CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues

Anaphora and ellipses are two common phenomena in dialogues. Without resolving referring expressions and information omission, dialogue systems may fail to generate consistent and coherent responses. Traditionally, anaphora is resolved by coreference resolution and ellipses by query rewrite. In this work, we propose a novel joint learning framework of modeling coreference resolution and query rewriting for complex, multi-turn dialogue understanding. Given an ongoing dialogue between a user and a dialogue assistant, for the user query, our joint learning model first predicts coreference links between the query and the dialogue context, and then generates a self-contained rewritten user query. To evaluate our model, we annotate a dialogue based coreference resolution dataset, MuDoCo, with rewritten queries. Results show that the performance of query rewrite can be substantially boosted (+2.3% F1) with the aid of coreference modeling. Furthermore, our joint model outperforms the state-of-the-art coreference resolution model (+2% F1) on this dataset.

[1]  Christopher D. Manning,et al.  Improving Coreference Resolution by Learning Entity-Level Distributed Representations , 2016, ACL.

[2]  Cheng Niu,et al.  Improving Multi-turn Dialogue Modelling with Utterance ReWriter , 2019, ACL.

[3]  Luke S. Zettlemoyer,et al.  Higher-Order Coreference Resolution with Coarse-to-Fine Inference , 2018, NAACL.

[4]  Christopher D. Manning,et al.  Deep Reinforcement Learning for Mention-Ranking Coreference Models , 2016, EMNLP.

[5]  Arpit Gupta,et al.  Scaling Multi-Domain Dialogue State Tracking via Query Reformulation , 2019, NAACL.

[6]  Dan Roth,et al.  Understanding the Value of Features for Coreference Resolution , 2008, EMNLP.

[7]  Jiwei Li,et al.  CorefQA: Coreference Resolution as Query-based Span Prediction , 2020, ACL.

[8]  Vincent Ng,et al.  Supervised Noun Phrase Coreference Research: The First Fifteen Years , 2010, ACL.

[9]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[10]  Kartikeya Upasani,et al.  MuDoCo: Corpus for Multidomain Coreference Resolution and Referring Expression Generation , 2020, LREC.

[11]  Michael Strube,et al.  Latent Structures for Coreference Resolution , 2015, TACL.

[12]  Omer Levy,et al.  BERT for Coreference Resolution: Baselines and Analysis , 2019, EMNLP/IJCNLP.

[13]  Changjian Hu,et al.  GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue , 2019, EMNLP.

[14]  Jonas Kuhn,et al.  Learning Structured Perceptrons for Coreference Resolution with Latent Antecedents and Non-local Features , 2014, ACL.

[15]  Claire Cardie,et al.  Identifying Anaphoric and Non-Anaphoric Noun Phrases to Improve Coreference Resolution , 2002, COLING.

[16]  Wei Yang,et al.  End-to-End Neural Context Reconstruction in Chinese Dialogue , 2019, Proceedings of the First Workshop on NLP for Conversational AI.

[17]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[18]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[19]  Vineet Kumar,et al.  Non-sentential Question Resolution using Sequence to Sequence Learning , 2016, COLING.

[20]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[21]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[22]  Dan Roth,et al.  A Joint Framework for Coreference Resolution and Mention Head Detection , 2015, CoNLL.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Vittorio Castelli,et al.  Slot Filling through Statistical Processing and Inference Rules , 2009, TAC.

[25]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[26]  Heeyoung Lee,et al.  A Multi-Pass Sieve for Coreference Resolution , 2010, EMNLP.

[27]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[28]  Zhucheng Tu,et al.  Open-Domain Question Answering Goes Conversational via Question Rewriting , 2020, NAACL.

[29]  Eraldo Rezende Fernandes,et al.  Latent Structure Perceptron with Feature Induction for Unrestricted Coreference Resolution , 2012, EMNLP-CoNLL Shared Task.

[30]  Omer Levy,et al.  SpanBERT: Improving Pre-training by Representing and Predicting Spans , 2019, TACL.

[31]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.