Competing Independent Modules for Knowledge Integration and Optimization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge sources are not available for sentiment analysis, but are used for many tasks. |
| Approach: | They propose a framework of untied independent modules for integrating off the shelf knowledge sources such as language models, lexica, POS information, and dependency relations. |
| Outcome: | The proposed framework is suitable for optimizing BERT-like language models even without external knowledge sources. |
Similar Papers
Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In recent years, pre-trained language models have become the de facto instrument for the field of natural language processing (NLP). |
| Approach: | They propose a method that injects linguistic structures into pre-trained language models in the parameter-efficient fine-tuning setting. |
| Outcome: | The proposed approach outperforms state-of-the-art methods with a comparable number of parameters. |
Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction (2020.coling-main)
Copied to clipboard
| Challenge: | Supervised-learning approaches fail to scale across domains where labeled data is lacking. |
| Approach: | They propose a method for incorporating external linguistic knowledge into a self-attention mechanism coupled with a transformer-based model. |
| Outcome: | The proposed method enables leveraging syntactic knowledge from transformer-based models to bridge the gap between domains. |
Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)
Copied to clipboard
| Challenge: | Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance. |
| Approach: | They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning. |
| Outcome: | The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods. |
Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction (N19-1)
Copied to clipboard
| Challenge: | Knowledge Bases (KBs) require constant updating to reflect changes to the world they represent. |
| Approach: | They propose a framework that unifies learning of RE and KBE models . the framework is based on a relation extraction task that uses a KB relation to a phrase . |
| Outcome: | The proposed framework unifies learning of RE and KBE models, leading to significant improvements over the state-of-the-art RE framework. |
MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision (2026.acl-long)
Copied to clipboard
| Challenge: | Multi-step reasoning remains challenging for language models with limited capacity . et al., 2025) demonstrate remarkable reasoning capabilities across diverse tasks . |
| Approach: | They propose a module-aware reasoning distillation framework that explicitly targets key Transformer components for effective reasoning transfer. |
| Outcome: | The proposed framework targets key components for effective reasoning transfer . it adopts an offline distillation setting, where a strong teacher model provides reasoning trajectories in advance . |
Bridging Knowledge Gaps in Neural Entailment via Symbolic Models (D18-1)
Copied to clipboard
| Challenge: | Textual entailment models focus on lexical gaps but rarely on knowledge gaps. |
| Approach: | They propose a fact-level decomposition of the hypothesis and a knowledge lookup module to fill knowledge gaps in Science Entailment task. |
| Outcome: | The proposed model outperforms the base model on the SciTail dataset by 3% and 5% on the textual premise and the structured knowledge base. |
AdapterHub: A Framework for Adapting Transformers (2020.emnlp-demos)
Copied to clipboard
Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych
| Challenge: | AdapterHub framework enables dynamic “stiching-in” of pre-trained adapters for different tasks and languages. |
| Approach: | They propose a framework that allows dynamic "stiching-in" of pre-trained adapters for different tasks and languages. |
| Outcome: | The proposed framework allows dynamic “stiching-in” of pre-trained adapters for different tasks and languages. |
Attention-based Conditioning Methods for External Knowledge Integration (P19-1)
Copied to clipboard
| Challenge: | Existing approaches for incorporating external knowledge into deep neural networks (RNNs) lexicon features are used to concatenate external information into the input or hidden network layers. |
| Approach: | They propose a method for conditioning external knowledge into RNNs by concatenating a representation of the external information to the input or hidden network layers. |
| Outcome: | The proposed approach improves performance on six benchmark datasets. |
KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to infuse knowledge graphs with pre-trained LMs are limited by the input sequence length. |
| Approach: | They propose a language model that leverages knowledge in local, document-level, and global contexts for long document understanding. |
| Outcome: | The proposed model achieves state-of-the-art on three long document understanding tasks across 6 datasets/settings. |
A Joint Neural Model for Information Extraction with Global Features (2020.acl-main)
Copied to clipboard
| Challenge: | Existing joint neural models for Information Extraction use local task-specific classifiers to predict labels for individual instances. |
| Approach: | They propose a joint neural framework that extracts the optimal IE result as a graph from an input sentence. |
| Outcome: | The proposed model achieves new state-of-the-art on all subtasks and does not use any language-specific feature. |