Papers with generative methods
Unified Neural Topic Model via Contrastive Learning and Term Weighting (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent techniques employ pretrained language models to improve topic quality. |
| Approach: | They propose a topic-based model that uses contrastive learning and term weighting to learn from a pretrained language model and discover influential terms from semantically coherent clusters. |
| Outcome: | The proposed model outperforms baselines across multiple topic coherence measures and can be used as an add-on to existing topic models and improves their performance. |
XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark (2026.findings-eacl)
Copied to clipboard
Ioan-Paul Ciobanu, Andrei-Iulian Hîji, Nicolae Catalin Ristea, Paul Irofti, Cristian Rusu, Radu Tudor Ionescu
| Challenge: | Recent advances in audio generation led to an increasing number of deepfakes . however, these methods are typically tested in an in-domain setup . |
| Approach: | They propose a large-scale cross-domain audio deepfake benchmark comprising 668.8 hours of real and deepfak speech. |
| Outcome: | The proposed benchmark compares audio deepfake detectors with existing methods in the wild . the results show that the proposed methods perform better in different languages than existing methods . |
Seq2Path: Generating Sentiment Tuples as Paths of a Tree (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing generative methods for extracting sentiment tuples do not have orders between the t-uples . a novel parallel generative framework for ABSA is proposed . |
| Approach: | They propose a parallel generative framework to generate sentiment tuples as paths of a tree . they train the model with an independent target and introduce a discriminative token . |
| Outcome: | The proposed method achieves state-of-the-art on AOPE, ASTE, TASD, UABSA, ACOS . it trains with the loss of ordinary Seq2Seq averaged over paths, and inferences automatically select valid paths. |
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation (P19-1)
Copied to clipboard
| Challenge: | Existing generative methods overlook grammatical structure or make factual mistakes in generated texts. |
| Approach: | They propose a template-based method to ensure the readability of generated type descriptions . they also propose measurable metrics to measure the readibility of the generated type description . |
| Outcome: | The proposed method improves substantially compared with baselines and achieves state-of-the-art performance on both datasets. |
Knowledge Enhanced Reflection Generation for Counseling Dialogues (2022.acl-long)
Copied to clipboard
| Challenge: | Using retrieval and generative methods, we generate responses using commonsense and domain knowledge. |
| Approach: | They propose a pipeline that collects domain knowledge through web mining and a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. |
| Outcome: | The proposed pipeline collects domain knowledge through web mining and incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. |
Sentence Representation Learning with Generative Objective rather than Contrastive Objective (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing sentences-level training objectives focus on acquiring sentence-level representations, but they lack effective self-supervised objectives. |
| Approach: | They propose a generative self-supervised learning objective based on phrase reconstruction to improve sentence representation. |
| Outcome: | Empirical results show that the proposed objective outperforms current methods on STS benchmarks and retrieval and reranking tasks. |
DORE: Document Ordered Relation Extraction based on Generative Framework (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing generative methods do not fit document-level relation extraction tasks where there are multiple entities and relational facts. |
| Approach: | They propose to generate a symbolic and ordered sequence from relation matrix which is easier to learn and introduce several negative sampling strategies to improve the performance with balanced signals. |
| Outcome: | The proposed method can improve the performance of the generative DocRE models on four datasets. |
Fusion meets Function: The Adaptive Selection-Generation Approach in Event Argument Extraction (2025.coling-main)
Copied to clipboard
| Challenge: | Event Argument Extraction is a critical subtask of Event Extraction, focused on identifying event arguments within text. |
| Approach: | They propose a Fusion Selection-Generation-Based Approach that merges selective and generative methods to enhance argument extraction accuracy. |
| Outcome: | The proposed method improves on the RAMS and WikiEvents, while preserving the unique characteristics of both methods. |
Text Generation Model Enhanced with Semantic Information in Aspect Category Sentiment Analysis (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for ACSA fail to model relations of target words and opinion words in a sentence including multiple aspects. |
| Approach: | They propose to incorporate AMR into a text generation model to model relations of target words and opinion words in a sentence including multiple aspects. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three datasets. |
MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for rewriting query terms struggle with natural language understanding . generative methods face high inference latency and cost in offline settings . |
| Approach: | They propose a hybrid pipeline for rewriting query queries using offline knowledge distillation and online reinforcement learning. |
| Outcome: | The proposed pipeline improves query relevance, diversity, adaptability and cost-effective evaluation without manual annotations on Amazon ESCI dataset. |
Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have developed powerful generative methods for aspect sentiment quad prediction (ASQP) but they still suffer from imprecise predictions and limited interpretability due to data scarcity and inadequate modeling of the quadruplet composition process. |
| Approach: | They propose a self-consistent reasoning-based aspect sentiment quadruple prediction framework which generates reasonings and corresponding quadruples in sequence. |
| Outcome: | The proposed model significantly improves its ability to handle complex reasoning tasks and correctly predict quadruplets through consistency voting, resulting in enhanced interpretability and accuracy in aspect sentiment quadr uplp prediction. |
Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Zero-Shot Learning (ZSL) is a new form of learning that uses textual description and attribute to transfer knowledge from seen to unseen classes. |
| Approach: | They propose a non-generative gating-based attribute refinement network for ZSL that uses a circle loss-guided attribute embedder to refine the attributes. |
| Outcome: | The proposed approach outperforms generative methods and most generative ones in all three scenarios. |
Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to name entity recognition use autoregressive decoding, hallucinated entities, and formatting errors. |
| Approach: | They propose a method that allows causal LLMs to perform discriminative token classification with full bidirectional context. |
| Outcome: | The proposed method surpasses the previous best method on zero-shot NER benchmarks by +7.9 F1 on average across CrossNER and MIT benchmarks. |
LEGO-ABSA: A Prompt-based Task Assemblable Unified Generative Framework for Multi-task Aspect-based Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing generative methods focus on a single task at a time. |
| Approach: | They propose a unified generative multi-task framework that can solve multiple ABSA tasks . they propose to control the type of task prompts consisting of multiple element prompts . |
| Outcome: | The proposed framework achieves state-of-the-art results in almost all ABSA tasks and competitive results in task transfer scenarios. |
Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis (2024.findings-emnlp)
Copied to clipboard
| Challenge: | generative methods have shown promising results for extracting sentiment quadruplets . compound sentences can contain multiple quadroutlets, making extraction difficult . |
| Approach: | They propose an Aspect Term Oriented Sentence Splitter which simplifies compound sentences into simpler and clearer forms. |
| Outcome: | The proposed method outperforms existing methods in ASQP and ACOS tasks. |
Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing taxonomy expansion methods struggle with representation limits and generalization, while generative methods process all candidates at once, introducing noise and exceeding context limits. |
| Approach: | They propose a plug-and-play framework that combines discriminative ranking and generative reasoning for efficient taxonomy expansion. |
| Outcome: | Experiments show that LORex improves accuracy by 12% and similarity by 5% over state-of-the-art methods. |
MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to multimodal learning assume a complete input modality setting, i.e., each modality is either complete or completely missing in both training and test sets. |
| Approach: | They propose an alignment dynamics learning module based on the theory of optimal transport for missing data imputation and a denoising training algorithm to enhance the quality of iputation and accuracy of model predictions. |
| Outcome: | The proposed method performs faster and more accurate inferences under different missing conditions and alleviates the overfitting issue. |
Knowledge Triplets Derivation from Scientific Publications via Dual-Graph Resonance (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing relation extraction methods aim to extract explicit triplet knowledge from documents, but they can hardly perceive unobserved factual relations. |
| Approach: | They propose a novel Extraction-Contextualization-Derivation strategy to generate a document-specific dynamic graph from a shared static knowledge graph. |
| Outcome: | The proposed method can generate richer explicit and implicit relations under the guidance of static and dynamic knowledge topologies. |
Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing research suggests that contextual representations of large language models exhibit subpar performance in downstream tasks, struggling to fully capture the semantic nuances of words. |
| Approach: | They investigate the bottom-up evolution of lexical semantics for a popular LLM . they probing its hidden states at the end of each layer using a contextualized word identification task . |
| Outcome: | The proposed model is able to encode lexical semantics in lower layers while achieving weaker induction in higher layers. |
Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text. |
| Approach: | They propose an explicit-agmented-generativ-e framework with distribution modification for hierarchical text classification. |
| Outcome: | The proposed framework improves on the initial distributions of tail classes and avoids misinterpreting predictions on unbalanced data. |
AnchorAlign: A Novel Anchor Alignment-enhanced Generative Method for Joint Named Entity Recognition and Relation Extraction (2026.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition and Relation Extraction are interdependent tasks in information extraction. |
| Approach: | They propose a generative method enhanced by anchor alignment to bridge NER and RE tasks . they use anchor entities as semantic pivots to align the two tasks based on their semantic representations . |
| Outcome: | The proposed method outperforms state-of-the-art models on five benchmark datasets. |