Papers with industry applications
Temporal Generalization for Spoken Language Understanding (2022.naacl-industry)
Copied to clipboard
| Challenge: | Spoken Language Understanding models are usually trained offline on historical data, but must perform well on incoming user requests after deployment. |
| Approach: | They propose different strategies for achieving good temporal generalization . they focus on temporal drift, where the distribution of utterances may change . |
| Outcome: | The proposed model can perform well on unseen domains, e.g., upcoming data. |
Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning (N18-3)
Copied to clipboard
| Challenge: | End-to-end neural models for conversational agents require large corpus of dialogues to learn effectively. |
| Approach: | They propose a method for building an agent for arbitrary tasks by combining dialogue self-play and crowd-sourcing. |
| Outcome: | The proposed approach can be quickly bootstrapped to deploy in front of users and further optimized via interactive learning from actual users. |
Practical Transformer-based Multilingual Text Classification (2021.naacl-industry)
Copied to clipboard
| Challenge: | XNLI does not reflect the data availability and task variety of industry applications. |
| Approach: | They compare transformer-based text classification methods to multilingual models in five different languages . they use a task- and domain-adaptive pretraining and data augmentation technique . |
| Outcome: | The proposed methods outperform monolingual models on two tasks in five languages . the results show that practical modifications can improve model performance without labeling . |
Developing Production-Level Conversational Interfaces with Shallow Semantic Parsing (D18-2)
Copied to clipboard
| Challenge: | In this demo, we demonstrate an end-to-end approach for building conversational interfaces from prototype to production. |
| Approach: | They propose an end-to-end approach for building conversational interfaces from prototype to production that leverages shallow semantic parsing. |
| Outcome: | The proposed approach has proven to work well for a number of applications across diverse verticals. |
Luna: A Lightweight Evaluation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost (2025.coling-industry)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) systems are crucial for enhancing the capabilities of large language models (LLMs) in industry applications. |
| Approach: | They propose a DeBERTA-large encoder for hallucination detection in RAG settings that is fine-tuned for halluination detection. |
| Outcome: | The proposed model outperforms GPT-3.5 and commercial evaluation frameworks on the hallucination detection task, with 97% and 91% reduction in cost and latency, respectively. |
Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Weak supervision and data programming are powerful tools to support information extraction models. |
| Approach: | They propose a prototype-based method to denoise weakly supervised training data . they use a model to model the correct contexts for a given target value . |
| Outcome: | The proposed method achieves 9% accuracy gain in attribute value extraction in e-commerce websites. |
Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Topic models are powerful tools to get overview of large collections of text data. |
| Approach: | They propose to use a tool called STELLAR for interactive topic browsing to evaluate topics from a real-world dataset. |
| Outcome: | The proposed model performs better than LDA models in the real-world and is scalable. |
Bidirectional Reasoning Supervision for Multilingual Financial Decision Making (2025.emnlp-industry)
Copied to clipboard
Muhammad Rafsan Kabir, Jawad Ibn Ahad, Robin Krambroeckers, Silvia Ahmed, M M Lutfe Elahi, Nabeel Mohammed, Shafin Rahman
| Challenge: | Large Language Models have been used for sentiment analysis, machine translation, and question answering, but their effectiveness in the multilingual financial domain remains unknown. |
| Approach: | They propose a fine-tuning approach that integrates positive and negative rationales alongside classification labels. |
| Outcome: | The proposed approach outperforms existing methods across English, Hindi, Bengali, and Telugu, and is suitable for industry applications. |
PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering (2026.acl-industry)
Copied to clipboard
| Challenge: | Multi-hop question answering is a practical bottleneck in industry applications . large language models (LLMs) fail frequently when evidence coverage is incomplete or reasoning trajectories drift . |
| Approach: | They propose a training-free two-stage framework that separates coverage from commitment . it performs breadth-first anchoring to build a high-recall evidence frontier . compared with IRCoT, it achieves 23.5% higher answer accuracy . |
| Outcome: | The proposed framework outperforms strong baselines in MHQA benchmarks and achieves 23.5% higher answer accuracy and 10.5% NDCG gains in retrieval quality. |
ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler (2024.lrec-main)
Copied to clipboard
| Challenge: | State-of-the-art intent classification and slot filling methods rely on data-intensive deep learning models . large language models exhibit remarkable zero-shot performance across various natural language tasks. |
| Approach: | They propose an approach framing IC and SF as language generation tasks for instruction-LLMs with a more efficient SF-prompting method. |
| Outcome: | The proposed approach outperforms state-of-the-art IC+SF method and in-context learning methods with GPT3.5 (175B). |
Learning from Wrong Predictions in Low-Resource Neural Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to Neural Machine Translation use additional linguistic sources and software tools but these are often not available in less favoured languages. |
| Approach: | They propose a pre-training strategy that leverages the relationships and similarities that exist between unaligned sentences to increase the dataset size of endangered and low-resource languages. |
| Outcome: | The proposed approach increases the dataset size of endangered and low-resource languages by the square of the initial quantity, matching the typical size of high-resourced datasets such as WMT14 En-Fr. |