Byte-pair encoding (BPE) is widely used in NLP for performing subword tokenization. It uncovers redundant patterns for compressing the data, and hence alleviates the sparsity problem in downstream applications. Subwords discovered during the first merge operations tend to have the most substantial impact on the compression of texts. However, the structural underpinnings of this effect have not been analyzed cross-linguistically. We conduct in-depth analyses across 47 typologically diverse languages and three parallel corpora, and thereby show that the types of recurrent patterns that have the strongest impact on compression are an indicator of morphological typology. For languages with richer inflectional morphology there is a preference for highly productive subwords on the early merges, while for languages with less inflectional morphology, idiosyncratic subwords are more prominent. Both types of patterns contribute to efficient compression. Counter to the common perception that BPE subwords are not linguistically relevant, we find patterns across languages that resemble those described in traditional typology. We thus propose a novel way to characterize languages according to their BPE subword properties, inspired by the notion of morphological productivity in linguistics. This allows us to have language vectors that encode typological knowledge induced from raw text. Our approach is easily applicable to a wider range of languages and texts, as it does not require annotated data or any external linguistic knowledge. We discuss its potential contributions to quantitative typology and multilingual NLP.

Cross-lingual transfer of parsing models has been shown to work well for several closely-related languages, but predicting the success in other cases remains hard. Our study is a comprehensive analysis of the impact of linguistic distance on the transfer of UD parsers. As an alternative to syntactic typological distances extracted from URIEL, we propose three text-based feature spaces and show that they can be more precise predictors, especially on a more local scale, when only shorter distances are taken into account. Our analyses also reveal that the good coverage in typological databases is not among the factors that explain good transfer.

We present the TeDDi sample, a diversity sample of text data for language comparison and multilingual Natural Language Processing. The TeDDi sample currently features 89 languages based on the typological diversity sample in the World Atlas of Language Structures. It consists of more than 20k texts and is accompanied by open-source corpus processing tools. The aim of TeDDi is to facilitate text-based quantitative analysis of linguistic diversity. We describe in detail the TeDDi sample, how it was created, data availability, and its added value through for NLP and linguistic research.

In linguistics, interlinear glossing is an essential procedure for analyzing the morphology of languages. This type of annotation is useful for language documentation, and it can also provide valuable data for NLP applications. We perform automatic glossing for Otomi, an under-resourced language. Our work also comprises the pre-processing and annotation of the corpus. We implement different sequential labelers. CRF models represented an efficient and good solution for our task. Two main observations emerged from our work: 1) models with a higher number of parameters (RNNs) performed worse in our low-resource scenario; and 2) the information encoded in the CRF feature function plays an important role in the prediction of labels; however, even in cases where POS tags are not available it is still possible to achieve competitive results.

This paper presents the results of the 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas. The shared task featured two independent tracks, and participants submitted machine translation systems for up to 10 indigenous languages. Overall, 8 teams participated with a total of 214 submissions. We provided training sets consisting of data collected from various sources, as well as manually translated sentences for the development and test sets. An official baseline trained on this data was also provided. Team submissions featured a variety of architectures, including both statistical and neural models, and for the majority of languages, many teams were able to considerably improve over the baseline. The best performing systems achieved 12.97 ChrF higher than baseline, when averaged across languages.

Neural models for morphological inflection have recently attained very high results. However, their interpretation remains challenging. Towards this goal, we propose a simple linguistically-motivated variant to the encoder-decoder model with attention. In our model, character-level cross-attention mechanism is complemented with a self-attention module over substrings of the input. We design a novel approach for pattern extraction from attention weights to interpret what the model learn. We apply our methodology to analyze the model’s decisions on three typologically-different languages and find that a) our pattern extraction method applied to cross-attention weights uncovers variation in form of inflection morphemes, b) pattern extraction from self-attention shows triggers for such variation, c) both types of patterns are closely aligned with grammar inflection classes and class assignment criteria, for all three languages. Additionally, we find that the proposed encoder attention component leads to consistent performance improvements over a strong baseline.

The distributions of orthographic word types are very different across languages due to typological characteristics, different writing traditions and potentially other factors. The wide range of cross-linguistic diversity is still a major challenge for NLP and the study of language. We use BPE and information-theoretic measures to investigate if distributions become similar under specific levels of subword tokenization. We perform a cross-linguistic comparison, following incremental merges of BPE (we go from characters to words) for 47 diverse languages. We show that text entropy values (a feature of probability distributions) tend to converge at specific subword levels: relatively few BPE merges (around 350) lead to the most similar distributions across languages. Additionally, we analyze the interaction between subword and word-level distributions and show that our findings can be interpreted in light of the ongoing discussion regarding different types of morphological complexity.

Indigenous languages of the American continent are highly diverse. However, they have received little attention from the technological perspective. In this paper, we review the research, the digital resources and the available NLP systems that focus on these languages. We present the main challenges and research questions that arise when distant languages and low-resource scenarios are faced. We would like to encourage NLP research in linguistically rich and diverse areas like the Americas.

We use two small parallel corpora for comparing the morphological complexity of Spanish, Otomi and Nahuatl. These are languages that belong to different linguistic families, the latter are low-resourced. We take into account two quantitative criteria, on one hand the distribution of types over tokens in a corpus, on the other, perplexity and entropy as indicators of word structure predictability. We show that a language can be complex in terms of how many different morphological word forms can produce, however, it may be less complex in terms of predictability of its internal structure of words.

This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface. Spanish and Nahuatl are distant languages spoken in the same country. Due to the scarcity of digital resources, we describe the several problems that arose when compiling this corpus: most of our sources were non-digital books, we faced errors when digitizing the sources and there were difficulties in the sentence alignment process, just to mention some. The documents of the parallel corpus are not homogeneous, they were extracted from different sources, there is dialectal, diachronical, and orthographical variation. Additionally, we present a web search interface that allows to make queries through the whole parallel corpus, the system is capable to retrieve the parallel fragments that contain a word or phrase searched by a user in any of the languages. To our knowledge, this is the first Spanish-Nahuatl public available digital parallel corpus. We think that this resource can be useful to develop language technologies and linguistic studies for this language pair.