1 code implementation • ACL 2022 • Junzhuo Li, Deyi Xiong
In this paper, we study two issues of semantic parsing approaches to conversational question answering over a large-scale knowledge base: (1) The actions defined in grammar are not sufficient to handle uncertain reasoning common in real-world scenarios.
no code implementations • AACL (iwdp) 2020 • Xinyi Cai, Deyi Xiong
The need to evaluate the ability of context-aware neural machine translation (NMT) models in dealing with specific discourse phenomena arises in document-level NMT.
no code implementations • EMNLP 2020 • Wanqiu Long, Bonnie Webber, Deyi Xiong
As different genres are known to differ in their communicative properties and as previously, for Chinese, discourse relations have only been annotated over news text, we have created the TED-CDB dataset.
no code implementations • COLING (CODI, CRAC) 2022 • Jie He, Wanqiu Long, Deyi Xiong
Large pre-trained neural models have achieved remarkable success in natural language process (NLP), inspiring a growing body of research analyzing their ability from different aspects.
no code implementations • FL4NLP (ACL) 2022 • Xinwei Wu, Li Gong, Deyi Xiong
Although differential privacy (DP) can protect language models from leaking privacy, its indiscriminative protection on all data points reduces its practical utility.
no code implementations • EMNLP 2021 • Huibin Ge, Chenxi Sun, Deyi Xiong, Qun Liu
Experiment results show that the Chinese pretrained language model PanGu-\alpha is 45 points behind human in terms of top-1 word prediction accuracy, indicating that Chinese WPLC is a challenging dataset.
no code implementations • EMNLP 2021 • Jiachen Tian, Shizhan Chen, Xiaowang Zhang, Zhiyong Feng, Deyi Xiong, Shaojuan Wu, Chunliu Dou
Difficult samples of the minority class in imbalanced text classification are usually hard to be classified as they are embedded into an overlapping semantic region with the majority class.
1 code implementation • EMNLP 2021 • Erguang Yang, Mingtong Liu, Deyi Xiong, Yujie Zhang, Yao Meng, Changjian Hu, Jinan Xu, Yufeng Chen
Particularly, we design a two-stage learning method to effectively train the model using non-parallel data.
1 code implementation • ACL 2022 • Yifei Luo, Minghui Xu, Deyi Xiong
Is there a principle to guide transfer learning across tasks in natural language processing (NLP)?
1 code implementation • COLING 2022 • Yikun Lei, Yuqi Ren, Deyi Xiong
In this paper, we propose a document-level neural machine translation framework, CoDoNMT, which models cohesion devices from two perspectives: Cohesion Device Masking (CoDM) and Cohesion Attention Focusing (CoAF).
no code implementations • COLING 2022 • Haoran Sun, Deyi Xiong
Knowledge transfer across languages is crucial for multilingual neural machine translation.
no code implementations • COLING 2022 • Wenjie Hao, Hongfei Xu, Deyi Xiong, Hongying Zan, Lingling Mu
Paraphrasing, i. e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP).
no code implementations • Findings (NAACL) 2022 • Erguang Yang, Chenglin Bai, Deyi Xiong, Yujie Zhang, Yao Meng, Jinan Xu, Yufeng Chen
To model the alignment relation between words and nodes, we propose an attention regularization objective, which makes the decoder accurately select corresponding syntax nodes to guide the generation of words. Experiments show that SI-SCP achieves state-of-the-art performances in terms of semantic and syntactic quality on two popular benchmark datasets. Additionally, we propose a Syntactic Template Retriever (STR) to retrieve compatible syntactic structures.
no code implementations • 12 Mar 2024 • Yan Liu, Renren Jin, Lin Shi, Zheng Yao, Deyi Xiong
We conduct extensive experiments on a wide range of LLMs on FineMath and find that there is still considerable room for improvements in terms of mathematical reasoning capability of Chinese LLMs.
1 code implementation • 28 Feb 2024 • Shaoyang Xu, Weilong Dong, Zishan Guo, Xinwei Wu, Deyi Xiong
Drawing from our findings on multilingual value alignment, we prudently provide suggestions on the composition of multilingual data for LLMs pre-training: including a limited number of dominant languages for cross-lingual alignment transfer while avoiding their excessive prevalence, and keeping a balanced distribution of non-dominant languages.
no code implementations • 28 Feb 2024 • Yuqi Ren, Renren Jin, Tongxuan Zhang, Deyi Xiong
We employ Representational Similarity Analysis (RSA) to mearsure the alignment between 16 mainstream LLMs and fMRI signals of the brain.
no code implementations • 26 Feb 2024 • Renren Jin, Jiangcun Du, Wuwei Huang, Wei Liu, Jian Luan, Bin Wang, Deyi Xiong
Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks.
