Papers with SDS
Deep Learning for Conversational AI (N18-6)
Copied to clipboard
| Challenge: | Spoken Dialogue Systems (SDS) have great commercial potential . the advent of deep learning has led to significant advances in this area of NLP research . |
| Approach: | This tutorial will introduce researchers to the pipeline framework for modelling goal-oriented dialogue systems. |
| Outcome: | This tutorial will familiarise researchers with the latest advances in spoken dialogue systems . the aim of the course is to encourage dialogue research in the NLP community . |
Actor-Double-Critic: Incorporating Model-Based Critic for Task-Oriented Dialogue Systems (2020.findings-emnlp)
Copied to clipboard
| Challenge: | In order to improve the sample-efficiency of deep reinforcement learning, we implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS). |
| Approach: | They propose to use an actor-double-critic to improve the stability and overall performance of imagination augmented agent (I2A) in spoken dialogue systems. |
| Outcome: | The proposed model-based agent (ADC) improves the stability and sample-efficiency of deep reinforcement learning (DRL) on a restaurant booking task. |
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model (P19-1)
Copied to clipboard
| Challenge: | Multi-document summarization (MDS) of news articles has been limited to datasets of a couple of hundred examples. |
| Approach: | They propose a model which integrates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets. |
| Outcome: | The proposed model achieves competitive results on large-scale datasets. |
Enhancing One-Shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism (2025.coling-main)
Copied to clipboard
Guanchen Li, Xiandong Zhao, Lian Liu, Zeping Li, Yixing Xu, Dong Li, Lu Tian, Jie He, Ashish Sirasao, Emad Barsoum
| Challenge: | Pre-trained language models (PLMs) are robust in contextual understanding but their considerable size incurs significant computational and storage costs. |
| Approach: | They propose a Sparse-Dense-Sparse pruning framework to prune PLMs . they prune less critical connections using conventional pruning methods . |
| Outcome: | The proposed pruning framework outperforms SparseGPT and Wanda under identical sparsity. |
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies on single-document summarization (SDS) benefit from advances in neural sequence learning, but they produce unsatisfactory results on multi-document summary (MDS). |
| Approach: | They propose a neural sequence learning method that unifies advanced neural SDS methods and statistical measures used in classical MDS. |
| Outcome: | The proposed method achieves state-of-the-art performance on benchmark MDS datasets. |
Towards Speech-only Opinion-level Sentiment Analysis (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing systems that estimate user preferences only in static manners or exploit interaction history are inadequate to accurately assess user preferences. |
| Approach: | They propose to integrate rank consistent ordinal regression into a speech-only sentiment prediction task performed by ResNet-like systems and use speaker verification extractors trained on larger datasets as low-level feature extractor. |
| Outcome: | The proposed system beats state-of-the-art unimodal systems on multimodal Opinion Sentiment and Emotion Intensity databases. |
Neural Generation of Dialogue Response Timings (2020.acl-main)
Copied to clipboard
| Challenge: | Using neural models, the timings of spoken response offsets in human dialogue can vary based on contextual elements of the dialogue. |
| Approach: | They propose neural models that simulate the distributions of response offsets taking into account the response turn as well as the preceding turn. |
| Outcome: | The proposed models can generate distributions of response offsets based on the response turn and preceding turn based upon human listening tests and offline experiments. |
A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models have been used for abstractive single-document summarization (SDS) but they may not be suitable for multi-document summary (MDS) |
| Approach: | They propose to enforce hierarchy on both encoder and decoder to facilitate multi-document interactions for MDS. |
| Outcome: | Xiao et al. (2019) outperforms or is competitive with the previous best models. |
Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System (2022.lrec-1)
Copied to clipboard
| Challenge: | Contextually aware intelligent agents are often required to understand the users and their surroundings in real-time. |
| Approach: | They propose to build a multimodal dialogue system for children learning basic math concepts using limited datasets. |
| Outcome: | The proposed system improves the Natural Language Understanding (NLU) module of a task-oriented SDS pipeline with limited dataset resources. |
Large Language Models Know What To Say But Not When To Speak (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for turn-taking in unscripted conversations focus only on turn-final TRPs and not within-turn TRP. |
| Approach: | They propose to use a dataset to evaluate the performance of state-of-the-art LLMs in modeling unscripted spoken interactions. |
| Outcome: | The proposed model improves on the existing models in unscripted conversations and paving the way for more naturalistic dialogue systems. |
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback (2026.findings-acl)
Copied to clipboard
Siddhant Arora, Jinchuan Tian, Jiatong Shi, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
| Challenge: | Existing studies on reinforcement learning from human or AI feedback have focused on semantic rewards at the utterance level. |
| Approach: | They propose a multi-reward RLAIF framework for speech-in/speech-out dialogue systems . they combine semantic, audio-quality, and emotion-consistency rewards . |
| Outcome: | The proposed framework improves speech-in/speech-out dialogue system quality . it combines semantic, audio-quality, and emotion-consistency rewards . the proposed framework is available to download from the cdc. |