Convolutional Neural Network Architectures for Matching Natural Language Sentences
- Baotian Hu, Zhengdong Lu, Hang Li, Qingcai Chen
- Computer ScienceNIPS
- 8 December 2014
Convolutional neural network models for matching two sentences are proposed, by adapting the convolutional strategy in vision and speech and nicely represent the hierarchical structures of sentences with their layer-by-layer composition and pooling.
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Jiatao Gu, Zhengdong Lu, Hang Li, V. Li
- Computer ScienceAnnual Meeting of the Association for…
- 21 March 2016
This paper incorporates copying into neural network-based Seq2Seq learning and proposes a new model called CopyNet with encoder-decoder structure which can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence.
AdaRank: a boosting algorithm for information retrieval
The proposed novel learning algorithm, referred to as AdaRank, repeatedly constructs 'weak rankers' on the basis of reweighted training data and finally linearly combines the weak rankers for making ranking predictions, which proves that the training process of AdaRank is exactly that of enhancing the performance measure used.
Neural Responding Machine for Short-Text Conversation
- Lifeng Shang, Zhengdong Lu, Hang Li
- Computer ScienceAnnual Meeting of the Association for…
- 8 March 2015
Empirical study shows that NRM can generate grammatically correct and content-wise appropriate responses to over 75% of the input text, outperforming state-of-the-arts in the same setting, including retrieval-based and SMT-based models.
LETOR: A benchmark collection for research on learning to rank for information retrieval
- Tao Qin, Tie-Yan Liu, Jun Xu, Hang Li
- Computer ScienceInformation retrieval (Boston)
- 1 August 2010
The details of the LETOR collection are described and it is shown how it can be used in different kinds of researches, and several state-of-the-art learning to rank algorithms on LETOR are compared.
Modeling Coverage for Neural Machine Translation
- Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, Hang Li
- Computer ScienceAnnual Meeting of the Association for…
- 19 January 2016
This paper proposes coverage-based NMT, which maintains a coverage vector to keep track of the attention history and improves both translation quality and alignment quality over standard attention- based NMT.
Adapting ranking SVM to document retrieval
- Yunbo Cao, Jun Xu, Tie-Yan Liu, Hang Li, Yalou Huang, H. Hon
- Computer ScienceAnnual International ACM SIGIR Conference on…
- 6 August 2006
Experimental results show that the modifications made in conventional Ranking SVM can outperform the conventional ranking SVM and other existing methods for document retrieval on two datasets and employ two methods to conduct optimization on the loss function: gradient descent and quadratic programming.
Learning to Rank for Information Retrieval and Natural Language Processing
- Hang Li
- Computer ScienceSynthesis Lectures on Human Language Technologies
- 22 April 2011
The author explains several example applications of learning to rank including web search, collaborative filtering, definition search, keyphrase extraction, query dependent summarization, and re-ranking in machine translation.
Context-aware query suggestion by mining click-through and session data
- Huanhuan Cao, Daxin Jiang, Hang Li
- Computer ScienceKnowledge Discovery and Data Mining
- 24 August 2008
This paper proposes a novel context-aware query suggestion approach which is in two steps, and outperforms two baseline methods in both coverage and quality of suggestions.
A general approximation framework for direct optimization of information retrieval measures
- Tao Qin, Tie-Yan Liu, Hang Li
- Computer ScienceInformation retrieval (Boston)
- 1 August 2010
A general framework for direct optimization of IR measures, which enjoys several theoretical advantages, and experiments on benchmark datasets show that the algorithms deduced from the framework are very effective when compared to existing methods.
...
...