Morocco

Text-only training is a promising new method for training multimodal machine learning models without data from every modality. However, few studies have explored its use as an approximation of missing data for supervised learning in data-scarce environments. In this work, we examine techniques to acquire text-based training data, address the modality gap, and present a case study on classifying subjective audio timbre descriptions based on three kinds of text-only training data and six augmentation methods on eight audio-timbre datasets. We find text-only training successfully trains supervised audio classifiers without audio that are able to compete with a zero-shot baseline and training on real audio.

EACL 2026

Audio Timbre Classification With Text-only Training

clap

text-only training

modality gap

timbre

audio

language

multimodal

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

workshop paper

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)* 

<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to EACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

A central limitation of current music understanding frameworks is the reliance on audio embeddings, which frequently yields interpretations lacking traceable ties to explicit musical elements such as notes, dynamics, and instrumentation. In this work, we address this gap with MIDI-PHOR, a midi-first framework that converts symbolic data into structured, queryable representations for reasoning. MIDI-PHOR distills each piece into three complementary views: a symbolic view capturing pitch, meter, and key; a time-series view that tracks rhythmic salience, texture, and role activity via symbolic proxies rather than unstable audio rendering; and an instrument-role graph encoding ensemble interactions. We distill these views into evidence-linked captions and evaluate them using a novel claim-verification protocol. Experiments demonstrate that MIDI-PHOR significantly reduces hallucinations compared to raw-midi baselines and offers a robust, auditable bridge between symbolic data and semantic music understanding.

MIDI-PHOR: Multi-View Distillation for Music Understanding and Captioning

This paper evaluates the effectiveness of large language models (LLMs) on the task of context-aware music recommendation, specifically focusing on the alignment of music tracks with a listening intent, in addition to user preferences. We present a preliminary investigation in which five LLMs (variants of LLama, Qwen, and Mistral) are tasked with ranking a candidate set of tracks containing both ground-truth items (associated with specific user-intent pairs) and distractor items (containing user-relevant, intent-relevant, or non-user and non-intent relevant items). Our results show that LLMs rank intent-user-relevant items higher than the distract items, with "Llama-3.1-8B-Instruct" having the best performance (NDCG of 0.32 vs. 0.20). We further investigate whether performance differs when mentioning the listening intent explicitly in the prompt vs. implicitly given solely music preferences. Surprisingly, the LLMs achieved the best performance through an implicit indication of intent, versus explicitly adding it to the prompt, with "Mistral-7B-Instruct-v0.3" performing the best (NDCG of 0.37 vs. 0.29).

Read Between the Tracks: Exploring LLM-driven Intent-based Music Recommendations

Playlist generation based on textual queries using large language models (LLMs) is becoming an important interaction paradigm for music streaming platforms. User queries span a wide spectrum from highly personalized intent to essentially catalog-style requests. Existing systems typically rely on non-personalized retrieval/ranking or apply a fixed level of preference conditioning to every query, which can overfit catalog queries to a single user or under-personalize explicitly listener-dependent requests. We present an industrial-scale LLM-based playlist generation system with dynamic personalization that adapts the personalization strength to the query type. We define a query taxonomy, train a query-type classifier on 5,000 manually labeled queries, and use its predicted probability to modulate the mixture of LLM-based semantic scoring and personalized evaluation. In a blind user study with pairwise comparisons and ELO aggregation, this approach consistently outperforms both non-personalized and fixed-personalization baselines.

Learning When to Personalize: LLM Based Playlist Generation via Query Taxonomy and Classification

The evaluation of music understanding in Large Audio-Language Models (LALMs) requires a rigorously defined benchmark that truly tests whether models can perceive and interpret music, a standard that current data methodologies frequently fail to meet. This paper introduces a meticulously structured approach to music evaluation, proposing a new dataset of 320 hand-written questions curated and validated by experts with musical training, arguing that such focused, manual curation is superior for probing complex audio comprehension. To demonstrate the use of the dataset, we benchmark six state-of-the-art LALMs and additionally test their robustness to uni-modal shortcuts.

HumMusQA: A Human-written Music Understanding QA Benchmark Dataset

With the conflation of digital and non-digital spaces, and NLP technologies being integrated into an increasing number of aspects of daily life, linguistic diversity cannot be fully understood without considering how language is used online. While existing models of linguistic diversity typically have relied on speaker numbers or language production, the dimension of diversity in language consumption remains comparatively understudied. To facilitate such research, we introduce WikiLingDiv, an openly accessible dataset for quantifying linguistic diversity in online knowledge retrieval using Wikipedia page views. Our dataset is based on yearly page views of 340 language editions of Wikipedia, aggregated across 239 countries and territories over 10 years (2015-2024). Using the dataset, we illustrate spatial and temporal patterns of digital linguistic diversity, suggesting that diversity has both increased and decreased across countries and regions, while highlighting country-specific dynamics in language usage. We release the dataset as an openly available and easily integrable data resource for researchers in computational linguistics, digital humanities, and the broader social sciences, enabling further work on linguistic variation, digital inequality, and the interaction between language use and digital technology.

WikiLingDiv: a dataset for quantifying digital linguistic diversity using Wikipedia page views

Large language models (LLMs) are post-trained on human feedback collected from annotator communities, yet the linguistic influence of these annotator communities on language models remains poorly understood. We investigated the stylistic transfer from Nigerian annotators to the LLaMA family of models through a natural experiment with LLaMA 2 and LLaMA 3.1, as their release dates are separated by the shutdown of a major data annotation service provider in Nigeria. We generated corpora from both model families and measured linguistic style by computing the difference-in-difference of the Jensen-Shannon distance on the bigram distribution between model outputs and corpora of Nigerian English and US English. We found that, although both pre-trained model variants exhibit similar proximity to both English variants, the LLaMA 2 post-trained model moved toward Nigerian English, while the LLaMA 3.1 post-trained model moved away from Nigerian English. Qualitatively, we found that post-trained LLaMA 2 models used significantly fewer contractions, in line with Nigerian English speakers opting to use a formal register due to its role as an index of knowledgeability. Our findings suggest that annotator communities can imprint linguistic style on large language models, with potential implications such as a disproportionately higher false positive rate in AI plagiarism detection for users who share a linguistic style with annotator communities.

Stylistic Transfer from Annotator Communities to Large Language Models

Indirect speech is a fundamental yet understudied form of reported speech that plays a crucial role in literary texts and communication. While direct speech detection has received significant attention in computational linguistics, the automatic identification of indirect speech remains a challenge due to its nuanced linguistic structure and contextual dependencies. This paper focuses on the detection of indirect speech in late 19th-century Scandinavian literature, where its presence has been linked to shifting aesthetic ideals. We present an annotated dataset of 150 segments, each randomly selected from 150 different novels, designed to capture indirect speech in Danish and Norwegian literature. We evaluate four pre-trained language models for classifying indirect speech, with results showing that a Danish Foundation Model (DFM Large), trained on extensive Danish data, has the highest performance. Finally, we conduct a classifier-assisted quantitative corpus analysis and find that the prevalence of indirect speech exhibits fluctuations over time.

Speaking on Their Behalf: Detecting Indirect Speech in Historical Danish and Norwegian Texts

Large Language Models (LLMs), even though exhibiting multiple capabilities on many NLP tasks, struggle with phonologically-grounded phenomena like rhyme detection and generation. When one moves to lower-resource languages such as Modern Greek, this is even more evident. In this paper, we present a hybrid neural-symbolic system that combines LLMs with deterministic phonological algorithms to achieve accurate rhyme identification and generation. We implement a comprehensive taxonomy of Greek rhyme types and employ an agentic generation pipeline with phonological verification. We use multiple prompting strategies (zero-shot, few-shot, Chain-of-Thought, and RAG-augmented) across several LLMs including Claude 3.7 and 4.5, GPT-4o, Gemini 2.0 and open-weight models like Llama 3.1 8B and 70B and Mistral Large. Results reveal a significant reasoning gap: while native-like models (Claude 3.7) perform intuitively (40% accuracy in identification), reasoning-heavy models (Claude 4.5) achieve state-of-the-art performance (54%) only when prompted with Chain-of-Thought. Most critically, pure LLM generation fails significantly (under 4% valid poems), while our hybrid verification loop restores performance to 73.1%. Along with the system presented, we further release a corpus of 40,000+ rhymes, derived from the Anemoskala and Interwar Poetry corpora, to support future research.

LLMs Got Rhyme? Hybrid Phonological Filtering for Greek Poetry Rhyme Detection and Generation

This paper investigates how language models (LMs) reproduce the existing gender disparity found in German media discourse about artificial intelligence (AI). Building on a human-annotated corpus of quotations from German media discourse on AI, we first quantify the frequency with which male and female speakers are directly cited across domains and speaker roles. We then train LLäMmlein (Pfister et al., 2025), a state-of-the-art German-only language model, GBERT, and a logistic regression model using only the quoted text as input and without providing any gender cues to classify the quotation as originating from a male or female speaker. By comparing model predictions with corpus-based gold labels, we find that male voices dominate both the corpus and the model predictions. Balancing the data mitigates but does not fully eliminate this disparity, indicating that the strong male-default tendency of transformer models cannot be explained by corpus skew alone, but also by their priors from pretraining. The study contributes to the interpretability of language models' output for DH-related tasks, adaptation of NLP tools to domain-specific humanities corpora, and knowledge modelling in the humanities.

Invisible Speakers? Gender Disparity in German AI Discourse and Its Reflection in Language Models

Graph-based Retrieval-Augmented Generation (RAG) is increasingly used to explore long, heterogeneous, and weakly structured corpora, including historical archives. However, in such settings, naive full-corpus indexing is often computationally costly and sensitive to OCR noise, document redundancy, and topical dispersion. In this paper, we investigate corpus pre-targeting strategies as an intermediate layer to improve the efficiency and effectiveness of graph-based RAG for historical research. We evaluate a set of pre-targeting heuristics tailored to single-hop and multi-hop of historical questions on HistoriQA-ThirdRepublic, a French question-answering dataset derived from parliamentary debates and contemporary newspapers. Our results show that appropriate pre-targeting strategies can improve retrieval recall by 3–5% while reducing token consumption by 32–37% compared to full-corpus indexing, without degrading coverage of relevant documents. Beyond performance gains, this work highlights the importance of corpus-level optimization for applying RAG to large-scale historical collections, and provides practical insights for adapting graph-based RAG pipelines to the specific constraints of digitized archives.

Downloads

Next from EACL 2026

MIDI-PHOR: Multi-View Distillation for Music Understanding and Captioning

Similar lecture

Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EACL 2026

MIDI-PHOR: Multi-View Distillation for Music Understanding and Captioning

Similar lecture

Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads