COLING 2025 Papers

Sophisticated grammatical error detection/correction tools are available for a small set of languages such as English and Chinese. However, it is not straightforward—if not impossible—to adapt them to morphologically rich languages with complex writing rules like Turkish which has more than 80 million speakers. Even though several tools exist for Turkish, they primarily focus on spelling errors rather than grammatical errors and lack features such as web interfaces, error explanations and feedback mechanisms. To fill this gap, we introduce GECTurk WEB, a light, open-source, and flexible web-based system that can detect and correct the most common forms of Turkish writing errors, such as the misuse of diacritics, compound and foreign words, pronouns, light verbs along with spelling mistakes. Our system provides native speakers and second language learners an easily accessible tool to detect/correct such mistakes and also to learn from their mistakes by showing the explanation for the violated rule(s). The proposed system achieves 88,3 system usability score, and is shown to help learn/remember a grammatical rule (confirmed by 80% of the participants). The GECTurk WEB is available both as an offline tool (https://github.com/GGLAB-KU/gecturkweb) or at www.gecturk.net.

Reverse Dictionary (RD) is the task of obtaining the most relevant word or set of words given a textual description or dictionary definition. Effective RD methods have applications in accessibility, translation or writing support systems. Moreover, in NLP research we find RD to be used to benchmark text encoders at various granularities, as it often requires word, definition and sentence embeddings. In this paper, we propose a simple approach to RD that leverages LLMs in combination with embedding models. Despite its simplicity, this approach outperforms supervised baselines in well studied RD datasets, while also showing less overfitting. We also conduct a number of experiments on different dictionaries and analyze how different styles, registers and target audiences impact the quality of RD systems. We conclude that, on average, untuned embeddings alone fare way below an LLM-only baseline (although they are competitive in highly technical dictionaries), but are crucial for boosting performance in combined methods.

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on text classification tasks with their powerful word embeddings, but their black-box nature, which leads to a lack of interpretability, has been a major concern. In this work, we introduce GAProtoNet, a novel white-box Multi-head Graph Attention-based Prototypical Network designed to explain the decisions of text classification models built with LM encoders. In our approach, the input vector and prototypes are regarded as nodes within a graph, and we utilize multi-head graph attention to selectively construct edges between the input node and prototype nodes to learn an interpretable prototypical representation. During inference, the model makes decisions based on a linear combination of activated prototypes weighted by the attention score assigned for each prototype, allowing its choices to be transparently explained by the attention weights and the prototypes. Experiments on multiple public datasets show our approach achieves superior results without sacrificing the accuracy of the original black-box LMs. We also compare with four alternative prototypical network variations and our approach achieves the best accuracy and F1 among all. Our case study and visualization of prototype clusters also demonstrate the efficiency in explaining the decisions of black-box models built with LMs.

The advancement of text generation models has granted us the capability to produce coherent and convincing text on demand. Yet, in real-life circumstances, individuals do not continuously generate text or voice their opinions. For instance, consumers pen product reviews after weighing the merits and demerits of a product, and professional analysts issue reports following significant news releases. In essence, opinion expression is typically prompted by particular reasons or signals. Despite long-standing developments in opinion mining, the appropriate timing for expressing an opinion remains largely unexplored. To address this deficit, our study introduces an innovative task - the identification of news-triggered opinion expressing timing. We ground this task in the actions of professional stock analysts and develop a novel dataset for investigation. Our Generator-Assisted Decision-Focused Approach (GADFA) is decision-focused, leveraging text generation models to steer the classification model, thus enhancing overall performance. Our experimental findings demonstrate that the text generated by our model contributes fresh insights from various angles, effectively aiding in identifying the optimal timing for opinion expression.

Event Argument Extraction is a critical task of Event Extraction, focused on identifying event arguments within text. This paper presents a novel Fusion Selection-Generation-Based Approach, by combining the precision of selective methods with the semantic generation capability of generative methods to enhance argument extraction accuracy. This synergistic integration, achieved through fusion prompt, element-based extraction, and fusion learning, addresses the challenges of input, process, and output fusion, effectively blending the unique characteristics of both methods into a cohesive model. Comprehensive evaluations on the RAMS and WikiEvents demonstrate the model’s state-of-the-art performance and efficiency.

Empathetic dialogue systems improve user experience across various domains. Existing approaches mainly focus on acquiring affective and cognitive knowledge from text, but neglect the unique personality traits of individuals and the inherently multimodal nature of human face-to-face conversation. To this end, we enhance the dialogue system with the ability to generate empathetic responses from a multimodal perspective, and consider the diverse personality traits of users. We incorporate multimodal data, such as images and texts, to understand the user’s emotional state and situation. Concretely, we first identify the user’s personality trait. Then, the dialogue system comprehends the user’s emotions and situation by the analysis of multimodal inputs. Finally, the response generator models the correlations among the personality, emotion, and multimodal data, to generate empathetic responses. Experiments on the MELD dataset and the MEDIC dataset validate the effectiveness of the proposed approach.

In a conversational system, dynamically generating follow-up questions based on context can help users explore information and provide a better user experience. Humans are usually able to ask questions that involve some general life knowledge and demonstrate higher order cognitive skills. However, the questions generated by existing methods are often limited to shallow contextual questions that are uninspiring and have a large gap to the human level. In this paper, we propose a three-stage external knowledge-enhanced follow-up question generation method, which generates questions by identifying contextual topics, constructing a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question. The model generates information-rich and exploratory follow-up questions by introducing external common sense knowledge and performing a knowledge fusion operation. Experiments show that compared to baseline models, our method generates questions that are more informative and closer to human questioning levels while maintaining contextual relevance.

Many of the world’s languages have insufficient data to train high-performing general neural machine translation (NMT) models, let alone domain-specific models, and often the only available parallel data are small amounts of religious texts. Hence, domain adaptation (DA) is a crucial issue faced by contemporary NMT and has, so far, been underexplored for low-resource languages. In this paper, we evaluate a set of methods from both low-resource NMT and DA in a realistic setting, in which we aim to translate between a high-resource and a low-resource language with access to only: a) parallel Bible data, b) a bilingual dictionary, and c) a monolingual target-domain corpus in the high-resource language. Our results show that the effectiveness of the tested methods varies, with the simplest one, DALI, being most effective. We follow up with a small human evaluation of DALI, which shows that there is still a need for more careful investigation of how to accomplish DA for low-resource NMT.

Embeddings play a pivotal role in the efficacy of large language models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform complex tasks that require a fundamental understanding of human language. Given that these embeddings themselves often reflect or exhibit bias, it stands to reason that these models may also inadvertently learn this bias. In this work, we build on the aforementioned seminal work of (CITATION) and (CITATION) and propose DeepSoftDebias, an algorithm that uses a neural network to perform ‘soft debiasing’. We exhaustively evaluate this algorithm across a variety of state-of-the-art datasets, accuracy metrics, and challenging NLP tasks. On a wide range of metrics, we find that DeepSoftDebias outperforms the current state-of-the-art methods at reducing bias across gender, race, and religion.

The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data annotation, a task whose importance cannot be underestimated, but which is time-consuming and costly. Thus, any dataset for resource-poor languages is precious, in particular when it is task-specific. Here, we explore the feasibility of repurposing an existing multilingual dataset for a new NLP task: we repurpose a subset of the BELEBELE dataset (Bandarkar et al., 2023), which was designed for multiple-choice question answering (MCQA), to enable the more practical task of extractive QA (EQA) in the style of machine reading comprehension. We present annotation guidelines and a parallel EQA dataset for English and Modern Standard Arabic (MSA). We also present QA evaluation results for several monolingual and cross-lingual QA pairs including English, MSA, and five Arabic dialects. We aim to help others adapt our approach for the remaining 120 BELEBELE language variants, many of which are deemed under-resourced. We also provide a thorough analysis and share insights to deepen understanding of the challenges and opportunities in NLP task reformulation.

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. The scarcity of specialized chemistry data, coupled with the complexity of multi-modal data such as 2D graph, 3D structure and spectrum, present distinct challenges. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic survey specifically focused on chemistry-oriented LLMs. In this paper, we outline methodologies for incorporating domain-specific chemistry knowledge and multi-modal information into LLMs, we also conceptualize chemistry LLMs as agents using chemistry tools and investigate their potential to accelerate scientific research. Additionally, we conclude the existing benchmarks to evaluate chemistry ability of LLMs. Finally, we critically examine the current challenges and identify promising directions for future research. Through this comprehensive survey, we aim to assist researchers in staying at the forefront of developments in chemistry LLMs and to inspire innovative applications in the field.

In the last decades, computational linguistics has become increasingly interested in annotation schemes that aim at an adequate description of the meaning of the sentences and texts. Discussions are ongoing on an appropriate annotation scheme for a large and complex amount of diverse information. In this contribution devoted to description of polyfunctional uninflected words (namely particles), i.e. words which, although having only one paradigmatic form, can have several different syntactic functions and even express relatively different semantic distinctions, we argue that it is the multi-layer system (linked from meaning to text) that allows a comprehensive description of the relations between morphological properties, syntactic function and expressed meaning, and thus contributes to greater accuracy in the description of the phenomena concerned and to the overall consistency of the annotated data. These aspects are demonstrated within the Prague Dependency Treebank annotation scheme, whose pioneering proposal can be found in the first COLING proceedings from 1965 (Sgall 1965), and to this day, the concept has proved to be sound and serves very well for complex annotation.

