# Towards End-to-End Open Conversational Machine Reading

arXiv: https://arxiv.org/abs/2210.07113 · HTML: https://mlsanity.com/paper/2210.07113/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 24 of 24)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension](https://mlsanity.com/paper/1902.00164/) (2019)
- [Challenges in Building Intelligent Open-domain Dialog Systems](https://mlsanity.com/paper/1905.05709/) (2019)
- [MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://mlsanity.com/paper/2004.04494/) (2020)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [Modeling Multi-turn Conversation with Deep Utterance Aggregation](https://mlsanity.com/paper/1806.09102/) (2018)
- [Tracking the World State with Recurrent Entity Networks](https://mlsanity.com/paper/1612.03969/) (2016)
- [A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues](https://mlsanity.com/paper/1812.00176/) (2018)
- [MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding](https://mlsanity.com/paper/2106.01541/) (2021)
- [Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading](https://mlsanity.com/paper/2010.01838/) (2020)
- [Dialogue Graph Modeling for Conversational Machine Reading](https://mlsanity.com/paper/2012.14827/) (2020)
- [Guiding Variational Response Generator to Exploit Persona](https://mlsanity.com/paper/1911.02390/) (2019)
- [A Short Survey of Pre-trained Language Models for Conversational AI-A NewAge in NLP](https://mlsanity.com/paper/2104.10810/) (2021)
- [IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems](https://mlsanity.com/paper/2002.00571/) (2020)
- [E3: Entailment-driven Extracting and Editing for Conversational Machine Reading](https://mlsanity.com/paper/1906.05373/) (2019)
- [Attending to Future Tokens For Bidirectional Sequence Generation](https://mlsanity.com/paper/1908.05915/) (2019)
- [Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading](https://mlsanity.com/paper/2005.12484/) (2020)
- [Open-Retrieval Conversational Machine Reading](https://mlsanity.com/paper/2102.08633/) (2021)
- [Lingke: A Fine-grained Multi-turn Chatbot for Customer Service](https://mlsanity.com/paper/1808.03430/) (2018)
- [Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning](https://mlsanity.com/paper/2010.01495/) (2020)
- [Smoothing Dialogue States for Open Conversational Machine Reading](https://mlsanity.com/paper/2108.12599/) (2021)
- [Fine-Grained Sentence Functions for Short-Text Conversation](https://mlsanity.com/paper/1907.10302/) (2019)

## Built on by (most cited first, 2 of 2)

- [Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2402.11142/) (2024)
- [PassiveQA: A Three-Action Framework for Epistemically Calibrated Question Answering via Supervised Finetuning](https://mlsanity.com/paper/2604.04565/) (2026)

## Abstract (arXiv)

In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. Existing works generally utilize two independent modules to approach this problem's two successive sub-tasks: first with a hard-label decision making and second with a question generation aided by various entailment reasoning methods. Such usual cascaded modeling is vulnerable to error propagation and prevents the two sub-tasks from being consistently optimized. In this work, we instead model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework on both sub-tasks by a large margin, achieving new state-of-the-art results. Further ablation studies support that our framework can generalize to different backbone models.