AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
In contrast to previous work, our method reduces the effort of complicated feature engineering by proposing an utterance encoder and a pointer module that models inter-utterance interactions

Online Conversation Disentanglement with Pointer Networks

EMNLP 2020, pp.6321-6330, (2020)

Cited by: 0|Views186
Full Text
Bibtex
Weibo

Abstract

Huge amounts of textual conversations occur online every day, where multiple conversations take place concurrently. Interleaved conversations lead to difficulties in not only following the ongoing discussions but also extracting relevant information from simultaneous messages. Conversation disentanglement aims to separate intermingled mes...More

Code:

Data:

0
Introduction
  • With the fast growth of Internet and mobile devices, people commonly communicate in the virtual world to discuss events, issues, tasks, and personal experiences.
  • The first stage involves link prediction that models “reply-to” relation between two utterances.
  • Elsner and Charniak (2008, 2010) combine conversation cues like speaker, mention, and time with content features like the number of shared words to train a linear classifier.
  • Mehri and Carenini (2017) pre-train an LSTM network to predict reply probability of an utterance, which is used in a link prediction classifier along with other handcrafted features.
  • The interactions between two utterances is captured by taking element-wise absolute difference of the encoded sentence features along with other handcrafted features. Kummerfeld et al (2019) uses feed-forward networks with averaged pre-trained word embedding and many hand-engineered features. Tan et al (2019) used an utterance-level LSTM network, while Zhu et al (2019) used a masked transformer to get a contextaware utterance representation considering utterances in the same conversation
Highlights
  • With the fast growth of Internet and mobile devices, people commonly communicate in the virtual world to discuss events, issues, tasks, and personal experiences
  • In the table we show the results for two variants of the models: (i) when the models consider only the utterance texts, as denoted by (T) suffix; (ii) when the models exclude the utterance text, as denoted by (−T) suffix
  • We have proposed a novel online framework for disentangling multi-party conversations
  • In contrast to previous work, our method reduces the effort of complicated feature engineering by proposing an utterance encoder and a pointer module that models inter-utterance interactions
  • Link prediction in our framework is modeled as a pointing function with a multinomial distribution over previous utterances
  • Extensive experiments have been conducted on the #Ubuntu dataset, which show that our method achieves state-of-the-art performance on both link and conversation prediction tasks without using any handcrafted features
Results
  • The authors present the main results in Table 2.
  • In the table the authors show the results for two variants of the models: (i) when the models consider only the utterance texts, as denoted by (T) suffix; (ii) when the models exclude the utterance text, as denoted by (−T) suffix.
  • SHCNN mainly focuses on modeling message content representations and only incorporates four context features: speaker identicality, absolute time difference, and the number of duplicate words.
  • The performance is not as good as the feed-forward model with many hand-engineered features
Conclusion
  • The authors have proposed a novel online framework for disentangling multi-party conversations.
  • In contrast to previous work, the method reduces the effort of complicated feature engineering by proposing an utterance encoder and a pointer module that models inter-utterance interactions.
  • Link prediction in the framework is modeled as a pointing function with a multinomial distribution over previous utterances.
  • Extensive experiments have been conducted on the #Ubuntu dataset, which show that the method achieves state-of-the-art performance on both link and conversation prediction tasks without using any handcrafted features
Tables
  • Table1: Statistics of train, dev and test datasets
  • Table2: Experimental results on the Ubuntu test set. “T” suffix means the model uses only utterance text. “−T” indicates the model excludes utterance text. “Joint Train” indicates the model is trained with the joint learning objective (Eq 15), “Self Link” indicate the model is decoded with self-link threshold re-adjustment
  • Table3: Self-link statistics on Ubuntu Dataset
  • Table4: Table 4
  • Table5: Self-link prediction results for the baseline model (<a class="ref-link" id="cKummerfeld_et+al_2019_a" href="#rKummerfeld_et+al_2019_a">Kummerfeld et al, 2019</a>)
Download tables as Excel
Funding
  • Our experiments on the Ubuntu IRC dataset show that our method achieves state-of-the-art performance in both link and conversation prediction tasks
  • Combined with joint training, our online decoding algorithm achieves state-of-the-art results
  • Extensive experiments have been conducted on the #Ubuntu dataset, which show that our method achieves state-of-the-art performance on both link and conversation prediction tasks without using any handcrafted features
Study subjects and analysis
participants: 4
consider the excerpt of a multi-party conversation in Figure 1 taken from the Ubuntu IRC corpus (Lowe et al, 2015). Even in this small excerpt, there are 4 concurrent conversations (distinguished by different colors) among 4 participants. Identifying or disentangling individual conversations is often considered as a prerequisite for downstream dialog tasks such as utterance ranking and generation (Lowe et al, 2017; Kim et al, 2019)

Reference
  • Erik Aumayr, Jeffrey Chan, and Conor Hayes. 201Reconstruction of threaded conversations in online discussion forums. In Fifth International AAAI Conference on Weblogs and Social Media.
    Google ScholarLocate open access versionFindings
  • Qian Chen, Xiaodan Zhu, Zhenhua Ling, Si Wei, Hui Jiang, and Diana Inkpen. 2016. Enhanced lstm for natural language inference. arXiv preprint arXiv:1609.06038.
    Findings
  • Micha Elsner and Eugene Charniak. 2008. You talking to me? a corpus and algorithm for conversation disentanglement. In Proceedings of ACL-08: HLT, pages 834–842, Columbus, Ohio. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Micha Elsner and Eugene Charniak. 2010. Disentangling chat. Computational Linguistics, 36(3):389– 409.
    Google ScholarLocate open access versionFindings
  • Micha Elsner and Eugene Charniak. 2011. Disentangling chat with local coherence models. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language
    Google ScholarLocate open access versionFindings
  • Technologies, pages 1179–1189, Portland, Oregon, USA. Association for Computational Linguistics.
    Google ScholarFindings
  • Sepp Hochreiter and Jurgen Schmidhuber. 199Long short-term memory. Neural computation, 9(8):1735–1780.
    Google ScholarLocate open access versionFindings
  • Lawrence Hubert and Phipps Arabie. 1985. Comparing partitions. Journal of classification, 2(1):193– 218.
    Google ScholarLocate open access versionFindings
  • Shenhao Jiang, Animesh Prasad, Min-Yen Kan, and Kazunari Sugiyama. 2018. Identifying emergent research trends by key authors and phrases. In Proceedings of the 27th International Conference on Computational Linguistics, pages 259–269, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Shafiq Joty, Giuseppe Carenini, Raymond Ng, and Gabriel Murray. 2019. Discourse analysis and its applications. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pages 12–17, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Seokhwan Kim, Michel Galley, Chulaka Gunasekara, Sungjin Lee, Adam Atkinson, Baolin Peng, Hannes Schulz, Jianfeng Gao, Jinchao Li, Mahmoud Adada, Minlie Huang, Luis Lastras, Jonathan K. Kummerfeld, Walter S. Lasecki, Chiori Hori, Anoop Cherian, Tim K. Marks, Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, and Raghav Gupta. 2019. The eighth dialog system technology challenge.
    Google ScholarFindings
  • Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
    Findings
  • Jonathan K. Kummerfeld, Sai R. Gouravajhala, Joseph Peper, Vignesh Athreya, Chulaka Gunasekara, Jatin Ganhotra, Siva Sankalp Patel, Lazaros Polymenakos, and Walter S. Lasecki. 2019. A large-scale corpus for conversation disentanglement. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
    Google ScholarLocate open access versionFindings
  • Changki Lee, Sangkeun Jung, and Cheon-Eum Park. 2017. Anaphora resolution with pointer networks. Pattern Recognition Letters, 95:1–7.
    Google ScholarLocate open access versionFindings
  • Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, and M Saiful Bari. 2019. A unified linear-time framework for sentence-level discourse parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4190– 4200, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Ryan Lowe, Nissan Pow, Iulian Serban, and Joelle Pineau. 2015. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909.
    Findings
  • Ryan Thomas Lowe, Nissan Pow, Iulian Vlad Serban, Laurent Charlin, Chia-Wei Liu, and Joelle Pineau. 20Training end-to-end dialogue systems with the ubuntu dialogue corpus. Dialogue & Discourse, 8(1):31–65.
    Google ScholarLocate open access versionFindings
  • Xuezhe Ma, Zecong Hu, Jingzhou Liu, Nanyun Peng, Graham Neubig, and Eduard Hovy. 20Stackpointer networks for dependency parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1403–1414, Melbourne, Australia. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Andrew McCallum and Ben Wellner. 2005. Conditional models of identity uncertainty with application to noun coreference. In L. K. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems 17, pages 905–912. MIT Press.
    Google ScholarLocate open access versionFindings
  • Shikib Mehri and Giuseppe Carenini. 2017. Chat disentanglement: Identifying semantic reply relationships with random forests and recurrent neural networks. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 615–623, Taipei, Taiwan. Asian Federation of Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • Marina Meila. 2007. Comparing clusterings—an information based distance. Journal of multivariate analysis, 98(5):873–895.
    Google ScholarLocate open access versionFindings
  • Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, and Xiaoli Li. 2020. Efficient constituency parsing by pointing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL’20, pages xx—-xx, Seattle, USA. ACL.
    Google ScholarLocate open access versionFindings
  • Jacki O’Neill and David Martin. 2003. Text chat in action. In Proceedings of the 2003 International ACM SIGGROUP Conference on Supporting Group Work, GROUP ’03, pages 40–49, New York, NY, USA. ACM.
    Google ScholarLocate open access versionFindings
  • Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In EMNLP’14, pages 1532–1543, Doha, Qatar.
    Google ScholarLocate open access versionFindings
  • Dou Shen, Qiang Yang, Jian-Tao Sun, and Zheng Chen. 2006. Thread detection in dynamic text message streams. In Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’06, pages 35–42, New York, NY, USA. ACM.
    Google ScholarLocate open access versionFindings
  • Alessandro Sordoni, Yoshua Bengio, Hossein Vahabi, Christina Lioma, Jakob Grue Simonsen, and JianYun Nie. 2015. A hierarchical recurrent encoderdecoder for generative context-aware query suggestion. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pages 553–562. ACM.
    Google ScholarLocate open access versionFindings
  • Ming Tan, Dakuo Wang, Yupeng Gao, Haoyu Wang, Saloni Potdar, Xiaoxiao Guo, Shiyu Chang, and Mo Yu. 2019. Context-aware conversation thread detection in multi-party chat. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6455–6460, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In Advances in Neural Information Processing Systems, pages 2692–2700.
    Google ScholarLocate open access versionFindings
  • Hongning Wang, Chi Wang, ChengXiang Zhai, and Jiawei Han. 2011a. Learning online discussion structures by conditional random fields. In Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, pages 435–444. ACM.
    Google ScholarLocate open access versionFindings
  • Li Wang, Marco Lui, Su Nam Kim, Joakim Nivre, and Timothy Baldwin. 2011b. Predicting thread discourse structure over technical web forums. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 13–25. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Lidan Wang and Douglas W Oard. 2009. Contextbased message expansion for disentanglement of interleaved text conversations. In Proceedings of human language technologies: The 2009 annual conference of the North American chapter of the association for computational linguistics, pages 200–208. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Weishi Wang, Shafiq Joty, and Steven C.H. Hoi. 2020. Response selection for multi-party conversations with dynamic topic tracking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP’20, pages XX—XX, Virtual. ACL.
    Google ScholarLocate open access versionFindings
  • Henghui Zhu, Feng Nan, Zhiguo Wang, Ramesh Nallapati, and Bing Xiang. 2019. Who did they respond to? conversation structure modeling using masked hierarchical transformer. arXiv preprint arXiv:1911.10666.
    Findings
Author
Tao Yu
Tao Yu
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科