Tokenization and morphological segmentation continue to pose challenges for text processing and studies of human language. Here, we focus on written Soranî Kurdish, which uses a modified script based on Persian and Arabic, and its transliterations into the Kurdish Latin script. Importantly, Perso-Arabic and Latin-based writing systems demonstrate different statistical and structural properties, which may have significant effects on subword vocabulary learning. This has major consequences for frequency- or probability-based models of morphological induction. We explore the possibility that jointly training subword vocabularies using a source script along with its transliteration would improve morphological segmentation, subword tokenization, and whether gains are observed for one system over others. We find that joint training has a similar effect to increasing vocabulary size, while keeping subwords shorter in length, which produces higher-quality subwords that map onto morphemes.

We present a solution to the problem of exemplar-based language production from variable-duration tokens, leveraging algorithms from the domain of time-series clustering and classification. Our model stores and outputs tokens of phonetically rich and temporally variable representations of recorded speech. We show qualitatively and quantitatively that model outputs retain essential acoustic/phonetic characteristics despite the noise introduced by averaging, and also demonstrate the effects of similarity and indexical information as constraints on exemplar cloud selection.

Modeling the most likely label when an annotation task is perspective-dependent discards relevant sources of variation that come from the annotators themselves. We present three approaches to modeling the controversiality of a particular text. First, we explicitly represented annotators using annotator embeddings to predict the training signals of each annotator’s selections in addition to a majority class label. This method leads to reduction in error relative to models without these features, allowing the overall result to influence the weights of each annotator on the final prediction. In a second set of experiments, annotators were not modeled individually but instead annotator judgments were combined in a pairwise fashion that allowed us to implicitly combine annotators. Overall, we found that aggregating and explicitly comparing annotators’ responses to a static document representation produced high-quality predictions in all datasets, though some systems struggle to account for large or variable numbers of annotators.

Annotation of discourse relations is a known difficult task, especially for non-expert annotators. In this paper, we investigate novice annotators’ uncertainty on the annotation of discourse relations on spoken conversational data. We find that dialogue context (single turn, pair of turns within speaker, and pair of turns across speakers) is a significant predictor of confidence scores. We compute distributed representations of discourse relations from co-occurrence statistics that incorporate information about confidence scores and dialogue context. We perform a hierarchical clustering analysis using these representations and show that weighting discourse relation representations with information about confidence and dialogue context coherently models our annotators’ uncertainty about discourse relation labels.

Time pressure and topic negotiation may impose constraints on how people leverage discourse relations (DRs) in spontaneous conversational contexts. In this work, we adapt a system of DRs for written language to spontaneous dialogue using crowdsourced annotations from novice annotators. We then test whether discourse relations are used differently across several types of multi-utterance contexts. We compare the patterns of DR annotation within and across speakers and within and across turns. Ultimately, we find that different discourse contexts produce distinct distributions of discourse relations, with single-turn annotations creating the most uncertainty for annotators. Additionally, we find that the discourse relation annotations are of sufficient quality to predict from embeddings of discourse units.

We present the second shared task on eye-tracking data prediction of the Cognitive Modeling and Computational Linguistics Workshop (CMCL). Differently from the previous edition, participating teams are asked to predict eye-tracking features from multiple languages, including a surprise language for which there were no available training data. Moreover, the task also included the prediction of standard deviations of feature values in order to account for individual differences between readers.A total of six teams registered to the task. For the first subtask on multilingual prediction, the winning team proposed a regression model based on lexical features, while for the second subtask on cross-lingual prediction, the winning team used a hybrid model based on a multilingual transformer embeddings as well as statistical features.

Annotating workplace bias in text is a noisy and subjective task. In encoding the inherently continuous nature of bias, aggregated binary classifications do not suffice. Best-worst scaling (BWS) offers a framework to obtain real-valued scores through a series of comparative evaluations, but it is often impractical to deploy to traditional annotation pipelines within industry. We present analyses of a small-scale bias dataset, jointly annotated with categorical annotations and BWS annotations. We show that there is a strong correlation between observed agreement and BWS score (Spearman’s r=0.72). We identify several shortcomings of BWS relative to traditional categorical annotation: (1) When compared to categorical annotation, we estimate BWS takes approximately 4.5x longer to complete; (2) BWS does not scale well to large annotation tasks with sparse target phenomena; (3) The high correlation between BWS and the traditional task shows that the benefits of BWS can be recovered from a simple categorically annotated, non-aggregated dataset.

Eye-tracking data from reading represent an important resource for both linguistics and natural language processing. The ability to accurately model gaze features is crucial to advance our understanding of language processing. This paper describes the Shared Task on Eye-Tracking Data Prediction, jointly organized with the eleventh edition of the Work- shop on Cognitive Modeling and Computational Linguistics (CMCL 2021). The goal of the task is to predict 5 different token- level eye-tracking metrics of the Zurich Cognitive Language Processing Corpus (ZuCo). Eye-tracking data were recorded during natural reading of English sentences. In total, we received submissions from 13 registered teams, whose systems include boosting algorithms with handcrafted features, neural models leveraging transformer language models, or hybrid approaches. The winning system used a range of linguistic and psychometric features in a gradient boosting framework.

We present the New York Times Word Innovation Types dataset, or NYTWIT, a collection of over 2,500 novel English words published in the New York Times between November 2017 and March 2019, manually annotated for their class of novelty (such as lexical derivation, dialectal variation, blending, or compounding). We present baseline results for both uncontextual and contextual prediction of novelty class, showing that there is room for improvement even for state-of-the-art NLP systems. We hope this resource will prove useful for linguists and NLP practitioners by providing a real-world environment of novel word appearance.

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.

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.

Natural language processing systems often struggle with out-of-vocabulary (OOV) terms, which do not appear in training data. Blends, such as “innoventor”, are one particularly challenging class of OOV, as they are formed by fusing together two or more bases that relate to the intended meaning in unpredictable manners and degrees. In this work, we run experiments on a novel dataset of English OOV blends to quantify the difficulty of interpreting the meanings of blends by large-scale contextual language models such as BERT. We first show that BERT’s processing of these blends does not fully access the component meanings, leaving their contextual representations semantically impoverished. We find this is mostly due to the loss of characters resulting from blend formation. Then, we assess how easily different models can recognize the structure and recover the origin of blends, and find that context-aware embedding systems outperform character-level and context-free embeddings, although their results are still far from satisfactory.

We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words. We show that the output of an encoder network can predict the phonetic durations of American English words better than a number of alternative forms. We also show that the model’s learned representations map onto existing measures of words’ phonological structure (phonological neighborhood density and phonotactic probability).