AI helps you reading Science

AI generates interpretation videos

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


pub
View the video

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:
We present a novel and extensive approach which formulates the incomplete utterance rewriting as a semantic segmentation task

Incomplete Utterance Rewriting as Semantic Segmentation

EMNLP 2020, pp.2846-2857, (2020)

Cited by: 0|Views363
Full Text
Bibtex
Weibo

Abstract

Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we present a novel and extensive approach, which formulates it as a semantic segmentation task. Instead o...More

Code:

Data:

0
Introduction
  • A dramatic progress has been achieved in singleturn dialogue modeling such as open-domain response generation (Shang et al, 2015), question answering (Rajpurkar et al, 2016), etc.
  • Multi-turn dialogue modeling is still in its infancy, as users tend to use incomplete utterances which usually omit or refer back to entities or concepts appeared in the dialogue context, namely ellipsis and coreference.
  • 北京今天是阴天 Beijing is cloudy today.
  • As shown in Table 1, the incomplete utterance x3 omits the subject “北京”(Beijing), and refers to the semantic of “阴 天”(cloudy) via “这 样”(this).
  • By explicitly recovering the hidden semantics behind x3 into x∗3, IUR makes the downstream dialogue modeling more precise
Highlights
  • A dramatic progress has been achieved in singleturn dialogue modeling such as open-domain response generation (Shang et al, 2015), question answering (Rajpurkar et al, 2016), etc
  • In this paper, we propose a novel and extensive approach which formulates IUR as semantic segmentation1
  • As far as we know, we are the first to present such a highly extensive approach which formulates the incomplete utterance rewriting as a semantic segmentation task
  • Our work is different from theirs since we model the editing process between two sentences as a semantic segmentation task
  • As in literature (Pan et al, 2019), we examine Rewritten U-shaped Network (RUN) using the widely used automatic metrics BLEU, ROUGE, EM and Rewriting F-score. (i) BLEUn (Bn) evaluates how similar the rewritten utterances are to the golden ones via the cumulative n-gram BLEU score (Papineni et al, 2002). (ii) ROUGEn (Rn) measures the n-gram overlapping between the rewritten utterances and the golden ones, while ROUGEL (RL) measures the longest matching sequence between them (Lin, 2004). (iii) EM stands for the exact match ac
  • Benefiting from being able to capture both local and global information, our approach achieves state-of-the-art performance on several datasets across different domains and languages
  • We present a novel and extensive approach which formulates the incomplete utterance rewriting as a semantic segmentation task
Methods
  • As shown in Figure 2, the approach firstly obtains the word-level edit matrix through three neural layers.
  • Based on the word-level edit matrix, it applies a generation algorithm to produce the rewritten utterance.
  • To construct a word-level edit matrix, the model passes through three neural layers: a context layer, an encoding layer and a subsequent segmentation layer.
Results
  • The authors employ both automatic metrics and human evaluations to evaluate the approach. As in literature (Pan et al, 2019), the authors examine RUN using the widely used automatic metrics BLEU, ROUGE, EM and Rewriting F-score. (i) BLEUn (Bn) evaluates how similar the rewritten utterances are to the golden ones via the cumulative n-gram BLEU score (Papineni et al, 2002). (ii) ROUGEn (Rn) measures the n-gram overlapping between the rewritten utterances and the golden ones, while ROUGEL (RL) measures the longest matching sequence between them (Lin, 2004). (iii) EM stands for the exact match ac- Model

    Syntactic † L-Gen † L-Ptr-Gen † RUN (Ours)

    PAC † RUN + BERT (Ours) P1 R1 F1 P2 R2 F2 P3.
  • As in literature (Pan et al, 2019), the authors examine RUN using the widely used automatic metrics BLEU, ROUGE, EM and Rewriting F-score.
  • (i) BLEUn (Bn) evaluates how similar the rewritten utterances are to the golden ones via the cumulative n-gram BLEU score (Papineni et al, 2002).
  • (ii) ROUGEn (Rn) measures the n-gram overlapping between the rewritten utterances and the golden ones, while ROUGEL (RL) measures the longest matching sequence between them (Lin, 2004).
Conclusion
  • While the approach has made some progress, it still has several limitations. First, the model severely relies on the word order implied by the dialogue.
  • The second limitation is that the authors predict edit types of each cell independently, ignoring the relationship between neighboring edit types.
  • The above limitations may raise concerns about the performance upper bound of the approach.
  • It is not an issue.
  • On three out of four datasets used in the experiments, more than 85% examples could be tackled perfectly by the approach (87.6% in TASK, 91.0% in REWRITE, 95.3% in MULTI).
  • The authors will investigate on extending the approach to more areas
Summary
  • Introduction:

    A dramatic progress has been achieved in singleturn dialogue modeling such as open-domain response generation (Shang et al, 2015), question answering (Rajpurkar et al, 2016), etc.
  • Multi-turn dialogue modeling is still in its infancy, as users tend to use incomplete utterances which usually omit or refer back to entities or concepts appeared in the dialogue context, namely ellipsis and coreference.
  • 北京今天是阴天 Beijing is cloudy today.
  • As shown in Table 1, the incomplete utterance x3 omits the subject “北京”(Beijing), and refers to the semantic of “阴 天”(cloudy) via “这 样”(this).
  • By explicitly recovering the hidden semantics behind x3 into x∗3, IUR makes the downstream dialogue modeling more precise
  • Methods:

    As shown in Figure 2, the approach firstly obtains the word-level edit matrix through three neural layers.
  • Based on the word-level edit matrix, it applies a generation algorithm to produce the rewritten utterance.
  • To construct a word-level edit matrix, the model passes through three neural layers: a context layer, an encoding layer and a subsequent segmentation layer.
  • Results:

    The authors employ both automatic metrics and human evaluations to evaluate the approach. As in literature (Pan et al, 2019), the authors examine RUN using the widely used automatic metrics BLEU, ROUGE, EM and Rewriting F-score. (i) BLEUn (Bn) evaluates how similar the rewritten utterances are to the golden ones via the cumulative n-gram BLEU score (Papineni et al, 2002). (ii) ROUGEn (Rn) measures the n-gram overlapping between the rewritten utterances and the golden ones, while ROUGEL (RL) measures the longest matching sequence between them (Lin, 2004). (iii) EM stands for the exact match ac- Model

    Syntactic † L-Gen † L-Ptr-Gen † RUN (Ours)

    PAC † RUN + BERT (Ours) P1 R1 F1 P2 R2 F2 P3.
  • As in literature (Pan et al, 2019), the authors examine RUN using the widely used automatic metrics BLEU, ROUGE, EM and Rewriting F-score.
  • (i) BLEUn (Bn) evaluates how similar the rewritten utterances are to the golden ones via the cumulative n-gram BLEU score (Papineni et al, 2002).
  • (ii) ROUGEn (Rn) measures the n-gram overlapping between the rewritten utterances and the golden ones, while ROUGEL (RL) measures the longest matching sequence between them (Lin, 2004).
  • Conclusion:

    While the approach has made some progress, it still has several limitations. First, the model severely relies on the word order implied by the dialogue.
  • The second limitation is that the authors predict edit types of each cell independently, ignoring the relationship between neighboring edit types.
  • The above limitations may raise concerns about the performance upper bound of the approach.
  • It is not an issue.
  • On three out of four datasets used in the experiments, more than 85% examples could be tackled perfectly by the approach (87.6% in TASK, 91.0% in REWRITE, 95.3% in MULTI).
  • The authors will investigate on extending the approach to more areas
Tables
  • Table1: An example dialogue between user A and B, including the context utterances (x1, x2), the incomplete utterance (x3) and the rewritten utterance (x∗3)
  • Table2: The experimental results of (Top) general and (Bottom) BERT-based results on MULTI. †: Results from <a class="ref-link" id="cPan_et+al_2019_a" href="#rPan_et+al_2019_a">Pan et al (2019</a>). A bolded number in a column indicates a statistically significant improvement against all the baselines (p < 0.05), whereas underline numbers show comparable performances. Both are same for Table 4&5
  • Table3: Statistics of different datasets. NA means the development set is also the test set. “Ques” is short for questions, “Avg” for average, “len” for length, “Con” for context utterance, “Cur” for current utterance, and “Rew” for rewritten utterance
  • Table4: The experimental results on REWRITE. †: Reproduced from the code released by <a class="ref-link" id="cSu_et+al_2019_a" href="#rSu_et+al_2019_a">Su et al (2019</a>)
  • Table5: The experimental results on (Left) TASK and (Right) CANARD. †: Results from <a class="ref-link" id="cQuan_et+al_2019_a" href="#rQuan_et+al_2019_a">Quan et al (2019</a>)
  • Table6: Pairwise human evaluation results about the rewritten utterance fluency on randomly sampled 500 dialogues from REWRITE. Our approach achieves similar or better fluency compared with top baselines
  • Table7: Human rating evaluations about the response quality on sampled 300 dialogues from the development set of MULTI. The score ranges from 0 to 2. “NR” represents the proportion of rewritten utterances which are equal to current utterances
  • Table8: The inference speed comparison between RUN and baselines. Beam stands for the beam size in beam search, not applicable for RUN. Latency is computed as the time to produce a single sentence without data batching, averaged over the development set of REWRITE. All models are implemented in PyTorch on a single NVIDIA V100
  • Table9: The ablation results on the development set of MULTI. “w/o Edit” means directly using the current utterance as the rewritten utterance. “w/o U-shape seg.” means that our segmentation layer is replaced by a feed-forward neural network with comparable parameters. The remaining variants ablate different similarity functions in the encoding layer
Download tables as Excel
Related work
  • The most related work to ours is the line of incomplete utterance rewriting. Recently, it has raised a large attention in several domains. In question answering, previous works include non-sentential utterance resolution using the sequence to sequence based architecture (Kumar and Joshi, 2016), incomplete follow-up question resolution via a retrieval sequence to sequence model (Kumar and Joshi, 2017) and sequence to sequence model with a copy mechanism (Elgohary et al, 2019; Quan et al, 2019). In conversational semantic parsing, Liu et al (2019b) proposed a novel approach which considers the structures of questions, while None Substitute Insert

    ∗ = ( 1, 2, 3, 4, 4, 5, 6, 6, 7, 9, 10, 7, 8 , ... , )

    Liu et al (2019a) imposed an intermediate structure span and decomposed the incomplete utterance rewriting into two sub-tasks. In dialogue generation, Pan et al (2019) presented a cascaded model which first picks words from the context via BERT, and then combines these words to generate the rewritten utterance, and Su et al (2019) distinguished the weights of context utterances and the incomplete utterance using a hyper-parameter λ. Different from all of them, we formulate the task as a semantic segmentation task.
Funding
  • This work was supported in part by National Natural Science Foundation of China (U1736217 and 61932003), and National Key R&D Program of China (2019YFF0302902)
Study subjects and analysis
data: 1
Although c and x are jointly encoded by BiLSTM (see the left of Figure 2), below we distinguish their hidden states for clear illustration. For a word cm(m = 1, . . . , M ) in c, its hidden state is denoted by um obtained through BiLSTM, while the hidden state hn is for word xn(n = 1, · · · , N ) in the incomplete utterance.As shown in Figure 2, our approach firstly obtains the word-level edit matrix through three neural layers. Then based on the word-level edit matrix, it applies a generation algorithm to produce the rewritten utterance

data: 1
Although c and x are jointly encoded by BiLSTM (see the left of Figure 2), below we distinguish their hidden states for clear illustration. For a word cm(m = 1, . . . , M ) in c, its hidden state is denoted by um obtained through BiLSTM, while the hidden state hn is for word xn(n = 1, · · · , N ) in the incomplete utterance. Encoding Layer On top of the context-aware hidden states, we consider several similarity functions to encode the word-to-word relevance

public datasets: 4
5.1 Experimental Setup. Datasets We conduct experiments on four public datasets across different domains: OpenDomain Dialogue MULTI Pan et al, 2019, REWRITE Su et al, 2019 , Task-Oriented Dialogue TASK Quan et al, 2019 and Question Answering in Context CANARD Elgohary et al, 2019. We use the same data split for these datasets as their original paper, and some statistics are shown in Table 3

workers: 5
The response candidate pool was formed by all utterances in MULTI. Finally, 5 workers were asked to evaluate responses following a multi-scale rating from 0 to 2: 0 means the response is not related to the dialogue; 1 means the response is related but not interesting enough; and 2 means the response is satisfying. To illustrate more clearly, we also conduct human rating evaluation on responses under the settings of original dialogue (i.e. without rewriting, relying on the SMN model itself to understand the context) and gold dialogue (i.e. human rewriting)

Reference
  • Anurag Arnab, Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Mans Larsson, Alexander Kirillov, Bogdan Savchynskyy, Carsten Rother, Fredrik Kahl, and Philip H. S. Torr. 2018. Conditional random fields meet deep neural networks for semantic segmentation: Combining probabilistic graphical models with deep learning for structured prediction. IEEE Signal Process. Mag., 35(1):37–52.
    Google ScholarLocate open access versionFindings
  • Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
    Google ScholarLocate open access versionFindings
  • Kevin Clark and Christopher D. Manning. 2015. Entity-centric coreference resolution with model stacking. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1405–1415, Beijing, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Kevin Clark and Christopher D. Manning. 2016. Improving coreference resolution by learning entitylevel distributed representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 643–653, Berlin, Germany. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Ahmed Elgohary, Denis Peskov, and Jordan BoydGraber. 2019. Can you unpack that? learning to rewrite questions-in-context. In Proceedings of the
    Google ScholarLocate open access versionFindings
  • 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5918–5924, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 201AllenNLP: A deep semantic natural language processing platform. In Proceedings of Workshop for NLP Open Source Software (NLP-OSS), pages 1– 6, Melbourne, Australia. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O.K. Li. 2016. Incorporating copying mechanism in sequence-to-sequence learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1631–1640, Berlin, Germany. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Hua He and Jimmy Lin. 2016. Pairwise word interaction modeling with deep neural networks for semantic similarity measurement. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 937– 948, San Diego, California. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Sepp Hochreiter and Jurgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780.
    Google ScholarLocate open access versionFindings
  • Joseph Hoshen and Raoul Kopelman. 1976. Percolation and cluster distribution. i. cluster multiple labeling technique and critical concentration algorithm. Physical Review B, 14:3438–3445.
    Google ScholarLocate open access versionFindings
  • Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77.
    Google ScholarLocate open access versionFindings
  • Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. BERT for coreference resolution: Baselines and analysis. 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 5803–5808, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Diederik P Kingma and Jimmy Ba. 20Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
    Google ScholarLocate open access versionFindings
  • Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander Rush. 2017. OpenNMT: Open-source toolkit for neural machine translation. In Proceedings of ACL 2017, System Demonstrations, pages 67–72, Vancouver, Canada. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Vineet Kumar and Sachindra Joshi. 2016. Nonsentential question resolution using sequence to sequence learning. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2022–2031, Osaka, Japan. The COLING 2016 Organizing Committee.
    Google ScholarLocate open access versionFindings
  • Vineet Kumar and Sachindra Joshi. 2017. Incomplete follow-up question resolution using retrieval based sequence to sequence learning. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’17, page 705–714, New York, NY, USA. Association for Computing Machinery.
    Google ScholarLocate open access versionFindings
  • Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-tofine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 687–692, New Orleans, Louisiana. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
    Google ScholarFindings
  • Qian Liu, Bei Chen, Haoyan Liu, Jian-Guang Lou, Lei Fang, Bin Zhou, and Dongmei Zhang. 2019a. A split-and-recombine approach for follow-up query analysis. 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 5316–5326, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Qian Liu, Bei Chen, Jian-Guang Lou, Ge Jin, and Dongmei Zhang. 2019b. FANDA: A novel approach to perform follow-up query analysis. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pages 6770–6777. AAAI Press.
    Google ScholarLocate open access versionFindings
  • Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, and Aliaksei Severyn. 2019.
    Google ScholarFindings
  • Encode, tag, realize: High-precision text editing. 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 5054–5065, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Zhufeng Pan, Kun Bai, Yan Wang, Lianqiang Zhou, and Xiaojiang Liu. 2019. Improving open-domain dialogue systems via multi-turn incomplete utterance restoration. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), pages 1824–1833, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, and Xueqi Cheng. 2016. Text matching as image recognition. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pages 2793–2799. AAAI Press.
    Google ScholarLocate open access versionFindings
  • Kishore Papineni, Salim Roukos, Todd Ward, and WeiJing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, ACL 2002, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alche-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada. Curran Associates, Inc.
    Google ScholarLocate open access versionFindings
  • Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Jun Quan, Deyi Xiong, Bonnie Webber, and Changjian Hu. 2019. GECOR: An end-to-end generative ellipsis and co-reference resolution model for taskoriented dialogue. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), pages 4547–4557, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), volume 9351 of LNCS, pages 234–241. Springer.
    Google ScholarLocate open access versionFindings
  • Mike Schuster and Kuldip K Paliwal. 1997. Bidirectional recurrent neural networks. Trans. Sig. Proc., 45(11):2673–2681.
    Google ScholarLocate open access versionFindings
  • Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointergenerator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073– 1083, Vancouver, Canada. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, and Yoshua Bengio. 2017. A hierarchical latent variable encoder-decoder model for generating dialogues. In Thirty-First AAAI Conference on Artificial Intelligence.
    Google ScholarLocate open access versionFindings
  • Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. Neural responding machine for short-text conversation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1577–1586, Beijing, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, and Jie Zhou. 2019. Improving multi-turn dialogue modelling with utterance ReWriter. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 22–31, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 5998–6008.
    Google ScholarLocate open access versionFindings
  • Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems 28, pages 2692–2700. Curran Associates, Inc.
    Google ScholarLocate open access versionFindings
  • Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, and Jamie Brew. 2019. Huggingface’s transformers: State-of-the-art natural language processing. CoRR, abs/1910.03771.
    Findings
  • Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, and Jiwei Li. 2020. CorefQA: Coreference resolution as query-based span prediction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6953–6963, Online. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Yu Wu, Furu Wei, Shaohan Huang, Yunli Wang, Zhoujun Li, and Ming Zhou. 2019. Response generation by context-aware prototype editing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7281–7288.
    Google ScholarLocate open access versionFindings
  • Yu Wu, Wei Wu, Chen Xing, Ming Zhou, and Zhoujun Li. 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 496–505, Vancouver, Canada. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Rui Yan, Yiping Song, and Hua Wu. 2016. Learning to respond with deep neural networks for retrievalbased human-computer conversation system. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’16, page 55–64, New York, NY, USA. Association for Computing Machinery.
    Google ScholarLocate open access versionFindings
  • Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, and Ting Liu. 2018. Context-sensitive generation of open-domain conversational responses. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2437–2447, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Kun Zhou, Kai Zhang, Yu Wu, Shujie Liu, and Jingsong Yu. 2019. Unsupervised context rewriting for open domain conversation. 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 1834–1844, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
小科