Textual domain is a crucial property within the Natural Language Processing (NLP) community due to its effects on downstream model performance. The concept itself is, however, loosely defined and, in practice, refers to any non-typological property, such as genre, topic, medium or style of a document. We investigate the core notion of domains via human proficiency in identifying related intrinsic textual properties, specifically the concepts of genre (communicative purpose) and topic (subject matter). We publish our annotations in TGeGUM: A collection of 9.1k sentences from the GUM dataset (Zeldes, 2017) with single sentence and larger context (i.e., prose) annotations for one of 11 genres (source type), and its topic/subtopic as per the Dewey Decimal library classification system (Dewey, 1979), consisting of 10/100 hierarchical topics of increased granularity. Each instance is annotated by three annotators, for a total of 32.7k annotations, allowing us to examine the level of human disagreement and the relative difficulty of each annotation task. With a Fleiss’ kappa of at most 0.53 on the sentence level and 0.66 at the prose level, it is evident that despite the ubiquity of domains in NLP, there is little human consensus on how to define them. By training classifiers to perform the same task, we find that this uncertainty also extends to NLP models.

When creating a new dataset for evaluation, one of the first considerations is the size of the dataset. If our evaluation data is too small, we risk making unsupported claims based on the results on such data. If, on the other hand, the data is too large, we waste valuable annotation time and costs that could have been used to widen the scope of our evaluation (i.e. annotate for more domains/languages). Hence, we investigate the effect of the size and a variety of sampling strategies of evaluation data to optimize annotation efforts, using dependency parsing as a test case. We show that for in-language in-domain datasets, 5,000 tokens is enough to obtain a reliable ranking of different parsers; especially if the data is distant enough from the training split (otherwise, we recommend 10,000). In cross-domain setups, the same amounts are required, but in cross-lingual setups much less (2,000 tokens) is enough.

Language understanding is a multi-faceted cognitive capability, which the Natural Language Processing (NLP) community has striven to model computationally for decades. Traditionally, facets of linguistic intelligence have been compartmentalized into tasks with specialized model architectures and corresponding evaluation protocols. With the advent of large language models (LLMs) the community has witnessed a dramatic shift towards general purpose, task-agnostic approaches powered by generative models. As a consequence, the traditional compartmentalized notion of language tasks is breaking down, followed by an increasing challenge for evaluation and analysis. At the same time, LLMs are being deployed in more real-world scenarios, including previously unforeseen zero-shot setups, increasing the need for trustworthy and reliable systems. Therefore, we argue that it is time to rethink what constitutes tasks and model evaluation in NLP, and pursue a more holistic view on language, placing trustworthiness at the center. Towards this goal, we review existing compartmentalized approaches for understanding the origins of a model’s functional capacity, and provide recommendations for more multi-faceted evaluation protocols.

Representational spaces learned via language modeling are fundamental to Natural Language Processing (NLP), however there has been limited understanding regarding how and when during training various types of linguistic information emerge and interact. Leveraging a novel information theoretic probing suite, which enables direct comparisons of not just task performance, but their representational subspaces, we analyze nine tasks covering syntax, semantics and reasoning, across 2M pre-training steps and five seeds. We identify critical learning phases across tasks and time, during which subspaces emerge, share information, and later disentangle to specialize. Across these phases, syntactic knowledge is acquired rapidly after 0.5% of full training. Continued performance improvements primarily stem from the acquisition of open-domain knowledge, while semantics and reasoning tasks benefit from later boosts to long-range contextualization and higher specialization. Measuring cross-task similarity further reveals that linguistically related tasks share information throughout training, and do so more during the critical phase of learning than before or after. Our findings have implications for model interpretability, multi-task learning, and learning from limited data.

Language from social media remains challenging to process automatically, especially for non-English languages. In this work, we introduce the first NLP dataset for TikTok comments and the first Danish social media dataset with part-of-speech annotation. We further supply annotations for normalization, code-switching, and annotator uncertainty. As transferring models to such a highly specialized domain is non-trivial, we conduct an extensive study into which source data and modeling decisions most impact the performance. Surprisingly, transferring from in-domain data, even from a different language, outperforms in-language, out-of-domain training. These benefits nonetheless rely on the underlying language models having been at least partially pre-trained on data from the target language. Using our additional annotation layers, we further analyze how normalization, code-switching, and human uncertainty affect the tagging accuracy.

The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to more established disciplines, a lack of common experimental standards remains an open challenge to the field at large. Starting from fundamental scientific principles, we distill ongoing discussions on experimental standards in NLP into a single, widely-applicable methodology. Following these best practices is crucial to strengthen experimental evidence, improve reproducibility and enable scientific progress. These standards are further collected in a public repository to help them transparently adapt to future needs.

Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored. The field of Computer Vision has begun to tackle encoder ranking, with promising forays into Natural Language Processing, however they lack coverage of linguistic tasks such as structured prediction. We propose probing to rank LMs, specifically for parsing dependencies in a given language, by measuring the degree to which labeled trees are recoverable from an LM’s contextualized embeddings. Across 46 typologically and architecturally diverse LM-language pairs, our probing approach predicts the best LM choice 79% of the time using orders of magnitude less compute than training a full parser. Within this study, we identify and analyze one recently proposed decoupled LM—RemBERT—and find it strikingly contains less inherent dependency information, but often yields the best parser after full fine-tuning. Without this outlier our approach identifies the best LM in 89% of cases.

With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori—as fine-tuning the entire space of available LMs is computationally prohibitive and unsustainable. However, encoder transferability estimation has received little to no attention in NLP. In this paper, we propose to generate quantitative evidence to predict which LM, out of a pool of models, will perform best on a target task without having to fine-tune all candidates. We provide a comprehensive study on LM ranking for 10 NLP tasks spanning the two fundamental problem types of classification and structured prediction. We adopt the state-of-the-art Logarithm of Maximum Evidence (LogME) measure from Computer Vision (CV) and find that it positively correlates with final LM performance in 94% of the setups.In the first study of its kind, we further compare transferability measures with the de facto standard of human practitioner ranking, finding that evidence from quantitative metrics is more robust than pure intuition and can help identify unexpected LM candidates.

Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers and frequencies. Leveraging these findings, we develop a fully learnable frequency filter to identify spectral profiles for any given task. It enables vastly more granular analyses than prior handcrafted filters, and improves on efficiency. After demonstrating the informativeness of spectral probing over manual filters in a monolingual setting, we investigate its multilingual characteristics across seven diverse NLP tasks in six languages. Our analyses identify distinctive spectral profiles which quantify cross-task similarity in a linguistically intuitive manner, while remaining consistent across languages—highlighting their potential as robust, lightweight task descriptors.

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.

Probing has become an important tool for analyzing representations in Natural Language Processing (NLP). For graphical NLP tasks such as dependency parsing, linear probes are currently limited to extracting undirected or unlabeled parse trees which do not capture the full task. This work introduces DepProbe, a linear probe which can extract labeled and directed dependency parse trees from embeddings while using fewer parameters and compute than prior methods. Leveraging its full task coverage and lightweight parametrization, we investigate its predictive power for selecting the best transfer language for training a full biaffine attention parser. Across 13 languages, our proposed method identifies the best source treebank 94% of the time, outperforming competitive baselines and prior work. Finally, we analyze the informativeness of task-specific subspaces in contextual embeddings as well as which benefits a full parser’s non-linear parametrization provides.

As input representation for each sub-word, the original BERT architecture proposes the sum of the sub-word embedding, position embedding and a segment embedding. Sub-word and position embeddings are well-known and studied, and encode lexical information and word position, respectively. In contrast, segment embeddings are less known and have so far received no attention, despite being ubiquitous in large pre-trained language models. The key idea of segment embeddings is to encode to which of the two sentences (segments) a word belongs to — the intuition is to inform the model about the separation of sentences for the next sentence prediction pre-training task. However, little is known on whether the choice of segment impacts performance. In this work, we try to fill this gap and empirically study the impact of the segment embedding during inference time for a variety of pre-trained embeddings and target tasks. We hypothesize that for single-sentence prediction tasks performance is not affected — neither in mono- nor multilingual setups — while it matters when swapping segment IDs in paired-sentence tasks. To our surprise, this is not the case. Although for classification tasks and monolingual BERT models no large differences are observed, particularly word-level multilingual prediction tasks are heavily impacted. For low-resource syntactic tasks, we observe impacts of segment embedding and multilingual BERT choice. We find that the default setting for the most used multilingual BERT model underperforms heavily, and a simple swap of the segment embeddings yields an average improvement of 2.5 points absolute LAS score for dependency parsing over 9 different treebanks.

Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized representations. We demonstrate that genre is recoverable from multilingual contextual embeddings and that it provides an effective signal for training data selection in cross-lingual, zero-shot scenarios. For 12 low-resource language treebanks, six of which are test-only, our genre-specific methods significantly outperform competitive baselines as well as recent embedding-based methods for data selection. Moreover, genre-based data selection provides new state-of-the-art results for three of these target languages.