Austria

This paper addresses the constraints of down-stream applications of pre-trained language models (PLMs) for low-resource languages. These constraints are pre-train data deficiency preventing a low-resource language from being well represented in a PLM and inaccessibility of high-quality task-specific data annotation that limits task learning. We propose to use automatically labeled texts combined with manually annotated data in a two-stage task fine-tuning approach. The experiments revealed that utilizing such methodology combined with vocabulary adaptation may compensate for the absence of a targeted PLM or the deficiency of manually annotated data. The methodology is validated on the morphological tagging task for the Udmurt language. We publish our best model that achieved 93.25% token accuracy on HuggingFace Hub along with the training code1.

ACL 2025

Combining Automated and Manual Data for Effective Downstream Fine-Tuning of Transformers for Low-Resource Language Applications

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 ACL 2025". 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 need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Transformer-based models have demonstrated significant success in various source code representation tasks. Nonetheless, traditional positional embeddings employed by these models inadequately capture the hierarchical structure intrinsic to source code, typically represented as Abstract Syntax Trees (ASTs). To address this, we propose a novel tree-based positional embedding approach that explicitly encodes hierarchical relationships derived from ASTs, including node depth and sibling indices. These hierarchical embeddings are integrated into the transformer architecture, specifically enhancing the CodeBERTa model. We thoroughly evaluate our proposed model through masked language modeling (MLM) pretraining and clone detection fine-tuning tasks. Experimental results indicate that our Tree-Enhanced CodeBERTa consistently surpasses the baseline model in terms of loss, accuracy, F1 score, precision, and recall, emphasizing the importance of incorporating explicit structural information into transformer-based representations of source code.

Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation

We investigate the capabilities of the openly available Llama 3.2 1B language model for Abstract Meaning Representation (AMR) parsing through supervised fine-tuning, further enhanced by reinforcement learning via Group Relative Policy Optimization (GRPO). Existing supervised methods for AMR parsing face limitations due to static loss functions and challenges in capturing complex semantic phenomena. To address this, our GRPO-based approach explicitly optimizes fine-grained semantic rewards, including Smatch scores, frame-argument correctness, and structural validity of logical operations. Experimental results show that supervised fine-tuning alone establishes Llama as a capable English AMR parser, and subsequent GRPO fine-tuning further improves its performance. Our final model achieves higher Smatch scores, consistently respects critical low-level semantic constraints, and outperforms existing parsers on high-level semantic evaluation metrics across diverse linguistic phenomena.

Enhancing AMR Parsing with Group Relative Policy Optimization

Non-factoid question answering (NFQA) poses a significant challenge due to its open-ended nature, diverse intents, and the necessity for multi-aspect reasoning, rendering conventional retrieval-augmented generation (RAG) approaches insufficient. To address this, we introduce Typed-RAG, a type-aware framework utilizing multi-aspect query decomposition tailored specifically for NFQA. Typed-RAG categorizes NFQs into distinct types—such as debate, experience, and comparison—and decomposes them into single-aspect sub-queries for targeted retrieval and generation. By synthesizing the retrieved results of these sub-queries, Typed-RAG generates more informative and contextually relevant responses. Additionally, we present Wiki-NFQA, a novel benchmark dataset encompassing diverse NFQ types. Experimental evaluation demonstrates that TypeRAG consistently outperforms baseline approaches, confirming the effectiveness of type-aware decomposition in improving both retrieval quality and answer generation for NFQA tasks.

Typed-RAG: Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation

Aspect sentiment quad prediction (ASQP) facilitates a detailed understanding of opinions expressed in a text by identifying the opinion term, aspect term, aspect category and sentiment polarity for each opinion. However, annotating a full set of training examples to fine-tune models for ASQP is a resource-intensive process. In this study, we explore the capabilities of large language models (LLMs) for zero- and few-shot learning on the ASQP task across five diverse datasets. We report F1 scores almost up to par with those obtained with state-of-the-art fine-tuned models and exceeding previously reported zero- and few-shot performance. In the 20-shot setting on the Rest16 restaurant domain dataset, LLMs achieved an F1 score of 51.54, compared to 60.39 by the best-performing fine-tuned method MVP. Additionally, we report the performance of LLMs in target aspect sentiment detection (TASD), where the F1 scores were close to fine-tuned models, achieving 68.93 on Rest16 in the 30-shot setting, compared to 72.76 with MVP. While human annotators remain essential for achieving optimal performance, LLMs can reduce the need for extensive manual annotation in ASQP tasks.

Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction

Large language models (LLMs) have advanced document-level relation extraction (DocRE), but DocRE is more complex than sentence-level relation extraction (SentRE), facing challenges like diverse relation types, coreference resolution and long-distance dependencies. Traditional pipeline methods, which detect relations before generating triplets, often propagate errors and harm performance. Meanwhile, fine-tuning methods require extensive human-annotated data, and in-context learning (ICL) underperforms compared to supervised approaches. We propose an iterative reflection framework for DocRE, inspired by human non-linear reading cognition. The framework leverages explicit and implicit relations between triplets to provide feedback for LLMs refinement. Explicit feedback uses logical rules-based reasoning, while implicit feedback reconstructs triplets into documents for comparison. This dual-process iteration mimics human semantic cognition, enabling dynamic optimization through self-generated supervision. For the first time, this achieves zero-shot performance comparable to fully supervised models. Experiments show our method surpasses existing LLM-based approaches and matches state-of-the-art BERT-based methods.

