Grapheme-to-phoneme conversion is an important component in many speech technologies, but until recently there were no multilingual benchmarks for this task. The third iteration of the SIGMORPHON shared task on multilingual grapheme-to-phoneme conversion features many improvements from the previous year’s task (Ashby et al., 2021), including additional languages, three subtasks varying the amount of available resources, extensive quality assurance procedures, and automated error analyses. Three teams submitted a total of fifteen systems, at best achieving relative reductions of word error rate of 14% in the crosslingual subtask and 14% in the very-low resource subtask. The generally consistent result is that cross-lingual transfer substantially helps grapheme-to-phoneme modeling, but not to the same degree as in-language examples.

Large multilingual models have inspired a new class of word alignment methods, which work well for the model’s pretraining languages. However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data. In this work, we ask: How do modern aligners perform on unseen languages, and are they better than traditional methods? We contribute gold-standard alignments for Bribri–Spanish, Guarani–Spanish, Quechua–Spanish, and Shipibo-Konibo–Spanish. With these, we evaluate state-of-the-art aligners with and without model adaptation to the target language. Finally, we also evaluate the resulting alignments extrinsically through two downstream tasks: named entity recognition and part-of-speech tagging. We find that although transformer-based methods generally outperform traditional models, the two classes of approach remain competitive with each other.

One challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we adapt large language models (LLMs) to split long ASR transcripts into segments that can be independently translated so as to maximize the overall translation quality. We overcome the tendency of hallucination in LLMs by incorporating finite-state constraints during decoding; these eliminate invalid outputs without requiring additional training. We discover that LLMs are adaptable to transcripts containing ASR errors through prompt-tuning or fine-tuning. Relative to a state-of-the-art automatic punctuation baseline, our best LLM improves the average BLEU by 2.9 points for English–German, English–Spanish, and English–Arabic TED talk translation in 9 test sets, just by improving segmentation.

In this position paper, we argue that computational text analysis lacks and requires organizing principles. A broad space separates its two constituent disciplines—natural language processing and social science—which has to date been sidestepped rather than filled by applying increasingly complex computational models to problems in social science research. We contrast descriptive and integrative findings, and our review of approximately 60 papers on computational text analysis reveals that those from *ACL venues are typically descriptive. The lack of theory began at the area’s inception and has over the decades, grown more important and challenging. A return to theoretically grounded research questions will propel the area from both theoretical and methodological points of view.

The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation, and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements on several fronts that were made in the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 66 new languages, including 24 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g., missing gender and macrons information. We have amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet.

This paper showcases the utility and timeliness of the Hong Kong Protest News Dataset, a highly curated collection of news articles from diverse news sources, to investigate longitudinal and synchronic news characterisations of protests in Hong Kong between 1998 and 2020. The properties of the dataset enable us to apply natural language processing to its 4522 articles and thereby study patterns of journalistic practice across newspapers. This paper sheds light on whether depth and/or manner of reporting changed over time, and if so, in what ways, or in response to what. In its focus and methodology, this paper helps bridge the gap between “validity-focused methodological debates” and the use of computational methods of analysis in the social sciences.

What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages? We conduct a thorough empirical experiment in 10 languages to ascertain this, considering five factors: (1) the amount of fine-tuning data, (2) the noise in the fine-tuning data, (3) the amount of pre-training data in the model, (4) the impact of domain mismatch, and (5) language typology. In addition to yielding several heuristics, the experiments form a framework for evaluating the data sensitivities of machine translation systems. While mBART is robust to domain differences, its translations for unseen and typologically distant languages remain below 3.0 BLEU. In answer to our title’s question, mBART is not a low-resource panacea; we therefore encourage shifting the emphasis from new models to new data.

Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages. Having long been multilingual, the field of computational morphology is increasingly moving towards approaches suitable for languages with minimal or no annotated resources. First, we survey recent developments in computational morphology with a focus on low-resource languages. Second, we argue that the field is ready to tackle the logical next challenge: understanding a language’s morphology from raw text alone. We perform an empirical study on a truly unsupervised version of the paradigm completion task and show that, while existing state-of-the-art models bridged by two newly proposed models we devise perform reasonably, there is still much room for improvement. The stakes are high: solving this task will increase the language coverage of morphological resources by a number of magnitudes.

