Representation Learning for Conversational Data using Discourse Mutual Information Maximization (2022.naacl-main)
Copied to clipboard
Bishal Santra, Sumegh Roychowdhury, Aishik Mandal, Vasu Gurram, Atharva Naik, Manish Gupta, Pawan Goyal
| Challenge: | Existing language modeling pretraining objectives do not take structural information of conversational text into account. |
| Approach: | They propose a structure-aware Mutual Information based loss-function DMI for training dialog-representation models that captures the inherent uncertainty in response prediction. |
| Outcome: | The proposed model outperforms strong baseline models on nine diverse tasks. |
Similar Papers
Pretraining Methods for Dialog Context Representation Learning (P19-1)
Copied to clipboard
| Challenge: | Existing methods for pretraining dialog context encoders are still in their infancy. |
| Approach: | They propose to use unsupervised pretraining objectives for dialog context representations to fine-tune and evaluate them on a set of downstream dialog tasks. |
| Outcome: | The proposed methods improve performance on a set of dialog tasks and are less data hungry. |
Pre-training Multi-party Dialogue Models with Latent Discourse Inference (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies have failed to scale up the pre-training process by putting aside unlabeled data . et al., 2019: multi-party dialogues are more difficult for models to understand since they involve multiple interlocutors resulting in interweaving reply-to relations and information flows. |
| Approach: | They propose to treat discourse structures as latent variables and jointly infer them to pre-train a model that understands the discourse structure of multi-party dialogues. |
| Outcome: | The proposed model outperforms baselines and achieves state-of-the-art results on multiple downstream tasks. |
Probing Task-Oriented Dialogue Representation from Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Using pre-trained language models, we find out which model has the most informative representation for task-oriented dialogue tasks. |
| Approach: | They propose a supervised classifier probe and unsupervised mutual information probe to investigate the mutual dependence between a real clustering and a representation clustering. |
| Outcome: | The proposed model is a supervised classifier probe and unsupervised mutual information probe. |
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (P18-1)
Copied to clipboard
| Challenge: | Existing encoder-decoder dialog models cannot output interpretable actions as in traditional systems. |
| Approach: | They propose an unsupervised discrete sentence representation learning method that integrates with existing encoder-decoder dialog models for interpretable response generation. |
| Outcome: | The proposed model can be integrated with existing encoder-decoder dialog models and discover interpretable semantics via either auto encoding or context predicting. |
Boosting Dialog Response Generation (P19-1)
Copied to clipboard
| Challenge: | Neural models generate the most common and generic responses all the time . Empirical results show that our method can significantly improve the diversity of responses generated by sequence-to-sequence models. |
| Approach: | They propose an iterative training process and ensemble method based on boosting to improve the diversity of responses generated by neural models. |
| Outcome: | Empirical results show that the proposed method significantly improves diversity and relevance of responses generated by all models. |
Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization (2021.acl-long)
Copied to clipboard
| Challenge: | Existing dialogue summarization systems encode text with a number of general semantic features, but these are often not available in open-domain tools. |
| Approach: | They propose to use DialoGPT to label three types of features on two datasets . they propose to employ pre-trained and non-pre-tried models as dialogue annotators . |
| Outcome: | The proposed method improves on two dialogue summarization datasets and achieves state-of-the-art performance. |
Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Recent models for unsupervised representation learning of text have put little focus on discourse-level representations. |
| Approach: | They propose an inter-sentence objective for pretraining language models that models discourse coherence and the distance between sentences. |
| Outcome: | The proposed model outperforms the BERT-Large model on the discourse representation benchmark DiscoEval and yields gains of 2%-6% absolute even for tasks that do not explicitly evaluate discourse. |
ConveRT: Efficient and Accurate Conversational Representations from Transformers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | ConveRT is a pretraining framework for conversational AI that is computationally heavy, slow, and expensive to train. |
| Approach: | They propose a pretraining framework for conversational tasks that is efficient, lightweight, and inexpensive. |
| Outcome: | The proposed model achieves state-of-the-art performance across widely established responses . it trains substantially faster than existing state- of-the art models . |
Towards Exploiting Background Knowledge for Building Conversation Systems (D18-1)
Copied to clipboard
| Challenge: | Existing dialog datasets contain a sequence of utterances without any explicit background knowledge associated with them. |
| Approach: | They propose to use movie chats to generate responses by copying unstructured background knowledge . they use a dataset of 9K conversations to test whether responses are generated by copy-and-modify models . |
| Outcome: | The proposed model mimics human process of conversing by copying and/or modifying sentences from unstructured background knowledge. |
Lightweight Transformers for Conversational AI (2022.naacl-industry)
Copied to clipboard
| Challenge: | Commercial dialogue systems typically require a small footprint and fast execution time, but recent trends are in the other direction, resulting in difficulties in model deployment. |
| Approach: | They build Transformer-based Language Models from scratch on large corpora of conversational data and compare their performance against BERT and other strong baselines on dialogue probing tasks. |
| Outcome: | The proposed model outperforms existing models on dialogue probing tasks and can be fine-tuned on a single consumer GPU card. |