Cognitive Mirroring for DocRE: A Self-Supervised Iterative Reflection Framework with Triplet-Centric Explicit and Implicit Feedback

This work explores transfer learning from several synthetic languages to English. We investigate the structure of the embeddings in the fine-tuned models, the information they contain, and the capabilities of the fine-tuned models on simple linguistic tasks. We also introduce a new synthetic language that leads to better transfer to English than the languages used in previous research. Finally, we introduce Tiny-Cloze Benchmark — a new synthetic benchmark for natural language understanding that is more informative for less powerful models. We use Tiny-Cloze Benchmark to evaluate fine-tuned models in several domains demonstrating that fine-tuning on a new synthetic language allows for better performance on a variety of tasks.

Transfer of Structural Knowledge from Synthetic Languages

In the large language model (LLM) revolution, embedding is a key component of various systems, such as retrieving knowledge or memories for LLMs or building content moderation filters. As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is advantageous to build a unified embedding model rather than dedicated ones for each scenario. In this context, the pre-trained multilingual decoder-only large language models, e.g., BLOOM, emerge as a viable backbone option. To assess their potential, we propose straightforward strategies for constructing embedders and introduce a universal evaluation benchmark. Experimental results show that our trained model is proficient at generating good embeddings across languages and tasks, even extending to languages and tasks for which no finetuning/pretraining data is available. We also present detailed analyses and additional evaluations. We hope that this work could encourage the development of more robust open-source universal embedders.

Language Models are Universal Embedders

Speech Event Extraction (SpeechEE) is a challenging task that lies at the intersection of Automatic Speech Recognition (ASR) and Natural Language Processing (NLP), requiring the identification of structured event information from spoken language. In this work, we present a modular, pipeline-based SpeechEE framework that integrates high-performance ASR with semantic search-enhanced prompting of Large Language Models (LLMs). Our system first classifies speech segments likely to contain events using a hybrid filtering mechanism including rule-based, BERT-based, and LLM-based models. It then employs few-shot LLM prompting, dynamically enriched via semantic similarity retrieval, to identify event triggers and extract corresponding arguments. We evaluate the pipeline using multiple LLMs—Llama3-8B, GPT-4o-mini, and o1-mini—highlighting significant performance gains with o1-mini, which achieves 63.3% F1 on trigger classification and 27.8% F1 on argument classification, outperforming prior benchmarks. Our results demonstrate that pipeline approaches, when empowered by retrieval-augmented LLMs, can rival or exceed end-to-end systems while maintaining interpretability and modularity. This work provides practical insights into LLM-driven event extraction and opens pathways for future hybrid models combining textual and acoustic features.

SpeechEE@XLLM25: Retrieval-Enhanced Few-Shot Prompting for Speech Event Extraction

Large language models (LLMs) have demon-
strated impressive reasoning capabilities
through Chain-of-Thought (CoT) prompting.
However, their reasoning processes remain
inexplicable and uncontrollable. In this paper,
we introduce a Step-Wise Reasoning and
Verification (SWRV) framework, designed
as a two-stage Parser–Verifier pipeline, that
decomposes the reasoning process into discrete
inference steps and rigorously validates each
one. Our Parser extracts problem constraints
and the sequence of reasoning steps from
the LLM’s output, and our Verifier, either
LM-based or powered by a symbolic solver,
checks the logical correctness of every step. To
ensure robust parsing, we fine-tune a compact
LM on a small, high-quality annotation set
generated by a more capable LM. Experiments
on the LLMSR dataset built atop LogiQA show
significant gains over baselines, illustrating
the effectiveness of our method for step-wise
analysis of LLM reasoning.

LLMSR@XLLM25: SWRV: Empowering Self-Verification of Small
Language Models through Step-wise Reasoning and Verification

Large, high-quality annotated corpora remain
scarce in document-level entity and relation ex-
traction in zero-shot or few-shot settings. In
this paper, we present a fully automatic, LLM-
based pipeline for synthetic data generation and
in-context learning for document-level entity
and relation extraction. In contrast to exist-
ing approaches that rely on manually annotated
demonstrations or direct zero-shot inference,
our method combines synthetic data generation
with retrieval-based in-context learning, using
a reasoning-optimized language model. This
allows us to build a high-quality demonstra-
tion database without manual annotation and to
dynamically retrieve relevant examples at infer-
ence time. Based on our approach we produce
a synthetic dataset of over 5k Wikipedia ab-
stracts with approximately 59k entities and 30k
relation triples. Finally, we evaluate in-context
learning performance on the DocIE shared task,
extracting entities and relations from long doc-
uments in a zero-shot setting. We find that
in-context joint entity and relation extraction
at document-level remains a challenging task,
even for state-of-the-art large language models.

Downloads

Next from ACL 2025

Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation

Similar lecture

Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES