Antonios Anastasopoulos

Claytone Sikasote, Kalinda Siaminwe, Stanly Mwape et al. · cmu

This work introduces Zambezi Voice, an open-source multilingual speech resource for Zambian languages. It contains two collections of datasets: unlabelled audio recordings of radio news and talk shows programs (160 hours) and labelled data (over 80 hours) consisting of read speech recorded from text sourced from publicly available literature books. The dataset is created for speech recognition but can be extended to multilingual speech processing research for both supervised and unsupervised learning approaches. To our knowledge, this is the first multilingual speech dataset created for Zambian languages. We exploit pretraining and cross-lingual transfer learning by finetuning the Wav2Vec2.0 large-scale multilingual pre-trained model to build end-to-end (E2E) speech recognition models for our baseline models. The dataset is released publicly under a Creative Commons BY-NC-ND 4.0 license and can be accessed via https://github.com/unza-speech-lab/zambezi-voice .

Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa et al. · eth-zurich, microsoft-research

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 made on several fronts over the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 67 new languages, including 30 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g. missing gender and macron information. We have also 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.

Shruti Rijhwani, Daisy Rosenblum, Michayla King et al. · cmu

There has been recent interest in improving optical character recognition (OCR) for endangered languages, particularly because a large number of documents and books in these languages are not in machine-readable formats. The performance of OCR systems is typically evaluated using automatic metrics such as character and word error rates. While error rates are useful for the comparison of different models and systems, they do not measure whether and how the transcriptions produced from OCR tools are useful to downstream users. In this paper, we present a human-centric evaluation of OCR systems, focusing on the Kwak'wala language as a case study. With a user study, we show that utilizing OCR reduces the time spent in the manual transcription of culturally valuable documents -- a task that is often undertaken by endangered language community members and researchers -- by over 50%. Our results demonstrate the potential benefits that OCR tools can have on downstream language documentation and revitalization efforts.

Sachin Kumar, Vidhisha Balachandran, Lucille Njoo et al. · cmu

Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in user-facing settings. In parallel, these improvements have prompted a heated discourse around the risks of societal harms they introduce, whether inadvertent or malicious. Several studies have explored these harms and called for their mitigation via development of safer, fairer models. Going beyond enumerating the risks of harms, this work provides a survey of practical methods for addressing potential threats and societal harms from language generation models. We draw on several prior works' taxonomies of language model risks to present a structured overview of strategies for detecting and ameliorating different kinds of risks/harms of language generators. Bridging diverse strands of research, this survey aims to serve as a practical guide for both LM researchers and practitioners, with explanations of different mitigation strategies' motivations, their limitations, and open problems for future research.

Nathaniel Krasner, Miriam Wanner, Antonios Anastasopoulos · cmu

Recent work by Søgaard (2020) showed that, treebank size aside, overlap between training and test graphs (termed leakage) explains more of the observed variation in dependency parsing performance than other explanations. In this work we revisit this claim, testing it on more models and languages. We find that it only holds for zero-shot cross-lingual settings. We then propose a more fine-grained measure of such leakage which, unlike the original measure, not only explains but also correlates with observed performance variation. Code and data are available here: https://github.com/miriamwanner/reu-nlp-project

Amir Hussein, Brian Yan, Antonios Anastasopoulos et al. · cmu

Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST, enhancing coherence and overcoming memory constraints of extended audio segments. Additionally, we propose context dropout to ensure robustness to the absence of context, and further improve performance by adding speaker information. Our proposed contextual E2E-ST outperforms the isolated utterance-based E2E-ST approach. Lastly, we demonstrate that in conversational speech, contextual information primarily contributes to capturing context style, as well as resolving anaphora and named entities.

Aditi Chaudhary, Arun Sampath, Ashwin Sheshadri et al. · cmu

One of the challenges in language teaching is how best to organize rules regarding syntax, semantics, or phonology in a meaningful manner. This not only requires content creators to have pedagogical skills, but also have that language's deep understanding. While comprehensive materials to develop such curricula are available in English and some broadly spoken languages, for many other languages, teachers need to manually create them in response to their students' needs. This is challenging because i) it requires that such experts be accessible and have the necessary resources, and ii) describing all the intricacies of a language is time-consuming and prone to omission. In this work, we aim to facilitate this process by automatically discovering and visualizing grammar descriptions. We extract descriptions from a natural text corpus that answer questions about morphosyntax (learning of word order, agreement, case marking, or word formation) and semantics (learning of vocabulary). We apply this method for teaching two Indian languages, Kannada and Marathi, which, unlike English, do not have well-developed resources for second language learning. To assess the perceived utility of the extracted material, we enlist the help of language educators from schools in North America to perform a manual evaluation, who find the materials have potential to be used for their lesson preparation and learner evaluation.

Aditi Chaudhary, Arun Sampath, Ashwin Sheshadri et al. · cmu

One of the challenges of language teaching is how to organize the rules regarding syntax, semantics, or phonology of the language in a meaningful manner. This not only requires pedagogical skills, but also requires a deep understanding of that language. While comprehensive materials to develop such curricula are available in English and some broadly spoken languages, for many other languages, teachers need to manually create them in response to their students' needs. This process is challenging because i) it requires that such experts be accessible and have the necessary resources, and ii) even if there are such experts, describing all the intricacies of a language is time-consuming and prone to omission. In this article, we present an automatic framework that aims to facilitate this process by automatically discovering and visualizing descriptions of different aspects of grammar. Specifically, we extract descriptions from a natural text corpus that answer questions about morphosyntax (learning of word order, agreement, case marking, or word formation) and semantics (learning of vocabulary) and show illustrative examples. We apply this method for teaching the Indian languages, Kannada and Marathi, which, unlike English, do not have well-developed pedagogical resources and, therefore, are likely to benefit from this exercise. To assess the perceived utility of the extracted material, we enlist the help of language educators from schools in North America who teach these languages to perform a manual evaluation. Overall, teachers find the materials to be interesting as a reference material for their own lesson preparation or even for learner evaluation.

Aditi Chaudhary, Zaid Sheikh, David R Mortensen et al. · cmu

Each language has its own complex systems of word, phrase, and sentence construction, the guiding principles of which are often summarized in grammar descriptions for the consumption of linguists or language learners. However, manual creation of such descriptions is a fraught process, as creating descriptions which describe the language in "its own terms" without bias or error requires both a deep understanding of the language at hand and linguistics as a whole. We propose an automatic framework AutoLEX that aims to ease linguists' discovery and extraction of concise descriptions of linguistic phenomena. Specifically, we apply this framework to extract descriptions for three phenomena: morphological agreement, case marking, and word order, across several languages. We evaluate the descriptions with the help of language experts and propose a method for automated evaluation when human evaluation is infeasible.

Brian Yan, Xuankai Chang, Antonios Anastasopoulos et al. · cmu

Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal representation. In this work, we instead propose a ST/MT multi-tasking framework with hard parameter sharing in which all model parameters are shared cross-modally. Our method reduces the speech-text modality gap via a pre-processing stage which converts speech and text inputs into two discrete token sequences of similar length -- this allows models to indiscriminately process both modalities simply using a joint vocabulary. With experiments on MuST-C, we demonstrate that our multi-tasking framework improves attentional encoder-decoder, Connectionist Temporal Classification (CTC), transducer, and joint CTC/attention models by an average of +0.5 BLEU without any external MT data. Further, we show that this framework incorporates external MT data, yielding +0.8 BLEU, and also improves transfer learning from pre-trained textual models, yielding +1.8 BLEU.

Fahim Faisal, Antonios Anastasopoulos · cmu

Large pretrained multilingual models, trained on dozens of languages, have delivered promising results due to cross-lingual learning capabilities on variety of language tasks. Further adapting these models to specific languages, especially ones unseen during pre-training, is an important goal towards expanding the coverage of language technologies. In this study, we show how we can use language phylogenetic information to improve cross-lingual transfer leveraging closely related languages in a structured, linguistically-informed manner. We perform adapter-based training on languages from diverse language families (Germanic, Uralic, Tupian, Uto-Aztecan) and evaluate on both syntactic and semantic tasks, obtaining more than 20% relative performance improvements over strong commonly used baselines, especially on languages unseen during pre-training.

Fahim Faisal, Antonios Anastasopoulos · cmu

Pretrained language models (PLMs) often fail to fairly represent target users from certain world regions because of the under-representation of those regions in training datasets. With recent PLMs trained on enormous data sources, quantifying their potential biases is difficult, due to their black-box nature and the sheer scale of the data sources. In this work, we devise an approach to study the geographic bias (and knowledge) present in PLMs, proposing a Geographic-Representation Probing Framework adopting a self-conditioning method coupled with entity-country mappings. Our findings suggest PLMs' representations map surprisingly well to the physical world in terms of country-to-country associations, but this knowledge is unequally shared across languages. Last, we explain how large PLMs despite exhibiting notions of geographical proximity, over-amplify geopolitical favouritism at inference time.

Sina Ahmadi, Milind Agarwal, Antonios Anastasopoulos · cmu

The Perso-Arabic scripts are a family of scripts that are widely adopted and used by various linguistic communities around the globe. Identifying various languages using such scripts is crucial to language technologies and challenging in low-resource setups. As such, this paper sheds light on the challenges of detecting languages using Perso-Arabic scripts, especially in bilingual communities where ``unconventional'' writing is practiced. To address this, we use a set of supervised techniques to classify sentences into their languages. Building on these, we also propose a hierarchical model that targets clusters of languages that are more often confused by the classifiers. Our experiment results indicate the effectiveness of our solutions.

Sina Ahmadi, Zahra Azin, Sara Belelli et al. · cmu

One of the major challenges that under-represented and endangered language communities face in language technology is the lack or paucity of language data. This is also the case of the Southern varieties of the Kurdish and Laki languages for which very limited resources are available with insubstantial progress in tools. To tackle this, we provide a few approaches that rely on the content of local news websites, a local radio station that broadcasts content in Southern Kurdish and fieldwork for Laki. In this paper, we describe some of the challenges of such under-represented languages, particularly in writing and standardization, and also, in retrieving sources of data and retro-digitizing handwritten content to create a corpus for Southern Kurdish and Laki. In addition, we study the task of language identification in light of the other variants of Kurdish and Zaza-Gorani languages.

Md Mushfiqur Rahman, Fardin Ahsan Sakib, Fahim Faisal et al. · cmu

Choosing an appropriate tokenization scheme is often a bottleneck in low-resource cross-lingual transfer. To understand the downstream implications of text representation choices, we perform a comparative analysis on language models having diverse text representation modalities including 2 segmentation-based models (\texttt{BERT}, \texttt{mBERT}), 1 image-based model (\texttt{PIXEL}), and 1 character-level model (\texttt{CANINE}). First, we propose a scoring Language Quotient (LQ) metric capable of providing a weighted representation of both zero-shot and few-shot evaluation combined. Utilizing this metric, we perform experiments comprising 19 source languages and 133 target languages on three tasks (POS tagging, Dependency parsing, and NER). Our analysis reveals that image-based models excel in cross-lingual transfer when languages are closely related and share visually similar scripts. However, for tasks biased toward word meaning (POS, NER), segmentation-based models prove to be superior. Furthermore, in dependency parsing tasks where word relationships play a crucial role, models with their character-level focus, outperform others. Finally, we propose a recommendation scheme based on our findings to guide model selection according to task and language requirements.

Md Mahfuz Ibn Alam, Ruoyu Xie, Fahim Faisal et al. · cmu

This report describes GMU's sentiment analysis system for the SemEval-2023 shared task AfriSenti-SemEval. We participated in all three sub-tasks: Monolingual, Multilingual, and Zero-Shot. Our approach uses models initialized with AfroXLMR-large, a pre-trained multilingual language model trained on African languages and fine-tuned correspondingly. We also introduce augmented training data along with original training data. Alongside finetuning, we perform phylogeny-based adapter tuning to create several models and ensemble the best models for the final submission. Our system achieves the best F1-score on track 5: Amharic, with 6.2 points higher F1-score than the second-best performing system on this track. Overall, our system ranks 5th among the 10 systems participating in all 15 tracks.

Ruoyu Xie, Antonios Anastasopoulos · cmu

An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of resources required to train and evaluate models, most modern language technologies are either nonexistent or unreliable to process endangered, local, and non-standardized languages. Optical character recognition (OCR) is often used to convert endangered language documents into machine-readable data. However, such OCR output is typically noisy, and most word alignment models are not built to work under such noisy conditions. In this work, we study the existing word-level alignment models under noisy settings and aim to make them more robust to noisy data. Our noise simulation and structural biasing method, tested on multiple language pairs, manages to reduce the alignment error rate on a state-of-the-art neural-based alignment model up to 59.6%.

Cristian Ahumada, Claudio Gutierrez, Antonios Anastasopoulos · cmu

Mapuzugun is the language of the Mapuche people. Due to political and historical reasons, its number of speakers has decreased and the language has been excluded from the educational system in Chile and Argentina. For this reason, it is very important to support the revitalization of the Mapuzugun in all spaces and media of society. In this work we present a tool towards supporting educational activities of Mapuzugun, tailored to the characteristics of the language. The tool consists of three parts: design and development of an orthography detector and converter; a morphological analyzer; and an informal translator. We also present a case study with Mapuzugun students showing promising results. Short Abstract in Mapuzuzgun: Tüfachi küzaw pegelfi kiñe zugun küzawpeyüm kelluaetew pu mapuzugun chillkatufe kimal kizu tañi zugun.

Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan et al.

Large Language Models (LLMs) perpetuate social biases, reflecting prejudices in their training data and reinforcing societal stereotypes and inequalities. Our work explores the potential of the Contact Hypothesis, a concept from social psychology for debiasing LLMs. We simulate various forms of social contact through LLM prompting to measure their influence on the model's biases, mirroring how intergroup interactions can reduce prejudices in social contexts. We create a dataset of 108,000 prompts following a principled approach replicating social contact to measure biases in three LLMs (LLaMA 2, Tulu, and NousHermes) across 13 social bias dimensions. We propose a unique debiasing technique, Social Contact Debiasing (SCD), that instruction-tunes these models with unbiased responses to prompts. Our research demonstrates that LLM responses exhibit social biases when subject to contact probing, but more importantly, these biases can be significantly reduced by up to 40% in 1 epoch of instruction tuning LLaMA 2 following our SCD strategy. Our code and data are available at https://github.com/chahatraj/breakingbias.

