Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

May 26, 2020 · Entered Twilight · 🏛 Annual Meeting of the Association for Computational Linguistics

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, dm, evaluator.py, evaluator_qg.py, fig, inference_e2e.py, inference_e2e.sh, inference_oracle_qg.sh, preprocess_dm.py, preprocess_qg.py, qg, train_dm.py, train_dm.sh, train_qg.sh

Authors Yifan Gao, Chien-Sheng Wu, Shafiq Joty, Caiming Xiong, Richard Socher, Irwin King, Michael R. Lyu, Steven C. H. Hoi arXiv ID 2005.12484 Category cs.CL: Computation & Language Citations 22 Venue Annual Meeting of the Association for Computational Linguistics Repository https://github.com/Yifan-Gao/explicit_memory_tracker ⭐ 39 Last Checked 1 month ago

Abstract

The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions. Existing approaches are limited in their decision making due to struggles in extracting question-related rules and reasoning about them. In this paper, we present a new framework of conversational machine reading that comprises a novel Explicit Memory Tracker (EMT) to track whether conditions listed in the rule text have already been satisfied to make a decision. Moreover, our framework generates clarification questions by adopting a coarse-to-fine reasoning strategy, utilizing sentence-level entailment scores to weight token-level distributions. On the ShARC benchmark (blind, held-out) testset, EMT achieves new state-of-the-art results of 74.6% micro-averaged decision accuracy and 49.5 BLEU4. We also show that EMT is more interpretable by visualizing the entailment-oriented reasoning process as the conversation flows. Code and models are released at https://github.com/Yifan-Gao/explicit_memory_tracker.