The field of natural language processing (NLP) has grown over the last few years: conferences have become larger, we have published an incredible amount of papers, and state-of-the-art research has been implemented in a large variety of customer-facing products. However, this paper argues that we have been less successful than we *should* have been and reflects on where and how the field fails to tap its full potential. Specifically, we demonstrate that, in recent years, **subpar time allocation has been a major obstacle for NLP research**. We outline multiple concrete problems together with their negative consequences and, importantly, suggest remedies to improve the status quo. We hope that this paper will be a starting point for discussions around which common practices are – or are *not* – beneficial for NLP research.

This paper presents a detailed foundational empirical case study of the nature of out-of-vocabulary words encountered in modern text in a moderate-resource language such as Bulgarian, and a multi-faceted distributional analysis of the underlying word-formation processes that can aid in their compositional translation, tagging, parsing, language modeling, and other NLP tasks. Given that out-of-vocabulary (OOV) words generally present a key open challenge to NLP and machine translation systems, especially toward the lower limit of resource availability, there are useful practical insights, as well as corpus-linguistic insights, from both a detailed manual and automatic taxonomic analysis of the types, multidimensional properties, and processing potential for multiple representative OOV data samples.

A challenge in designing high-stakes language assessments is calibrating the test item difficulties, either a priori or from limited pilot test data. While prior work has addressed ‘cold start’ estimation of item difficulties without piloting, we devise a multi-task generalized linear model with BERT features to jump-start these estimates, rapidly improving their quality with as few as 500 test-takers and a small sample of item exposures (≈6 each) from a large item bank (≈4,000 items). Our joint model provides a principled way to compare test-taker proficiency, item difficulty, and language proficiency frameworks like the Common European Framework of Reference (CEFR). This also enables new item difficulty estimates without piloting them first, which in turn limits item exposure and thus enhances test item security. Finally, using operational data from the Duolingo English Test, a high-stakes English proficiency test, we find that the difficulty estimates derived using this method correlate strongly with lexico-grammatical features that correlate with reading complexity.

We describe the second SIGMORPHON shared task on unsupervised morphology: the goal of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering is to cluster word types from a raw text corpus into paradigms. To this end, we release corpora for 5 development and 9 test languages, as well as gold partial paradigms for evaluation. We receive 14 submissions from 4 teams that follow different strategies, and the best performing system is based on adaptor grammars. Results vary significantly across languages. However, all systems are outperformed by a supervised lemmatizer, implying that there is still room for improvement.

We apply statistical techniques from natural language processing to Western and Hong Kong–based English language newspaper articles that discuss the 2019–2020 Hong Kong protests of the Anti-Extradition Law Amendment Bill Movement. Topic modeling detects central themes of the reporting and shows the differing agendas toward one country, two systems. Embedding-based usage shift (at the word level) and sentiment analysis (at the document level) both support that Hong Kong–based reporting is more negative and more emotionally charged. A two-way test shows that while July 1, 2019 is a turning point for media portrayal, the differences between western- and Hong Kong–based reporting did not magnify when the protests began; rather, they already existed. Taken together, these findings clarify how the portrayal of activism in Hong Kong evolved throughout the Movement.

We apply statistical techniques from natural language processing to a collection of Western and Hong Kong–based English-language newspaper articles spanning the years 1998–2020, studying the difference and evolution of its portrayal. We observe that both content and attitudes differ between Western and Hong Kong–based sources. ANOVA on keyword frequencies reveals that Hong Kong–based papers discuss protests and democracy less often. Topic modeling detects salient aspects of protests and shows that Hong Kong–based papers made fewer references to police violence during the Anti–Extradition Law Amendment Bill Movement. Diachronic shifts in word embedding neighborhoods reveal a shift in the characterization of salient keywords once the Movement emerged. Together, these raise questions about the existence of anodyne reporting from Hong Kong–based media. Likewise, they illustrate the importance of sample selection for protest event analysis.

We describe the design and findings of the SIGMORPHON 2020 shared task on multilingual grapheme-to-phoneme conversion. Participants were asked to submit systems which take in a sequence of graphemes in a given language as input, then output a sequence of phonemes representing the pronunciation of that grapheme sequence. Nine teams submitted a total of 23 systems, at best achieving a 18% relative reduction in word error rate (macro-averaged over languages), versus strong neural sequence-to-sequence baselines. To facilitate error analysis, we publicly release the complete outputs for all systems—a first for the SIGMORPHON workshop.

In this paper, we describe the findings of the SIGMORPHON 2020 shared task on unsupervised morphological paradigm completion (SIGMORPHON 2020 Task 2), a novel task in the field of inflectional morphology. Participants were asked to submit systems which take raw text and a list of lemmas as input, and output all inflected forms, i.e., the entire morphological paradigm, of each lemma. In order to simulate a realistic use case, we first released data for 5 development languages. However, systems were officially evaluated on 9 surprise languages, which were only revealed a few days before the submission deadline. We provided a modular baseline system, which is a pipeline of 4 components. 3 teams submitted a total of 7 systems, but, surprisingly, none of the submitted systems was able to improve over the baseline on average over all 9 test languages. Only on 3 languages did a submitted system obtain the best results. This shows that unsupervised morphological paradigm completion is still largely unsolved. We present an analysis here, so that this shared task will ground further research on the topic.

This paper presents the Johns Hopkins University submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education (STAPLE). We participated in all five language tasks, placing first in each. Our approach involved a language-agnostic pipeline of three components: (1) building strong machine translation systems on general-domain data, (2) fine-tuning on Duolingo-provided data, and (3) generating n-best lists which are then filtered with various score-based techniques. In addi- tion to the language-agnostic pipeline, we attempted a number of linguistically-motivated approaches, with, unfortunately, little success. We also find that improving BLEU performance of the beam-search generated translation does not necessarily improve on the task metric—weighted macro F1 of an n-best list.

We present findings from the creation of a massively parallel corpus in over 1600 languages, the Johns Hopkins University Bible Corpus (JHUBC). The corpus consists of over 4000 unique translations of the Christian Bible and counting. Our data is derived from scraping several online resources and merging them with existing corpora, combining them under a common scheme that is verse-parallel across all translations. We detail our effort to scrape, clean, align, and utilize this ripe multilingual dataset. The corpus captures the great typological variety of the world’s languages. We catalog this by showing highly similar proportions of representation of Ethnologue’s typological features in our corpus. We also give an example application: projecting pronoun features like clusivity across alignments to richly annotate languages which do not mark the distinction.

In this work, we explore massively multilingual low-resource neural machine translation. Using translations of the Bible (which have parallel structure across languages), we train models with up to 1,107 source languages. We create various multilingual corpora, varying the number and relatedness of source languages. Using these, we investigate the best ways to use this many-way aligned resource for multilingual machine translation. Our experiments employ a grammatically and phylogenetically diverse set of source languages during testing for more representative evaluations. We find that best practices in this domain are highly language-specific: adding more languages to a training set is often better, but too many harms performance—the best number depends on the source language. Furthermore, training on related languages can improve or degrade performance, depending on the language. As there is no one-size-fits-most answer, we find that it is critical to tailor one’s approach to the source language and its typology.

The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological paradigms for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. We have implemented several improvements to the extraction pipeline which creates most of our data, so that it is both more complete and more correct. We have added 66 new languages, as well as new parts of speech for 12 languages. We have also amended the schema in several ways. Finally, we present three new community tools: two to validate data for resource creators, and one to make morphological data available from the command line. UniMorph is based at the Center for Language and Speech Processing (CLSP) at Johns Hopkins University in Baltimore, Maryland. This paper details advances made to the schema, tooling, and dissemination of project resources since the UniMorph 2.0 release described at LREC 2018.

Exploiting the broad translation of the Bible into the world’s languages, we train and distribute morphosyntactic tools for approximately one thousand languages, vastly outstripping previous distributions of tools devoted to the processing of inflectional morphology. Evaluation of the tools on a subset of available inflectional dictionaries demonstrates strong initial models, supplemented and improved through ensembling and dictionary-based reranking. Likewise, a novel type-to-token based evaluation metric allows us to confirm that models generalize well across rare and common forms alike

We introduce WikiPron, an open-source command-line tool for extracting pronunciation data from Wiktionary, a collaborative multilingual online dictionary. We first describe the design and use of WikiPron. We then discuss the challenges faced scaling this tool to create an automatically-generated database of 1.7 million pronunciations from 165 languages. Finally, we validate the pronunciation database by using it to train and evaluating a collection of generic grapheme-to-phoneme models. The software, pronunciation data, and models are all made available under permissive open-source licenses.

The noun lexica of many natural languages are divided into several declension classes with characteristic morphological properties. Class membership is far from deterministic, but the phonological form of a noun and/or its meaning can often provide imperfect clues. Here, we investigate the strength of those clues. More specifically, we operationalize this by measuring how much information, in bits, we can glean about declension class from knowing the form and/or meaning of nouns. We know that form and meaning are often also indicative of grammatical gender—which, as we quantitatively verify, can itself share information with declension class—so we also control for gender. We find for two Indo-European languages (Czech and German) that form and meaning respectively share significant amounts of information with class (and contribute additional information above and beyond gender). The three-way interaction between class, form, and meaning (given gender) is also significant. Our study is important for two reasons: First, we introduce a new method that provides additional quantitative support for a classic linguistic finding that form and meaning are relevant for the classification of nouns into declensions. Secondly, we show not only that individual declensions classes vary in the strength of their clues within a language, but also that these variations themselves vary across languages.

We propose the task of unsupervised morphological paradigm completion. Given only raw text and a lemma list, the task consists of generating the morphological paradigms, i.e., all inflected forms, of the lemmas. From a natural language processing (NLP) perspective, this is a challenging unsupervised task, and high-performing systems have the potential to improve tools for low-resource languages or to assist linguistic annotators. From a cognitive science perspective, this can shed light on how children acquire morphological knowledge. We further introduce a system for the task, which generates morphological paradigms via the following steps: (i) EDIT TREE retrieval, (ii) additional lemma retrieval, (iii) paradigm size discovery, and (iv) inflection generation. We perform an evaluation on 14 typologically diverse languages. Our system outperforms trivial baselines with ease and, for some languages, even obtains a higher accuracy than minimally supervised systems.

This paper proposes a simple and effective approach to address the problem of posterior collapse in conditional variational autoencoders (CVAEs). It thus improves performance of machine translation models that use noisy or monolingual data, as well as in conventional settings. Extending Transformer and conditional VAEs, our proposed latent variable model measurably prevents posterior collapse by (1) using a modified evidence lower bound (ELBO) objective which promotes mutual information between the latent variable and the target, and (2) guiding the latent variable with an auxiliary bag-of-words prediction task. As a result, the proposed model yields improved translation quality compared to existing variational NMT models on WMT Ro↔En and De↔En. With latent variables being effectively utilized, our model demonstrates improved robustness over non-latent Transformer in handling uncertainty: exploiting noisy source-side monolingual data (up to +3.2 BLEU), and training with weakly aligned web-mined parallel data (up to +4.7 BLEU).

The training objective of unidirectional language models (LMs) is similar to a psycholinguistic benchmark known as the cloze task, which measures next-word predictability. However, LMs lack the rich set of experiences that people do, and humans can be highly creative. To assess human parity in these models’ training objective, we compare the predictions of three neural language models to those of human participants in a freely available behavioral dataset (Luke & Christianson, 2016). Our results show that while neural models show a close correspondence to human productions, they nevertheless assign insufficient probability to how often speakers guess upcoming words, especially for open-class content words.

We present a method for completing multilingual translation dictionaries. Our probabilistic approach can synthesize new word forms, allowing it to operate in settings where correct translations have not been observed in text (cf. cross-lingual embeddings). In addition, we propose an approximate Maximum Mutual Information (MMI) decoding objective to further improve performance in both many-to-one and one-to-one word level translation tasks where we use either multiple input languages for a single target language or more typical single language pair translation. The model is trained in a many-to-many setting, where it can leverage information from related languages to predict words in each of its many target languages. We focus on 6 languages: French, Spanish, Italian, Portuguese, Romanian, and Turkish. When indirect multilingual information is available, ensembling with mixture-of-experts as well as incorporating related languages leads to a 27% relative improvement in whole-word accuracy of predictions over a single-source baseline. To seed the completion when multilingual data is unavailable, it is better to decode with an MMI objective.

A grammatical gender system divides a lexicon into a small number of relatively fixed grammatical categories. How similar are these gender systems across languages? To quantify the similarity, we define gender systems extensionally, thereby reducing the problem of comparisons between languages’ gender systems to cluster evaluation. We borrow a rich inventory of statistical tools for cluster evaluation from the field of community detection (Driver and Kroeber, 1932; Cattell, 1945), that enable us to craft novel information theoretic metrics for measuring similarity between gender systems. We first validate our metrics, then use them to measure gender system similarity in 20 languages. We then ask whether our gender system similarities alone are sufficient to reconstruct historical relationships between languages. Towards this end, we make phylogenetic predictions on the popular, but thorny, problem from historical linguistics of inducing a phylogenetic tree over extant Indo-European languages. Of particular interest, languages on the same branch of our phylogenetic tree are notably similar, whereas languages from separate branches are no more similar than chance.