Anjishnu Mukherjee, Chahat Raj, Ziwei Zhu et al.

Human biases are ubiquitous but not uniform: disparities exist across linguistic, cultural, and societal borders. As large amounts of recent literature suggest, language models (LMs) trained on human data can reflect and often amplify the effects of these social biases. However, the vast majority of existing studies on bias are heavily skewed towards Western and European languages. In this work, we scale the Word Embedding Association Test (WEAT) to 24 languages, enabling broader studies and yielding interesting findings about LM bias. We additionally enhance this data with culturally relevant information for each language, capturing local contexts on a global scale. Further, to encompass more widely prevalent societal biases, we examine new bias dimensions across toxicity, ableism, and more. Moreover, we delve deeper into the Indian linguistic landscape, conducting a comprehensive regional bias analysis across six prevalent Indian languages. Finally, we highlight the significance of these social biases and the new dimensions through an extensive comparison of embedding methods, reinforcing the need to address them in pursuit of more equitable language models. All code, data and results are available here: https://github.com/iamshnoo/weathub.

Prabin Bhandari, Antonios Anastasopoulos, Dieter Pfoser

Understanding urban mobility patterns and analyzing how people move around cities helps improve the overall quality of life and supports the development of more livable, efficient, and sustainable urban areas. A challenging aspect of this work is the collection of mobility data by means of user tracking or travel surveys, given the associated privacy concerns, noncompliance, and high cost. This work proposes an innovative AI-based approach for synthesizing travel surveys by prompting large language models (LLMs), aiming to leverage their vast amount of relevant background knowledge and text generation capabilities. Our study evaluates the effectiveness of this approach across various U.S. metropolitan areas by comparing the results against existing survey data at different granularity levels. These levels include (i) pattern level, which compares aggregated metrics like the average number of locations traveled and travel time, (ii) trip level, which focuses on comparing trips as whole units using transition probabilities, and (iii) activity chain level, which examines the sequence of locations visited by individuals. Our work covers several proprietary and open-source LLMs, revealing that open-source base models like Llama-2, when fine-tuned on even a limited amount of actual data, can generate synthetic data that closely mimics the actual travel survey data, and as such provides an argument for using such data in mobility studies.

Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan et al.

Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the Dataset of retrieved associations, (Dora), publicly available here https://github.com/chahatraj/BiasDora.

Prabin Bhandari, Antonios Anastasopoulos, Dieter Pfoser

Despite the impressive performance of Large Language Models (LLM) for various natural language processing tasks, little is known about their comprehension of geographic data and related ability to facilitate informed geospatial decision-making. This paper investigates the extent of geospatial knowledge, awareness, and reasoning abilities encoded within such pretrained LLMs. With a focus on autoregressive language models, we devise experimental approaches related to (i) probing LLMs for geo-coordinates to assess geospatial knowledge, (ii) using geospatial and non-geospatial prepositions to gauge their geospatial awareness, and (iii) utilizing a multidimensional scaling (MDS) experiment to assess the models' geospatial reasoning capabilities and to determine locations of cities based on prompting. Our results confirm that it does not only take larger, but also more sophisticated LLMs to synthesize geospatial knowledge from textual information. As such, this research contributes to understanding the potential and limitations of LLMs in dealing with geospatial information.

Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos

We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated by DALL-E 3 and validated by humans, containing 9,935 images of 67 countries and 10 concept classes; (2) the underlying implicit and potentially stereotypical cultural associations with a cultural artifact extraction task; and (3) an approach to adapt cultural representation in an image based on extracted associations using a modular pipeline, CultureAdapt. We find disparities in cultural understanding at geographic sub-region levels with both open-source (LLaVA) and closed-source (GPT-4V) models on DalleStreet and other existing benchmarks, which we try to understand using over 18,000 artifacts that we identify in association to different countries. Our findings reveal a nuanced picture of the cultural competence of LMMs, highlighting the need to develop culture-aware systems. Dataset and code are available at https://github.com/iamshnoo/crossroads

Angeela Acharya, Sulabh Shrestha, Anyi Chen et al.

The utilization of Electronic Health Records (EHRs) for clinical risk prediction is on the rise. However, strict privacy regulations limit access to comprehensive health records, making it challenging to apply standard machine learning algorithms in practical real-world scenarios. Previous research has addressed this data limitation by incorporating medical ontologies and employing transfer learning methods. In this study, we investigate the potential of leveraging language models (LMs) as a means to incorporate supplementary domain knowledge for improving the performance of various EHR-based risk prediction tasks. Unlike applying LMs to unstructured EHR data such as clinical notes, this study focuses on using textual descriptions within structured EHR to make predictions exclusively based on that information. We extensively compare against previous approaches across various data types and sizes. We find that employing LMs to represent structured EHRs, such as diagnostic histories, leads to improved or at least comparable performance in diverse risk prediction tasks. Furthermore, LM-based approaches offer numerous advantages, including few-shot learning, the capability to handle previously unseen medical concepts, and adaptability to various medical vocabularies. Nevertheless, we underscore, through various experiments, the importance of being cautious when employing such models, as concerns regarding the reliability of LMs persist.

Antonios Anastasopoulos, Giuseppe Ateniese, Evgenios M. Kornaropoulos

Recent results in learning a language in the limit have shown that, although language identification is impossible, language generation is tractable. As this foundational area expands, we need to consider the implications of language generation in real-world settings. This work offers the first theoretical treatment of safe language generation. Building on the computational paradigm of learning in the limit, we formalize the tasks of safe language identification and generation. We prove that under this model, safe language identification is impossible, and that safe language generation is at least as hard as (vanilla) language identification, which is also impossible. Last, we discuss several intractable and tractable cases.

Md Nishat Raihan, Umma Hani Tanmoy, Anika Binte Islam et al.

Identifying offensive content in social media is vital for creating safe online communities. Several recent studies have addressed this problem by creating datasets for various languages. In this paper, we explore offensive language identification in texts with transliterations and code-mixing, linguistic phenomena common in multilingual societies, and a known challenge for NLP systems. We introduce TB-OLID, a transliterated Bangla offensive language dataset containing 5,000 manually annotated comments. We train and fine-tune machine learning models on TB-OLID, and we evaluate their results on this dataset. Our results show that English pre-trained transformer-based models, such as fBERT and HateBERT achieve the best performance on this dataset.

Md Nishat Raihan, Dhiman Goswami, Antara Mahmud et al.

Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several datasets have been build with the goal of training computational models for code-mixing. Although it is very common to observe code-mixing with multiple languages, most datasets available contain code-mixed between only two languages. In this paper, we introduce SentMix-3L, a novel dataset for sentiment analysis containing code-mixed data between three languages Bangla, English, and Hindi. We carry out a comprehensive evaluation using SentMix-3L. We show that zero-shot prompting with GPT-3.5 outperforms all transformer-based models on SentMix-3L.

Fahim Faisal, Orevaoghene Ahia, Aarohi Srivastava et al.

Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied variety datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different language varieties. We provide substantial evidence of performance disparities between standard and non-standard language varieties, and we also identify language clusters with large performance divergence across tasks. We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for language varieties and one step towards advancing it further. Code/data: https://github.com/ffaisal93/DialectBench

Jonathan Mbuya, Dieter Pfoser, Antonios Anastasopoulos

This paper presents a novel approach for trajectory anomaly detection using an autoregressive causal-attention model, termed LM-TAD. This method leverages the similarities between language statements and trajectories, both of which consist of ordered elements requiring coherence through external rules and contextual variations. By treating trajectories as sequences of tokens, our model learns the probability distributions over trajectories, enabling the identification of anomalous locations with high precision. We incorporate user-specific tokens to account for individual behavior patterns, enhancing anomaly detection tailored to user context. Our experiments demonstrate the effectiveness of LM-TAD on both synthetic and real-world datasets. In particular, the model outperforms existing methods on the Pattern of Life (PoL) dataset by detecting user-contextual anomalies and achieves competitive results on the Porto taxi dataset, highlighting its adaptability and robustness. Additionally, we introduce the use of perplexity and surprisal rate metrics for detecting outliers and pinpointing specific anomalous locations within trajectories. The LM-TAD framework supports various trajectory representations, including GPS coordinates, staypoints, and activity types, proving its versatility in handling diverse trajectory data. Moreover, our approach is well-suited for online trajectory anomaly detection, significantly reducing computational latency by caching key-value states of the attention mechanism, thereby avoiding repeated computations.

Dhiman Goswami, Md Nishat Raihan, Antara Mahmud et al.

Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several works have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce OffMix-3L, a novel offensive language identification dataset containing code-mixed data from three different languages. We experiment with several models on this dataset and observe that BanglishBERT outperforms other transformer-based models and GPT-3.5.

Anjishnu Mukherjee, Chutong Meng, Antonios Anastasopoulos

This paper argues that contemporary multilingual NLP has converged on a fragile and misleading paradigm of incidental multilingualism. Today's LLMs appear multilingual largely because they are trained on massive, uneven web corpora, not because multilingual or multicultural competence has been treated as a core design objective. We contend that this paradigm systematically produces unequal, brittle, and opaque behavior across languages, with severe consequences in real-world and agentic deployments where models must reason, plan, and act across multiple linguistic contexts. We report a focused empirical study of two practical questions: which languages models self-report as supported and which languages they actually respond in across multilingual prompts. We additionally demonstrate how even a simple language-change attack can surface these failures and expose hidden assumptions about language in LLM-based systems. To address this, we call for a shift toward multilingualism by design: a research agenda that treats equitable multilingual performance, cultural grounding, and cross-lingual behavioral understanding as first-class goals in all aspects of the model pipeline.

Sina Ahmadi, Daban Q. Jaff, Md Mahfuz Ibn Alam et al. · cmu

Kurdish, an Indo-European language spoken by over 30 million speakers, is considered a dialect continuum and known for its diversity in language varieties. Previous studies addressing language and speech technology for Kurdish handle it in a monolithic way as a macro-language, resulting in disparities for dialects and varieties for which there are few resources and tools available. In this paper, we take a step towards developing resources for language and speech technology for varieties of Central Kurdish, creating a corpus by transcribing movies and TV series as an alternative to fieldwork. Additionally, we report the performance of machine translation, automatic speech recognition, and language identification as downstream tasks evaluated on Central Kurdish varieties. Data and models are publicly available under an open license at https://github.com/sinaahmadi/CORDI.

Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos

Large language models are typically trained by treating text as a single global distribution, often resulting in geographically homogenized behavior. We study metadata conditioning as a lightweight approach for localization, pre-training 31 models (at 0.5B and 1B parameter scales) from scratch on large-scale English news data annotated with verified URLs, country tags, and continent tags, covering 4 continents and 17 countries. Across four controlled experiments, we show that metadata conditioning consistently improves in-region performance without sacrificing cross-region generalization, enables global models to recover localization comparable to region-specific models, and improves learning efficiency. Our ablation studies demonstrate that URL-level metadata alone captures much of the geographic signal, while balanced regional data coverage remains essential, as metadata cannot fully compensate for missing regions. Finally, we introduce a downstream benchmark of 800 localized news MCQs and show that after instruction tuning, metadata conditioned global models achieve accuracy comparable to LLaMA-3.2-1B-Instruct, despite being trained on substantially less data. Together, these results establish metadata conditioning as a practical and compute-efficient approach for localization of language models.

Fahim Faisal, Md Mushfiqur Rahman, Antonios Anastasopoulos

There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators ("LLM-as-a-judge") is a growing research area, their sensitivity to dialectal nuances is still underexplored and requires more focused attention. In this paper, we address these gaps through a comprehensive toxicity evaluation of LLMs across diverse dialects. We create a multi-dialect dataset through synthetic transformations and human-assisted translations, covering 10 language clusters and 60 varieties. We then evaluated three LLMs on their ability to assess toxicity across multilingual, dialectal, and LLM-human consistency. Our findings show that LLMs are sensitive in handling both multilingual and dialectal variations. However, if we have to rank the consistency, the weakest area is LLM-human agreement, followed by dialectal consistency. Code repository: \url{https://github.com/ffaisal93/dialect_toxicity_llm_judge}

Fahim Faisal, Antonios Anastasopoulos

This report presents GMUNLP's participation to the Dialect-Copa shared task at VarDial 2024, which focuses on evaluating the commonsense reasoning capabilities of large language models (LLMs) on South Slavic micro-dialects. The task aims to assess how well LLMs can handle non-standard dialectal varieties, as their performance on standard languages is already well-established. We propose an approach that combines the strengths of different types of language models and leverages data augmentation techniques to improve task performance on three South Slavic dialects: Chakavian, Cherkano, and Torlak. We conduct experiments using a language-family-focused encoder-based model (BERTić) and a domain-agnostic multilingual model (AYA-101). Our results demonstrate that the proposed data augmentation techniques lead to substantial performance gains across all three test datasets in the open-source model category. This work highlights the practical utility of data augmentation and the potential of LLMs in handling non-standard dialectal varieties, contributing to the broader goal of advancing natural language understanding in low-resource and dialectal settings. Code:https://github.com/ffaisal93/dialect_copa

Fahim Faisal, Antonios Anastasopoulos

The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully understood, especially in the complex setting of massively multilingual LMs. We propose an \textit{efficient} method to study transfer language influence in zero-shot performance on another target language. Unlike previous work, our approach disentangles downstream tasks from language, using dedicated adapter units. Our findings suggest that some languages do not largely affect others, while some languages, especially ones unseen during pre-training, can be extremely beneficial or detrimental for different target languages. We find that no transfer language is beneficial for all target languages. We do, curiously, observe languages previously unseen by MLMs consistently benefit from transfer from almost any language. We additionally use our modular approach to quantify negative interference efficiently and categorize languages accordingly. Furthermore, we provide a list of promising transfer-target language configurations that consistently lead to target language performance improvements. Code and data are publicly available: https://github.com/ffaisal93/neg_inf

Nishat Raihan, Antonios Anastasopoulos, Marcos Zampieri

Despite being the 5th most spoken language, Bangla remains underrepresented in Large Language Models (LLMs), particularly for code generation. This primarily stems from the scarcity of high-quality data to pre-train and/or finetune such models. Hence, we introduce the first dedicated family of Code LLMs for Bangla (1B & 9B). We offer three major contributions: (1) a comprehensive Bangla code instruction datasets for programming domain adaptation; (2) MBPP-Bangla, an evaluation benchmark for Bangla code generation; and (3) the TigerCoder-family of Code LLMs, achieving significant ~11-18% performance gains at Pass@1 over existing multilingual and general-purpose Bangla LLMs. Our findings show that curated, high-quality datasets can overcome limitations of smaller models for low-resource languages. We open-source all resources to advance further Bangla LLM research.

Sam Blouir, Jimmy T. H. Smith, Antonios Anastasopoulos et al.

Efficient state space models (SSMs), such as linear recurrent neural networks and linear attention variants, offer computational advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associative recall, and question answering over long contexts. Previous efforts to address these challenges have focused on architectural modifications, often reintroducing computational inefficiencies. In this paper, we propose a novel training procedure, Birdie, that significantly enhances the in-context retrieval capabilities of SSMs without altering their architecture. Our approach combines bidirectional input processing with dynamic mixtures of specialized pre-training objectives, optimized via reinforcement learning. We introduce a new bidirectional SSM architecture that seamlessly transitions from bidirectional context processing to causal generation. Experimental evaluations demonstrate that Birdie markedly improves performance on retrieval-intensive tasks such as multi-number phone book lookup, long paragraph question-answering, and infilling. This narrows the performance gap with Transformers, while retaining computational efficiency. Our findings highlight the importance of training procedures in leveraging the fixed-state capacity of SSMs, offering a new direction to advance their capabilities. All code and pre-trained models are available at https://www.github.com/samblouir/birdie, with support for JAX and PyTorch.

Zaid Sheikh, Antonios Anastasopoulos, Shruti Rijhwani et al. · cmu

Effectively using Natural Language Processing (NLP) tools in under-resourced languages requires a thorough understanding of the language itself, familiarity with the latest models and training methodologies, and technical expertise to deploy these models. This could present a significant obstacle for language community members and linguists to use NLP tools. This paper introduces the CMU Linguistic Annotation Backend, an open-source framework that simplifies model deployment and continuous human-in-the-loop fine-tuning of NLP models. CMULAB enables users to leverage the power of multilingual models to quickly adapt and extend existing tools for speech recognition, OCR, translation, and syntactic analysis to new languages, even with limited training data. We describe various tools and APIs that are currently available and how developers can easily add new models/functionality to the framework. Code is available at https://github.com/neulab/cmulab along with a live demo at https://cmulab.dev

Pooya Fayyazsanavi, Antonios Anastasopoulos, Jana Košecká

Sign language translation from video to spoken text presents unique challenges owing to the distinct grammar, expression nuances, and high variation of visual appearance across different speakers and contexts. The intermediate gloss annotations of videos aim to guide the translation process. In our work, we focus on {\em Gloss2Text} translation stage and propose several advances by leveraging pre-trained large language models (LLMs), data augmentation, and novel label-smoothing loss function exploiting gloss translation ambiguities improving significantly the performance of state-of-the-art approaches. Through extensive experiments and ablation studies on the PHOENIX Weather 2014T dataset, our approach surpasses state-of-the-art performance in {\em Gloss2Text} translation, indicating its efficacy in addressing sign language translation and suggesting promising avenues for future research and development.

Claytone Sikasote, Eunice Mukonde, Md Mahfuz Ibn Alam et al.

We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on speech recognition (ASR), machine translation (MT) and speech translation (ST) tasks, and sketch out other potential future multimodal uses of our dataset. We hope that by making the dataset available to the research community, this work will foster research and encourage collaboration across the language, speech, and vision communities especially for languages outside the "traditionally" used high-resourced ones. All data and code are publicly available: https://github.com/csikasote/bigc.

Fahim Faisal, Yinkai Wang, Antonios Anastasopoulos

As language technologies become more ubiquitous, there are increasing efforts towards expanding the language diversity and coverage of natural language processing (NLP) systems. Arguably, the most important factor influencing the quality of modern NLP systems is data availability. In this work, we study the geographical representativeness of NLP datasets, aiming to quantify if and by how much do NLP datasets match the expected needs of the language speakers. In doing so, we use entity recognition and linking systems, also making important observations about their cross-lingual consistency and giving suggestions for more robust evaluation. Last, we explore some geographical and economic factors that may explain the observed dataset distributions. Code and data are available here: https://github.com/ffaisal93/dataset_geography. Additional visualizations are available here: https://nlp.cs.gmu.edu/project/datasetmaps/.

Fahim Faisal, Sharlina Keshava, Md Mahfuz ibn Alam et al.

Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces. However, current benchmarks in QA research do not account for the errors that speech recognition models might introduce, nor do they consider the language variations (dialects) of the users. To address this gap, we augment an existing QA dataset to construct a multi-dialect, spoken QA benchmark on five languages (Arabic, Bengali, English, Kiswahili, Korean) with more than 68k audio prompts in 24 dialects from 255 speakers. We provide baseline results showcasing the real-world performance of QA systems and analyze the effect of language variety and other sensitive speaker attributes on downstream performance. Last, we study the fairness of the ASR and QA models with respect to the underlying user populations. The dataset, model outputs, and code for reproducing all our experiments are available: https://github.com/ffaisal93/SD-QA.

Fahim Faisal, Antonios Anastasopoulos

Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all languages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pre-trained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc fine-tuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems. Code and dataset are publicly available here: https://github.com/ffaisal93/aligned_qa

Aditi Chaudhary, Kayo Yin, Antonios Anastasopoulos et al.

Learning fine-grained distinctions between vocabulary items is a key challenge in learning a new language. For example, the noun "wall" has different lexical manifestations in Spanish -- "pared" refers to an indoor wall while "muro" refers to an outside wall. However, this variety of lexical distinction may not be obvious to non-native learners unless the distinction is explained in such a way. In this work, we present a method for automatically identifying fine-grained lexical distinctions, and extracting concise descriptions explaining these distinctions in a human- and machine-readable format. We confirm the quality of these extracted descriptions in a language learning setup for two languages, Spanish and Greek, where we use them to teach non-native speakers when to translate a given ambiguous word into its different possible translations. Code and data are publicly released here (https://github.com/Aditi138/LexSelection)

Md Mahfuz ibn Alam, Antonios Anastasopoulos, Laurent Besacier et al.

As neural machine translation (NMT) systems become an important part of professional translator pipelines, a growing body of work focuses on combining NMT with terminologies. In many scenarios and particularly in cases of domain adaptation, one expects the MT output to adhere to the constraints provided by a terminology. In this work, we propose metrics to measure the consistency of MT output with regards to a domain terminology. We perform studies on the COVID-19 domain over 5 languages, also performing terminology-targeted human evaluation. We open-source the code for computing all proposed metrics: https://github.com/mahfuzibnalam/terminology_evaluation

Arnab Debnath, Navid Rajabi, Fardina Fathmiul Alam et al.

Question answering (QA) in English has been widely explored, but multilingual datasets are relatively new, with several methods attempting to bridge the gap between high- and low-resourced languages using data augmentation through translation and cross-lingual transfer. In this project, we take a step back and study which approaches allow us to take the most advantage of existing resources in order to produce QA systems in many languages. Specifically, we perform extensive analysis to measure the efficacy of few-shot approaches augmented with automatic translations and permutations of context-question-answer pairs. In addition, we make suggestions for future dataset development efforts that make better use of a fixed annotation budget, with a goal of increasing the language coverage of QA datasets and systems. Code and data for reproducing our experiments are available here: https://github.com/NavidRajabi/EMQA.

Claytone Sikasote, Antonios Anastasopoulos

We present a preprocessed, ready-to-use automatic speech recognition corpus, BembaSpeech, consisting over 24 hours of read speech in the Bemba language, a written but low-resourced language spoken by over 30% of the population in Zambia. To assess its usefulness for training and testing ASR systems for Bemba, we train an end-to-end Bemba ASR system by fine-tuning a pre-trained DeepSpeech English model on the training portion of the BembaSpeech corpus. Our best model achieves a word error rate (WER) of 54.78%. The results show that the corpus can be used for building ASR systems for Bemba. The corpus and models are publicly released at https://github.com/csikasote/BembaSpeech.

Md Mosharaf Hossain, Antonios Anastasopoulos, Eduardo Blanco et al.

As machine translation (MT) systems progress at a rapid pace, questions of their adequacy linger. In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. We investigate whether translating negation is an issue for modern MT systems using 17 translation directions as test bed. Through thorough analysis, we find that indeed the presence of negation can significantly impact downstream quality, in some cases resulting in quality reductions of more than 60%. We also provide a linguistically motivated analysis that directly explains the majority of our findings. We release our annotations and code to replicate our analysis here: https://github.com/mosharafhossain/negation-mt.