Cross-lingual transfer allows models to perform tasks in languages unseen during training and is often assumed to benefit from increased multilinguality.In this work, we challenge this assumption in the context of two underexplored, sense-aware tasks: polysemy disambiguation and lexical semantic change.Through a largescale analysis across 28 languages, we show that multilingual training is neither necessary nor inherently beneficial for effective transfer.Instead, we find that confounding factors, such as fine-tuning data composition and evaluation artifacts, can better account for the perceived advantages of multilinguality.Our findings call for more rigorous evaluations in multilingual NLP, and more nuanced and sensible choice of models for transfer.We release fine-tuned models and benchmarks to support further research, with implications extending to low-resource and typologically diverse languages.

The task of Definition Generation has recently gained attention as an interpretable approach to modeling word meaning.Thus far, most research has been conducted in English, with limited work and resources for other languages.In this work, we expand Definition Generation beyond English to a suite of 22 languages and evaluate Llama-based models within a monolingual, multilingual, and cross-lingual setting.Our experiments show that monolingual fine-tuning consistently outperforms pretrained baselines, with the largest gains observed in languages with lower initial performance; and that multilingual fine-tuning does not consistently improve performance on the individual fine-tuning languages.Our cross-lingual evaluation reveals that models fine-tuned on a single language typically lose the ability to generate definitions in other languages, whereas multilingual models exhibit robust generalization even to languages unseen during fine-tuning.

Modern language models are capable of contextualizing words based on their surrounding context.However, this capability is often compromised due to semantic change that leads to words being used in new, unexpected contexts not encountered during pre-training.In this paper, we model semantic change by studying the effect of unexpected contexts introduced by lexical replacements.We propose a replacement schema where a target word is substituted with lexical replacements of varying relatedness, thus simulating different kinds of semantic change.Furthermore, we leverage the replacement schema as a basis for a novel interpretable model for semantic change.We are also the first to evaluate the use of LLaMa for semantic change detection.

This study addresses the critical issue of Natural Language Processing in low-resource languages such as Hindi, which, despite having substantial number of speakers, is limited in linguistic resources. The paper focuses on Word Sense Disambiguation, a fundamental NLP task that deals with polysemous words. It introduces a novel Hindi WSD dataset in the modern WiC format, enabling the training and testing of contextualized models. The primary contributions of this work lie in testing the efficacy of multilingual models to transfer across languages and hence to handle polysemy in low-resource languages, and in providing insights into the minimum training data required for a viable solution. Experiments compare different contextualized models on the WiC task via transfer learning from English to Hindi. Models purely transferred from English yield poor 55% accuracy, while fine-tuning on Hindi dramatically improves performance to 90% accuracy. This demonstrates the need for language-specific tuning and resources like the introduced Hindi WiC dataset to drive advances in Hindi NLP. The findings offer valuable insights into addressing the NLP needs of widely spoken yet low-resourced languages, shedding light on the problem of transfer learning in these contexts.

With recent advances, neural models can achieve human-level performance on various natural language tasks.However, there are no guarantees that any explanations from these models are faithful, i.e. that they reflect the inner workings of the model.Atomic inference overcomes this issue, providing interpretable and faithful model decisions.This approach involves making predictions for different components (or atoms) of an instance, before using interpretable and deterministic rules to derive the overall prediction based on the individual atom-level predictions.We investigate the effectiveness of using LLM-generated facts as atoms, decomposing Natural Language Inference premises into lists of facts.While directly using generated facts in atomic inference systems can result in worse performance, with 1) a multi-stage fact generation process, and 2) a training regime that incorporates the facts, our fact-based method outperforms other approaches. 1 Logical Rules for TrainingInstance

Current Natural Language Inference (NLI) models achieve impressive results, sometimes outperforming humans when evaluating on indistribution test sets.However, as these models are known to learn from annotation artefacts and dataset biases, it is unclear to what extent the models are learning the task of NLI instead of learning from shallow heuristics in their training data.We address this issue by introducing a logical reasoning framework for NLI, creating highly transparent model decisions that are based on logical rules.Unlike prior work, we show that improved interpretability can be achieved without decreasing the predictive accuracy.We almost fully retain performance on SNLI, while also identifying the exact hypothesis spans that are responsible for each model prediction.Using the e-SNLI human explanations, we verify that our model makes sensible decisions at a span level, despite not using any span labels during training.We can further improve model performance and span-level decisions by using the e-SNLI explanations during training.Finally, our model is more robust in a reduced data setting.When training with only 1,000 examples, out-of-distribution performance improves on the MNLI matched and mismatched validation sets by 13% and 16% relative to the baseline.Training with fewer observations yields further improvements, both in-distribution and out-ofdistribution.

Word meaning is notoriously difficult to capture, both synchronically and diachronically.In this paper, we describe the creation of the largest resource of graded contextualized, diachronic word meaning annotation in four different languages, based on 100,000 human semantic proximity judgments.We describe in detail the multi-round incremental annotation process, the choice for a clustering algorithm to group usages into senses, and possible -diachronic and synchronic -uses for this dataset.

Performance in cross-lingual NLP tasks is impacted by the (dis)similarity of languages at hand: e.g., previous work has suggested there is a connection between the expected success of bilingual lexicon induction (BLI) and the assumption of (approximate) isomorphism between monolingual embedding spaces.In this work we present a large-scale study focused on the correlations between monolingual embedding space similarity and task performance, covering thousands of language pairs and four different tasks: BLI, parsing, POS tagging and MT.We hypothesize that statistics of the spectrum of each monolingual embedding space indicate how well they can be aligned.We then introduce several isomorphism measures between two embedding spaces, based on the relevant statistics of their individual spectra.We empirically show that 1) language similarity scores derived from such spectral isomorphism measures are strongly associated with performance observed in different crosslingual tasks, and 2) our spectral-based measures consistently outperform previous standard isomorphism measures, while being computationally more tractable and easier to interpret.Finally, our measures capture complementary information to typologically driven language distance measures, and the combination of measures from the two families yields even higher task performance correlations.

Natural Language Inference (NLI) datasets contain annotation artefacts resulting in spurious correlations between the natural language utterances and their respective entailment classes.These artefacts are exploited by neural networks even when only considering the hypothesis and ignoring the premise, leading to unwanted biases.Belinkov et al. (2019b) proposed tackling this problem via adversarial training, but this can lead to learned sentence representations that still suffer from the same biases.We show that the bias can be reduced in the sentence representations by using an ensemble of adversaries, encouraging the model to jointly decrease the accuracy of these different adversaries while fitting the data.This approach produces more robust NLI models, outperforming previous de-biasing efforts when generalised to 12 other NLI datasets (Belinkov et al., 2019a;Mahabadi et al., 2020).In addition, we find that the optimal number of adversarial classifiers depends on the dimensionality of the sentence representations, with larger sentence representations being more difficult to de-bias while benefiting from using a greater number of adversaries.

State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment.We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise.We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset.We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.

The point of departure of this article is the claim that sense-specific vectors provide an advantage over normal vectors due to the polysemy that they presumably represent.This claim is based on performance gains observed in gold standard evaluation tests such as word similarity tasks.We demonstrate that this claim, at least as it is instantiated in prior art, is unfounded in two ways.Furthermore, we provide empirical data and an analytic discussion that may account for the previously reported improved performance.First, we show that ground-truth polysemy degrades performance in word similarity tasks.Therefore word similarity tasks are not suitable as an evaluation test for polysemy representation.Second, random assignment of words to senses is shown to improve performance in the same task.This and additional results point to the conclusion that performance gains as reported in previous work may be an artifact of random sense assignment, which is equivalent to sub-sampling and multiple estimation of word vector representations.Theoretical analysis shows that this may on its own be beneficial for the estimation of word similarity, by reducing the bias in the estimation of the cosine distance.

This article evaluates three proposed laws of semantic change.Our claim is that in order to validate a putative law of semantic change, the effect should be observed in the genuine condition but absent or reduced in a suitably matched control condition, in which no change can possibly have taken place.Our analysis shows that the effects reported in recent literature must be substantially revised: (i) the proposed negative correlation between meaning change and word frequency is shown to be largely an artefact of the models of word representation used; (ii) the proposed negative correlation between meaning change and prototypicality is shown to be much weaker than what has been claimed in prior art; and (iii) the proposed positive correlation between meaning change and polysemy is largely an artefact of word frequency.These empirical observations are corroborated by analytical proofs that show that count representations introduce an inherent dependence on word frequency, and thus word frequency cannot be evaluated as an independent factor with these representations.