This paper explores the use of Large Language Models (LLMs) in the generation and evaluation of analytical reports derived from Earnings Calls (ECs). Addressing a current gap in research, we explore the generation of analytical reports with LLMs in a multi-agent framework, designing specialized agents that introduce diverse viewpoints and desirable topics of analysis into the report generation process. Through multiple analyses, we examine the alignment between generated and human-written reports and the impact of both individual and collective agents. Our findings suggest that the introduction of additional agents results in more insightful reports, although reports generated by human experts remain preferred in the majority of cases. Finally, we address the challenging issue of report evaluation, we examine the limitations and strengths of LLMs in assessing the quality of generated reports in different settings, revealing a significant correlation with human experts across multiple dimensions.

Abusive language detection relies on understanding different levels of intensity, expressiveness and targeted groups, which requires commonsense reasoning, world knowledge and linguistic nuances that evolve over time. Here, we frame the problem as a knowledge-guided learning task, and demonstrate that LLMs’ implicit knowledge without an accurate strategy is not suitable for multi-class detection nor explanation generation. We publicly release GLlama Alarm, the knowledge-Guided version of Llama-2 instruction fine-tuned for multi-class abusive language detection and explanation generation. By being fine-tuned on structured explanations and external reliable knowledge sources, our model mitigates bias and generates explanations that are relevant to the text and coherent with human reasoning, with an average 48.76% better alignment with human judgment according to our expert survey.

Document Image Translation (DIT) aims to translate documents in images from one language to another. It requires visual layouts and textual contents understanding, as well as document coherence capturing. However, current methods often rely on the quality of OCR output, which, particularly in complex-layout scenarios, frequently loses the crucial document coherence, leading to chaotic text. To overcome this problem, we introduce a novel end-to-end network, named Zoom-out DIT (ZoomDIT), inspired by human translation procedures. It jointly accomplishes the multi-level tasks including word positioning, sentence recognition & translation, and document organization, based on a fine-to-coarse zoom-out framework, to progressively realize “chaotic words to coherent document” and improve translation. We further contribute a new large-scale DIT dataset with multi-level fine-grained labels. Extensive experiments on public and our new dataset demonstrate significant improvements in translation quality towards complex-layout document images, offering a robust solution for reorganizing the chaotic OCR outputs to a coherent document translation.

In this study, we tackle three main challenges of deep sequential processing models in previous research: (1) memory degradation, (2) inaccurate gradient backpropagation, and (3) compatibility with next-token prediction. Specifically, to address (1-2), we define a Flashback property in which memory is preserved perfectly as an identity mapping of its stored value in a memory region until it is overwritten by a hidden state at a different time step. We propose a Flashback mechanism that satisfies this property in a fully differentiable, end-to-end manner. Further, to tackle (3), we propose architectures that incorporate the Flashback mechanism into Transformers and Mamba, enabling next-token prediction for language modeling tasks. In experiments, we trained on The Pile dataset, which includes diverse texts, to evaluate tradeoffs between commonsense reasoning accuracy, processing speed, and memory usage after introducing the Flashback mechanism into existing methods. The evaluations confirmed the effectiveness of the Flashback mechanism.

Automated assessment in natural language generation is a challenging task. Instruction-tuned large language models (LLMs) have shown promise in reference-free evaluation, particularly through comparative assessment. However, the quadratic computational complexity of pairwise comparisons limits its scalability. To address this, efficient comparative assessment has been explored by applying comparative strategies on zero-shot LLM probabilities. We propose a framework for finetuning LLMs for comparative assessment to align the model’s output with the target distribution of comparative probabilities. By training on soft probabilities, our approach improves state-of-the-art performance while maintaining high performance with an efficient subset of comparisons.

Recent advancements in text-to-image generation, notably the series of Stable Diffusion methods, have enabled the production of diverse, high-quality photo-realistic images. Nevertheless, these techniques still exhibit limitations in terms of knowledge access. Retrieval-augmented image generation is a straightforward way to tackle this problem. Current studies primarily utilize coarse-grained retrievers, employing initial prompts as search queries for knowledge retrieval. This approach, however, is ineffective in accessing valuable knowledge in long-tail text-to-image generation scenarios. To alleviate this problem, we introduce FineRAG, a fine-grained model that systematically breaks down the retrieval-augmented image generation task into four critical stages: query decomposition, candidate selection, retrieval-augmented diffusion, and self-reflection. Experimental results on both general and long-tailed benchmarks show that our proposed method significantly reduces the noise associated with retrieval-augmented image generation and performs better in complex, open-world scenarios.

Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the hallucination rate in legal QA, we first introduce a benchmark called LegalHalBench and three automatic metrics to evaluate the common hallucinations when LLMs answer legal questions. We then propose a hallucination mitigation method that integrates behavior cloning and a novel Hard Sample-aware Iterative Direct Preference Optimization (HIPO). We conduct extensive real-data experiments to validate the effectiveness of our approach. Our results demonstrate remarkable improvements in various metrics, including the newly proposed Non-Hallucinated Statute Rate, Statute Relevance Rate, Legal Claim Truthfulness, as well as traditional metrics such as METEOR, BERTScore, ROUGE-L, and win rates.