1 code implementation • 26 Dec 2023 • Tianhao Shen, Sun Li, Quan Tu, Deyi Xiong
We expect that RoleEval would highlight the significance of assessing role knowledge for large language models across various languages and cultural settings.
no code implementations • 20 Dec 2023 • Dan Shi, Chaobin You, Jiantao Huang, Taihao Li, Deyi Xiong
With these pre-defined domains and slots, we collect 76, 787 commonsense knowledge annotations from 19, 700 dialogues through crowdsourcing.
no code implementations • 5 Dec 2023 • Xiaohua Xing, Yuqi Ren, Die Zou, Qiankun Zhang, Bingxuan Mao, Jianquan Yao, Deyi Xiong, Shuang Zhang, Liang Wu
Recently, artificial intelligence has been extensively deployed across various scientific disciplines, optimizing and guiding the progression of experiments through the integration of abundant datasets, whilst continuously probing the vast theoretical space encapsulated within the data.
no code implementations • 16 Nov 2023 • Yimin Jing, Renren Jin, Jiahao Hu, Huishi Qiu, Xiaohua Wang, Peng Wang, Deyi Xiong
In pursuit of this goal, various benchmarks have been constructed to evaluate the instruction-following capacity of these models.
no code implementations • 7 Nov 2023 • Shaoyang Xu, Junzhuo Li, Deyi Xiong
Multilingual pretrained language models serve as repositories of multilingual factual knowledge.
no code implementations • 31 Oct 2023 • Leiyu Pan, Supryadi, Deyi Xiong
In particular, we use character-, word-, and multi-level noises to attack the specific translation direction of the multilingual neural machine translation model and evaluate the robustness of other translation directions.
1 code implementation • 31 Oct 2023 • Haoran Sun, Xiaohu Zhao, Yikun Lei, Shaolin Zhu, Deyi Xiong
In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages.
1 code implementation • 31 Oct 2023 • Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong
The ability of data memorization and regurgitation in pretrained language models, revealed in previous studies, brings the risk of data leakage.
1 code implementation • 30 Oct 2023 • Zishan Guo, Renren Jin, Chuang Liu, Yufei Huang, Dan Shi, Supryadi, Linhao Yu, Yan Liu, Jiaxuan Li, Bojian Xiong, Deyi Xiong
We hope that this comprehensive overview will stimulate further research interests in the evaluation of LLMs, with the ultimate goal of making evaluation serve as a cornerstone in guiding the responsible development of LLMs.
no code implementations • 26 Sep 2023 • Tianhao Shen, Renren Jin, Yufei Huang, Chuang Liu, Weilong Dong, Zishan Guo, Xinwei Wu, Yan Liu, Deyi Xiong
We also envision bridging the gap between the AI alignment research community and the researchers engrossed in the capability exploration of LLMs for both capable and safe LLMs.
1 code implementation • 25 Jul 2023 • Yu Fu, Deyi Xiong, Yue Dong
To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection.
1 code implementation • 30 Jun 2023 • Mehrad Moradshahi, Tianhao Shen, Kalika Bali, Monojit Choudhury, Gaël de Chalendar, Anmol Goel, Sungkyun Kim, Prashant Kodali, Ponnurangam Kumaraguru, Nasredine Semmar, Sina J. Semnani, Jiwon Seo, Vivek Seshadri, Manish Shrivastava, Michael Sun, Aditya Yadavalli, Chaobin You, Deyi Xiong, Monica S. Lam
We create a new multilingual benchmark, X-RiSAWOZ, by translating the Chinese RiSAWOZ to 4 languages: English, French, Hindi, Korean; and a code-mixed English-Hindi language.
1 code implementation • 28 Jun 2023 • Yufei Huang, Deyi Xiong
In this work, we present a Chinese Bias Benchmark dataset that consists of over 100K questions jointly constructed by human experts and generative language models, covering stereotypes and societal biases in 14 social dimensions related to Chinese culture and values.
1 code implementation • 17 May 2023 • Chuang Liu, Renren Jin, Yuqi Ren, Linhao Yu, Tianyu Dong, Xiaohan Peng, Shuting Zhang, Jianxiang Peng, Peiyi Zhang, Qingqing Lyu, Xiaowen Su, Qun Liu, Deyi Xiong
Comprehensively evaluating the capability of large language models in multiple tasks is of great importance.
no code implementations • 19 Dec 2022 • Yu Fu, Deyi Xiong, Yue Dong
We introduce inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models, imitating human summarization behaviors.
no code implementations • 16 Dec 2022 • Weilong Dong, Xinwei Wu, Junzhuo Li, Shuangzhi Wu, Chao Bian, Deyi Xiong
It broadcasts the global model in the server to each client and produces pseudo data for clients so that knowledge from the global model can be explored to enhance few-shot learning of each client model.
no code implementations • 16 Dec 2022 • Junzhuo Li, Xinwei Wu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong
Knowledge distillation (KD) has been widely used for model compression and knowledge transfer.
no code implementations • 7 Nov 2022 • Tengxun Zhang, Hongfei Xu, Josef van Genabith, Deyi Xiong, Hongying Zan
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction.
1 code implementation • COLING 2022 • Renren Jin, Deyi Xiong
Experiment results on two datasets for massively multilingual neural machine translation demonstrate that language-aware multi-head attention benefits both supervised and zero-shot translation and significantly alleviates the off-target translation issue.
no code implementations • 22 Jun 2022 • Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina McMillan-Major, Anna Shvets, Ashish Upadhyay, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez-Beltrachini, Leonardo F. R. Ribeiro, Lewis Tunstall, Li Zhang, Mahima Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
no code implementations • 10 Jun 2022 • Zhiyuan Zeng, Deyi Xiong
We therefore extend the unsupervised models to few-shot parsing models (FPOA, FPIO) that use a few annotated trees to learn better linear projection matrices for parsing.
2 code implementations • ACL 2022 • Dexin Wang, Kai Fan, Boxing Chen, Deyi Xiong
k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT).
1 code implementation • ACL 2022 • Linjuan Wu, Shaojuan Wu, Xiaowang Zhang, Deyi Xiong, Shizhan Chen, Zhiqiang Zhuang, Zhiyong Feng
To explicitly transfer only semantic knowledge to the target language, we propose two groups of losses tailored for semantic and syntactic encoding and disentanglement.
no code implementations • 16 Dec 2021 • Yuqi Ren, Deyi Xiong
The proposed framework only requires cognitive processing signals recorded under natural reading as inputs, and can be used to detect a wide range of linguistic features with a single cognitive dataset.
no code implementations • Findings (EMNLP) 2021 • Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Hang Li, Deyi Xiong
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
no code implementations • ACL 2021 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong
In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality.
no code implementations • ACL 2021 • Zhiyuan Zeng, Deyi Xiong
For autoregressive NMT models that generate target words from left to right, we observe that adversarial attack on the source language is more effective than on the target language, and that attacking front positions of target sentences or positions of source sentences aligned to the front positions of corresponding target sentences is more effective than attacking other positions.
no code implementations • ACL 2021 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Meng Zhang
This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this.
no code implementations • ACL 2021 • Jie He, Bo Peng, Yi Liao, Qun Liu, Deyi Xiong
Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error.
1 code implementation • ACL 2021 • Yuqi Ren, Deyi Xiong
Most previous studies integrate cognitive language processing signals (e. g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring the gap between the two modalities (i. e., textual vs. cognitive) and noise in cognitive features.
no code implementations • NAACL 2021 • Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Deyi Xiong
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
1 code implementation • 30 Mar 2021 • Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Deyi Xiong
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
1 code implementation • 5 Mar 2021 • Jinsong Su, Jialong Tang, Hui Jiang, Ziyao Lu, Yubin Ge, Linfeng Song, Deyi Xiong, Le Sun, Jiebo Luo
In aspect-based sentiment analysis (ABSA), many neural models are equipped with an attention mechanism to quantify the contribution of each context word to sentiment prediction.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
no code implementations • 17 Feb 2021 • Jun Quan, Meng Yang, Qiang Gan, Deyi Xiong, Yiming Liu, Yuchen Dong, Fangxin Ouyang, Jun Tian, Ruiling Deng, Yongzhi Li, Yang Yang, Daxin Jiang
Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility.
no code implementations • 18 Dec 2020 • Dexin Wang, Deyi Xiong
In this paper, we propose an object-level visual context modeling framework (OVC) to efficiently capture and explore visual information for multimodal machine translation.
no code implementations • 15 Dec 2020 • Wenjie Qin, Xiang Li, Yuhui Sun, Deyi Xiong, Jianwei Cui, Bin Wang
In this paper, we propose a robust neural machine translation (NMT) framework.
no code implementations • COLING 2020 • Mingtong Liu, Erguang Yang, Deyi Xiong, Yujie Zhang, Yao Meng, Changjian Hu, Jinan Xu, Yufeng Chen
We propose a learning-exploring method to generate sentences as learning objectives from the learned data distribution, and employ reinforcement learning to combine these new learning objectives for model training.
no code implementations • COLING 2020 • Xu Cao, Deyi Xiong, Chongyang Shi, Chao Wang, Yao Meng, Changjian Hu
Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Jie He, Tao Wang, Deyi Xiong, Qun Liu
Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy ( 6 60. 1{\%}) and reasoning consistency (6 31{\%}).
1 code implementation • EMNLP 2020 • Jun Quan, Shian Zhang, Qian Cao, Zizhong Li, Deyi Xiong
In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations.
no code implementations • COLING 2020 • Yufang Huang, Wentao Zhu, Deyi Xiong, Yiye Zhang, Changjian Hu, Feiyu Xu
Unsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation.
no code implementations • Findings (EMNLP) 2021 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong
The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily.
no code implementations • 13 Jul 2020 • Hongfei Xu, Qiuhui Liu, Deyi Xiong, Josef van Genabith
In this paper, we suggest that the residual connection has its drawbacks, and propose to train Transformers with the depth-wise LSTM which regards outputs of layers as steps in time series instead of residual connections, under the motivation that the vanishing gradient problem suffered by deep networks is the same as recurrent networks applied to long sequences, while LSTM (Hochreiter and Schmidhuber, 1997) has been proven of good capability in capturing long-distance relationship, and its design may alleviate some drawbacks of residual connections while ensuring the convergence.
no code implementations • ACL 2020 • Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu, Jingyi Zhang
Considering that modeling phrases instead of words has significantly improved the Statistical Machine Translation (SMT) approach through the use of larger translation blocks ("phrases") and its reordering ability, modeling NMT at phrase level is an intuitive proposal to help the model capture long-distance relationships.
no code implementations • ACL 2020 • Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu
We propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate.
no code implementations • ACL 2020 • Jun Quan, Deyi Xiong
Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation.
no code implementations • 30 Mar 2020 • Pei Zhang, Xu Zhang, Wei Chen, Jian Yu, Yan-Feng Wang, Deyi Xiong
In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
no code implementations • NAACL 2021 • Hongfei Xu, Josef van Genabith, Qiuhui Liu, Deyi Xiong
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches.
1 code implementation • LREC 2020 • Wanqiu Long, Xinyi Cai, James E. M. Reid, Bonnie Webber, Deyi Xiong
Text corpora annotated with language-related properties are an important resource for the development of Language Technology.
no code implementations • 5 Dec 2019 • Jun Quan, Deyi Xiong
The training of task-oriented dialogue systems is often confronted with the lack of annotated data.
no code implementations • 2 Dec 2019 • Tao Wang, Shaohui Kuang, Deyi Xiong, António Branco
As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge.
no code implementations • 25 Nov 2019 • Qian Cao, Shaohui Kuang, Deyi Xiong
In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction.
no code implementations • ACL 2020 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Jingyi Zhang
In this paper, we first empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers.
no code implementations • IJCNLP 2019 • Xin Tan, Longyin Zhang, Deyi Xiong, Guodong Zhou
In this paper, we propose a hierarchical model to learn the global context for document-level neural machine translation (NMT).
1 code implementation • IJCNLP 2019 • Yimin Jing, Deyi Xiong, Yan Zhen
We analyze BiPaR in depth and find that BiPaR offers good diversification in prefixes of questions, answer types and relationships between questions and passages.
no code implementations • IJCNLP 2019 • Jiazuo Qiu, Deyi Xiong
The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer.
no code implementations • IJCNLP 2019 • Jun Quan, Deyi Xiong, Bonnie Webber, Changjian Hu
Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues.
no code implementations • IJCNLP 2019 • Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Lei LI
In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}.
3 code implementations • EMNLP 2018 • Biao Zhang, Deyi Xiong, Jinsong Su, Qian Lin, Huiji Zhang
Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English- German and English-French language pairs in terms of both translation quality and speed.
no code implementations • EMNLP 2018 • Qian Cao, Deyi Xiong
Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments.
no code implementations • COLING 2018 • Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Chao Bian
Neural machine translation with source-side attention have achieved remarkable performance.
no code implementations • COLING 2018 • Shiqi Zhang, Deyi Xiong
In this paper, we propose a new sentence weighting method for the domain adaptation of neural machine translation.
no code implementations • COLING 2018 • Shaohui Kuang, Deyi Xiong
Neural machine translation (NMT) systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring inter-sentence information.
1 code implementation • ACL 2018 • Biao Zhang, Deyi Xiong, Jinsong Su
To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer.
Ranked #61 on Machine Translation on WMT2014 English-German
no code implementations • 16 Jan 2018 • Jinsong Su, Shan Wu, Deyi Xiong, Yaojie Lu, Xianpei Han, Biao Zhang
Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper.
no code implementations • COLING 2018 • Shaohui Kuang, Deyi Xiong, Weihua Luo, Guodong Zhou
Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text.
no code implementations • ACL 2018 • Shaohui Kuang, Junhui Li, António Branco, Weihua Luo, Deyi Xiong
In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase.
no code implementations • EMNLP 2017 • Xing Wang, Zhaopeng Tu, Deyi Xiong, Min Zhang
Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does.
no code implementations • ACL 2017 • Junhui Li, Deyi Xiong, Zhaopeng Tu, Muhua Zhu, Min Zhang, Guodong Zhou
Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into NMT effectively to provide further improvements.
no code implementations • 27 Apr 2017 • Biao Zhang, Deyi Xiong, Jinsong Su
In this paper, we propose a novel GRU-gated attention model (GAtt) for NMT which enhances the degree of discrimination of context vectors by enabling source representations to be sensitive to the partial translation generated by the decoder.
no code implementations • COLING 2016 • Fangyuan Li, Ruihong Huang, Deyi Xiong, Min Zhang
Aiming to resolve high complexities of event descriptions, previous work (Huang and Riloff, 2013) proposes multi-faceted event recognition and a bootstrapping method to automatically acquire both event facet phrases and event expressions from unannotated texts.
no code implementations • COLING 2016 • Haiqing Tang, Deyi Xiong, Oier Lopez de Lacalle, Eneko Agirre
Selecting appropriate translations for source words with multiple meanings still remains a challenge for statistical machine translation (SMT).
no code implementations • COLING 2016 • Biao Zhang, Deyi Xiong, Jinsong Su, Hong Duan, Min Zhang
Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing.
no code implementations • COLING 2016 • Jinsong Su, Biao Zhang, Deyi Xiong, Ruochen Li, Jianmin Yin
After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model.
no code implementations • COLING 2016 • Haiqing Tang, Deyi Xiong, Min Zhang, ZhengXian Gong
In this paper, we study semantic dependencies between verbs and their arguments by modeling selectional preferences in the context of machine translation.
no code implementations • 17 Oct 2016 • Xing Wang, Zhengdong Lu, Zhaopeng Tu, Hang Li, Deyi Xiong, Min Zhang
Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years.
no code implementations • 25 Sep 2016 • Jinsong Su, Zhixing Tan, Deyi Xiong, Rongrong Ji, Xiaodong Shi, Yang Liu
Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences.
no code implementations • 29 Jul 2016 • Biao Zhang, Deyi Xiong, Jinsong Su
The vanilla sequence-to-sequence learning (seq2seq) reads and encodes a source sequence into a fixed-length vector only once, suffering from its insufficiency in modeling structural correspondence between the source and target sequence.
1 code implementation • EMNLP 2016 • Biao Zhang, Deyi Xiong, Jinsong Su, Hong Duan, Min Zhang
Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence.
1 code implementation • 25 May 2016 • Biao Zhang, Deyi Xiong, Jinsong Su
In this paper, we propose a bidimensional attention based recursive autoencoder (BattRAE) to integrate clues and sourcetarget interactions at multiple levels of granularity into bilingual phrase representations.
no code implementations • 12 Mar 2016 • Biao Zhang, Deyi Xiong, Jinsong Su
Inspired by this, we propose a neural recognizer for implicit discourse relation analysis, which builds upon a semantic memory that stores knowledge in a distributed fashion.
1 code implementation • EMNLP 2016 • Biao Zhang, Deyi Xiong, Jinsong Su, Qun Liu, Rongrong Ji, Hong Duan, Min Zhang
In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound.