outperform existing phone recognition systems with much fewer parameters. Further scaling via noisy student training on 11,000 hours of pseudo-labeled multilingual data yields further improvement. While ZIPA achieves strong performance on benchmarks, error analysis reveals persistent limitations in modeling sociophonetic diversity, underscoring challenges for future research.

Valentin Hofmann, Leonie Weissweiler, David Mortensen et al. · cmu, oxford

What mechanisms underlie linguistic generalization in large language models (LLMs)? This question has attracted considerable attention, with most studies analyzing the extent to which the language skills of LLMs resemble rules. As of yet, it is not known whether linguistic generalization in LLMs could equally well be explained as the result of analogical processes, which can be formalized as similarity operations on stored exemplars. A key shortcoming of prior research is its focus on linguistic phenomena with a high degree of regularity, for which rule-based and analogical approaches make the same predictions. Here, we instead examine derivational morphology, specifically English adjective nominalization, which displays notable variability. We introduce a new method for investigating linguistic generalization in LLMs: focusing on GPT-J, we fit cognitive models that instantiate rule-based and analogical learning to the LLM training data and compare their predictions on a set of nonce adjectives with those of the LLM, allowing us to draw direct conclusions regarding underlying mechanisms. As expected, rule-based and analogical models explain the predictions of GPT-J equally well for adjectives with regular nominalization patterns. However, for adjectives with variable nominalization patterns, the analogical model provides a much better match. Furthermore, GPT-J's behavior is sensitive to the individual word frequencies, even for regular forms, a behavior that is consistent with an analogical account of regular forms but not a rule-based one. These findings refute the hypothesis that GPT-J's linguistic generalization on adjective nominalization involves rules, suggesting similarity operations on stored exemplars as the underlying mechanism. Overall, our study suggests that analogical processes play a bigger role in the linguistic generalization of LLMs than previously thought.

Haeji Jung, Changdae Oh, Jooeon Kang et al.

Approaches to improving multilingual language understanding often struggle with significant performance gaps between high-resource and low-resource languages. While there are efforts to align the languages in a single latent space to mitigate such gaps, how different input-level representations influence such gaps has not been investigated, particularly with phonemic inputs. We hypothesize that the performance gaps are affected by representation discrepancies between these languages, and revisit the use of phonemic representations as a means to mitigate these discrepancies. To demonstrate the effectiveness of phonemic representations, we present experiments on three representative cross-lingual tasks on 12 languages in total. The results show that phonemic representations exhibit higher similarities between languages compared to orthographic representations, and it consistently outperforms grapheme-based baseline model on languages that are relatively low-resourced. We present quantitative evidence from three cross-lingual tasks that demonstrate the effectiveness of phonemic representations, and it is further justified by a theoretical analysis of the cross-lingual performance gap.

Chenxuan Cui, Ying Chen, Qinxin Wang et al. · cmu

Proto-form reconstruction has been a painstaking process for linguists. Recently, computational models such as RNN and Transformers have been proposed to automate this process. We take three different approaches to improve upon previous methods, including data augmentation to recover missing reflexes, adding a VAE structure to the Transformer model for proto-to-language prediction, and using a neural machine translation model for the reconstruction task. We find that with the additional VAE structure, the Transformer model has a better performance on the WikiHan dataset, and the data augmentation step stabilizes the training.

Kwanghee Choi, Eunjung Yeo, Cheol Jun Cho et al.

Transformer-based self-supervised speech models (S3Ms) are often described as contextualized, yet what this entails remains unclear. Here, we focus on how a single frame-level S3M representation can encode phones and their surrounding context. Prior work has shown that S3Ms represent phones compositionally; for example, phonological vectors such as voicing, bilabiality, and nasality vectors are superposed in the S3M representation of [m]. We extend this view by proposing that phonological information from a sequence of neighboring phones is also compositionally encoded in a single frame, such that vectors corresponding to previous, current, and next phones are superposed within a single frame-level representation. We show that this structure has several properties, including orthogonality between relative positions, and emergence of implicit phonetic boundaries. Together, our findings advance our understanding of context-dependent S3M representations.

Chin-Jou Li, Eunjung Yeo, Kwanghee Choi et al. · cmu

Automatic speech recognition (ASR) for dysarthric speech remains challenging due to data scarcity, particularly in non-English languages. To address this, we fine-tune a voice conversion model on English dysarthric speech (UASpeech) to encode both speaker characteristics and prosodic distortions, then apply it to convert healthy non-English speech (FLEURS) into non-English dysarthric-like speech. The generated data is then used to fine-tune a multilingual ASR model, Massively Multilingual Speech (MMS), for improved dysarthric speech recognition. Evaluation on PC-GITA (Spanish), EasyCall (Italian), and SSNCE (Tamil) demonstrates that VC with both speaker and prosody conversion significantly outperforms the off-the-shelf MMS performance and conventional augmentation techniques such as speed and tempo perturbation. Objective and subjective analyses of the generated data further confirm that the generated speech simulates dysarthric characteristics.

Minu Kim, Hoirin Kim, David R. Mortensen

Similarities between language representations derived from Self-Supervised Speech Models (S3Ms) have been observed to primarily reflect geographic proximity or surface typological similarities driven by recent expansion or contact, potentially missing deeper genealogical signals. We investigate how scaling linguistic coverage of an S3M-based language identification system from 126 to 4,017 languages influences this topology. Our results reveal a non-linear effect: while phylogenetic recovery remains stagnant up to the 1K scale, the 4K model displays a dramatic qualitative shift, resolving both clear lineages and complex, long-term linguistic contact. Notably, our analysis reveals the emergence of a robust macro-cluster in the Pacific (comprising Papuan, Oceanic, and Australian languages) and investigates its latent drivers. We find that the 4K model utilizes a more concentrated encoding that captures shared, robust acoustic signatures such as global energy dynamics. These findings suggest that massive S3Ms can internalize multiple layers of language history, providing a promising perspective for computational phylogenetics and the study of language contact.

Ananth Hariharan, David Mortensen

This study demonstrates how hybrid neural-symbolic methods can yield significant new insights into the evolution of a morphologically rich, low-resource language. We challenge the naive assumption that linguistic change is simplification by quantitatively analyzing over 2,000 years of Sanskrit, demonstrating how weakly-supervised hybrid methods can yield new insights into the evolution of morphologically rich, low-resource languages. Our approach addresses data scarcity through weak supervision, using 100+ high-precision regex patterns to generate pseudo-labels for fine-tuning a multilingual BERT. We then fuse symbolic and neural outputs via a novel confidence-weighted ensemble, creating a system that is both scalable and interpretable. Applying this framework to a 1.47-million-word diachronic corpus, our ensemble achieves a 52.4% overall feature detection rate. Our findings reveal that Sanskrit's overall morphological complexity does not decrease but is instead dynamically redistributed: while earlier verbal features show cyclical patterns of decline, complexity shifts to other domains, evidenced by a dramatic expansion in compounding and the emergence of new philosophical terminology. Critically, our system produces well-calibrated uncertainty estimates, with confidence strongly correlating with accuracy (Pearson r = 0.92) and low overall calibration error (ECE = 0.043), bolstering the reliability of these findings for computational philology.

Brendon Boldt, David Mortensen · cmu

We introduce CSAR, an algorithm for inducing morphemes from emergent language corpora of parallel utterances and meanings. It is a greedy algorithm that (1) weights morphemes based on mutual information between forms and meanings, (2) selects the highest-weighted pair, (3) removes it from the corpus, and (4) repeats the process to induce further morphemes (i.e., Count, Select, Ablate, Repeat). The effectiveness of CSAR is first validated on procedurally generated datasets and compared against baselines for related tasks. Second, we validate CSAR's performance on human language data to show that the algorithm makes reasonable predictions in adjacent domains. Finally, we analyze a handful of emergent languages, quantifying linguistic characteristics like degree of synonymy and polysemy.

Brendon Boldt, David Mortensen · cmu

In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of emergent language as well as corroborate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language.

Karen Rosero, Eunjung Yeo, David R. Mortensen et al. · cmu

We present ChiReSSD, a speech reconstruction framework that preserves children speaker's identity while suppressing mispronunciations. Unlike prior approaches trained on healthy adult speech, ChiReSSD adapts to the voices of children with speech sound disorders (SSD), with particular emphasis on pitch and prosody. We evaluate our method on the STAR dataset and report substantial improvements in lexical accuracy and speaker identity preservation. Furthermore, we automatically predict the phonetic content in the original and reconstructed pairs, where the proportion of corrected consonants is comparable to the percentage of correct consonants (PCC), a clinical speech assessment metric. Our experiments show Pearson correlation of 0.63 between automatic and human expert annotations, highlighting the potential to reduce the manual transcription burden. In addition, experiments on the TORGO dataset demonstrate effective generalization for reconstructing adult dysarthric speech. Our results indicate that disentangled, style-based TTS reconstruction can provide identity-preserving speech across diverse clinical populations.

Niyati Bafna, Emily Chang, Nathaniel R. Robinson et al. · cmu

Most of the world's languages and dialects are low-resource, and lack support in mainstream machine translation (MT) models. However, many of them have a closely-related high-resource language (HRL) neighbor, and differ in linguistically regular ways from it. This underscores the importance of model robustness to dialectal variation and cross-lingual generalization to the HRL dialect continuum. We present DialUp, consisting of a training-time technique for adapting a pretrained model to dialectal data (M->D), and an inference-time intervention adapting dialectal data to the model expertise (D->M). M->D induces model robustness to potentially unseen and unknown dialects by exposure to synthetic data exemplifying linguistic mechanisms of dialectal variation, whereas D->M treats dialectal divergence for known target dialects. These methods show considerable performance gains for several dialects from four language families, and modest gains for two other language families. We also conduct feature and error analyses, which show that language varieties with low baseline MT performance are more likely to benefit from these approaches.

Eunjung Yeo, Julie Liss, Visar Berisha et al.

Purpose: Speech intelligibility is a critical outcome in the assessment and management of dysarthria, yet most research and clinical practices have focused on English, limiting their applicability across languages. This commentary introduces a conceptual framework--and a demonstration of how it can be implemented--leveraging artificial intelligence (AI) to advance cross-language intelligibility assessment of dysarthric speech. Method: We propose a two-tiered conceptual framework consisting of a universal speech model that encodes dysarthric speech into acoustic-phonetic representations, followed by a language-specific intelligibility assessment model that interprets these representations within the phonological or prosodic structures of the target language. We further identify barriers to cross-language intelligibility assessment of dysarthric speech, including data scarcity, annotation complexity, and limited linguistic insights into dysarthric speech, and outline potential AI-driven solutions to overcome these challenges. Conclusion: Advancing cross-language intelligibility assessment of dysarthric speech necessitates models that are both efficient and scalable, yet constrained by linguistic rules to ensure accurate and language-sensitive assessment. Recent advances in AI provide the foundational tools to support this integration, shaping future directions toward generalizable and linguistically informed assessment frameworks.

Jimin Sohn, Jeihee Cho, Junyong Lee et al.

Positive thinking is thought to be an important component of self-motivation in various practical fields such as education and the workplace. Previous work, including sentiment transfer and positive reframing, has focused on the positive side of language. However, self-motivation that drives people to reach their goals has not yet been studied from a computational perspective. Moreover, negative feedback has not yet been explored, even though positive and negative feedback are both necessary to grow self-motivation. To facilitate self-motivation, we propose CArrot and STICk (CASTIC) dataset, consisting of 12,590 sentences with 5 different strategies for enhancing self-motivation. Our data and code are publicly available at here.

Atharva Naik, Kexun Zhang, Nathaniel Robinson et al.

Historical linguists have long written a kind of incompletely formalized ''program'' that converts reconstructed words in an ancestor language into words in one of its attested descendants that consist of a series of ordered string rewrite functions (called sound laws). They do this by observing pairs of words in the reconstructed language (protoforms) and the descendent language (reflexes) and constructing a program that transforms protoforms into reflexes. However, writing these programs is error-prone and time-consuming. Prior work has successfully scaffolded this process computationally, but fewer researchers have tackled Sound Law Induction (SLI), which we approach in this paper by casting it as Programming by Examples. We propose a language-agnostic solution that utilizes the programming ability of Large Language Models (LLMs) by generating Python sound law programs from sound change examples. We evaluate the effectiveness of our approach for various LLMs, propose effective methods to generate additional language-agnostic synthetic data to fine-tune LLMs for SLI, and compare our method with existing automated SLI methods showing that while LLMs lag behind them they can complement some of their weaknesses.

Liang Lu, Peirong Xie, David R. Mortensen

Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount of labeled data. We propose a semisupervised historical reconstruction task in which the model is trained on only a small amount of labeled data (cognate sets with proto-forms) and a large amount of unlabeled data (cognate sets without proto-forms). We propose a neural architecture for comparative reconstruction (DPD-BiReconstructor) incorporating an essential insight from linguists' comparative method: that reconstructed words should not only be reconstructable from their daughter words, but also deterministically transformable back into their daughter words. We show that this architecture is able to leverage unlabeled cognate sets to outperform strong semisupervised baselines on this novel task.

Taiqi He, Kwanghee Choi, Lindia Tjuatja et al.

Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of linguistic annotation that can support documentation and resource creation for these languages' communities. IGT typically consists of (1) transcriptions, (2) morphological segmentation, (3) glosses, and (4) free translations to a majority language. We propose Wav2Gloss: a task in which these four annotation components are extracted automatically from speech, and introduce the first dataset to this end, Fieldwork: a corpus of speech with all these annotations, derived from the work of field linguists, covering 37 languages, with standard formatting, and train/dev/test splits. We provide various baselines to lay the groundwork for future research on IGT generation from speech, such as end-to-end versus cascaded, monolingual versus multilingual, and single-task versus multi-task approaches.

Ryan Soh-Eun Shim, Kalvin Chang, David R. Mortensen · cmu

Received wisdom in linguistic typology holds that if the structure of a language becomes more complex in one dimension, it will simplify in another, building on the assumption that all languages are equally complex (Joseph and Newmeyer, 2012). We study this claim on a micro-level, using a tightly-controlled sample of Dutch dialects (across 366 collection sites) and Min dialects (across 60 sites), which enables a more fair comparison across varieties. Even at the dialect level, we find empirical evidence for a tradeoff between word length and a computational measure of phonotactic complexity from a LSTM-based phone-level language model-a result previously documented only at the language level. A generalized additive model (GAM) shows that dialects with low phonotactic complexity concentrate around the capital regions, which we hypothesize to correspond to prior hypotheses that language varieties of greater or more diverse populations show reduced phonotactic complexity. We also experiment with incorporating the auxiliary task of predicting syllable constituency, but do not find an increase in the negative correlation observed.