The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic description in 66 languages. The first task evolves past years’ inflection tasks by examining transfer of morphological inflection knowledge from a high-resource language to a low-resource language. This year also presents a new second challenge on lemmatization and morphological feature analysis in context. All submissions featured a neural component and built on either this year’s strong baselines or highly ranked systems from previous years’ shared tasks. Every participating team improved in accuracy over the baselines for the inflection task (though not Levenshtein distance), and every team in the contextual analysis task improved on both state-of-the-art neural and non-neural baselines.

A longstanding debate in semiotics centers on the relationship between linguistic signs and their corresponding semantics: is there an arbitrary relationship between a word form and its meaning, or does some systematic phenomenon pervade? For instance, does the character bigram ‘gl’ have any systematic relationship to the meaning of words like ‘glisten’, ‘gleam’ and ‘glow’? In this work, we offer a holistic quantification of the systematicity of the sign using mutual information and recurrent neural networks. We employ these in a data-driven and massively multilingual approach to the question, examining 106 languages. We find a statistically significant reduction in entropy when modeling a word form conditioned on its semantic representation. Encouragingly, we also recover well-attested English examples of systematic affixes. We conclude with the meta-point: Our approximate effect size (measured in bits) is quite small—despite some amount of systematicity between form and meaning, an arbitrary relationship and its resulting benefits dominate human language.

There is an extensive history of scholarship into what constitutes a “basic” color term, as well as a broadly attested acquisition sequence of basic color terms across many languages, as articulated in the seminal work of Berlin and Kay (1969). This paper employs a set of diverse measures on massively cross-linguistic data to operationalize and critique the Berlin and Kay color term hypotheses. Collectively, the 14 empirically-grounded computational linguistic metrics we design—as well as their aggregation—correlate strongly with both the Berlin and Kay basic/secondary color term partition (γ = 0.96) and their hypothesized universal acquisition sequence. The measures and result provide further empirical evidence from computational linguistics in support of their claims, as well as additional nuance: they suggest treating the partition as a spectrum instead of a dichotomy.

We conduct a manual error analysis of the CoNLL-SIGMORPHON Shared Task on Morphological Reinflection. This task involves natural language generation: systems are given a word in citation form (e.g., hug) and asked to produce the corresponding inflected form (e.g., the simple past hugged). We propose an error taxonomy and use it to annotate errors made by the top two systems across twelve languages. Many of the observed errors are related to inflectional patterns sensitive to inherent linguistic properties such as animacy or affect; many others are failures to predict truly unpredictable inflectional behaviors. We also find nearly one quarter of the residual “errors” reflect errors in the gold data.

For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then trans- late with machine translation (MT). A major cause of the performance gap is that, while existing AST corpora are small, massive datasets exist for both the ASR and MT subsystems. In this work, we evaluate several data augmentation and pretraining approaches for AST, by comparing all on the same datasets. Simple data augmentation by translating ASR transcripts proves most effective on the English–French augmented LibriSpeech dataset, closing the performance gap from 8.2 to 1.4 BLEU, compared to a very strong cascade that could directly utilize copious ASR and MT data. The same end-to-end approach plus fine-tuning closes the gap on the English–Romanian MuST-C dataset from 6.7 to 3.7 BLEU. In addition to these results, we present practical rec- ommendations for augmentation and pretraining approaches. Finally, we decrease the performance gap to 0.01 BLEU us- ing a Transformer-based architecture.

The Universal Dependencies (UD) and Universal Morphology (UniMorph) projects each present schemata for annotating the morphosyntactic details of language. Each project also provides corpora of annotated text in many languages—UD at the token level and UniMorph at the type level. As each corpus is built by different annotators, language-specific decisions hinder the goal of universal schemata. With compatibility of tags, each project’s annotations could be used to validate the other’s. Additionally, the availability of both type- and token-level resources would be a boon to tasks such as parsing and homograph disambiguation. To ease this interoperability, we present a deterministic mapping from Universal Dependencies v2 features into the UniMorph schema. We validate our approach by lookup in the UniMorph corpora and find a macro-average of 64.13% recall. We also note incompatibilities due to paucity of data on either side. Finally, we present a critical evaluation of the foundations, strengths, and weaknesses of the two annotation projects.

To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each component’s contribution to, and capacity for, domain adaptation. We find that freezing any single component during continued training has minimal impact on performance, and that performance is surprisingly good when a single component is adapted while holding the rest of the model fixed. We also find that continued training does not move the model very far from the out-of-domain model, compared to a sensitivity analysis metric, suggesting that the out-of-domain model can provide a good generic initialization for the new domain.