Search Results for author: Lili Mou

Found 70 papers, 36 papers with code

Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach

1 code implementation Findings (EMNLP) 2021 Anup Anand Deshmukh, Qianqiu Zhang, Ming Li, Jimmy Lin, Lili Mou

In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages.

Chunking Transfer Learning

Weakly Supervised Reasoning by Neuro-Symbolic Approaches

no code implementations19 Sep 2023 Xianggen Liu, Zhengdong Lu, Lili Mou

Deep learning has largely improved the performance of various natural language processing (NLP) tasks.

Search and Learning for Unsupervised Text Generation

no code implementations18 Sep 2023 Lili Mou

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI.

Text Generation

Unsupervised Chunking with Hierarchical RNN

1 code implementation10 Sep 2023 Zijun Wu, Anup Anand Deshmukh, Yongkang Wu, Jimmy Lin, Lili Mou

Our approach involves a two-stage training process: pretraining with an unsupervised parser and finetuning on downstream NLP tasks.


f-Divergence Minimization for Sequence-Level Knowledge Distillation

1 code implementation27 Jul 2023 Yuqiao Wen, Zichao Li, Wenyu Du, Lili Mou

Experiments across four datasets show that our methods outperform existing KD approaches, and that our symmetric distilling losses can better force the student to learn from the teacher distribution.

Knowledge Distillation

Teacher Forcing Recovers Reward Functions for Text Generation

1 code implementation17 Oct 2022 Yongchang Hao, Yuxin Liu, Lili Mou

We additionally propose a simple modification to stabilize the RL training on non-parallel datasets with our induced reward function.

regression reinforcement-learning +2

An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

2 code implementations29 Sep 2022 Yuqiao Wen, Yongchang Hao, Yanshuai Cao, Lili Mou

Open-domain dialogue systems aim to interact with humans through natural language texts in an open-ended fashion.

Dialogue Generation

Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search

1 code implementation10 Aug 2022 Lucas N. Ferreira, Lili Mou, Jim Whitehead, Levi H. S. Lelis

We use Monte Carlo Tree Search as a decoding mechanism to steer the probability distribution learned by a language model towards a given emotion.

Language Modelling Music Generation

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

1 code implementation28 May 2022 Puyuan Liu, Xiang Zhang, Lili Mou

Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation.

Headline Generation Sentence Summarization

MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration

1 code implementation9 Feb 2022 Siguang Huang, Yunli Wang, Lili Mou, Huayue Zhang, Han Zhu, Chuan Yu, Bo Zheng

In previous work, researchers have developed several calibration methods to post-process the outputs of a predictor to obtain calibrated values, such as binning and scaling methods.

Medical Diagnosis

An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets

1 code implementation LREC 2022 Yuqiao Wen, Guoqing Luo, Lili Mou

Open-domain dialogue systems aim to converse with humans through text, and dialogue research has heavily relied on benchmark datasets.

Search and Learn: Improving Semantic Coverage for Data-to-Text Generation

1 code implementation6 Dec 2021 Shailza Jolly, Zi Xuan Zhang, Andreas Dengel, Lili Mou

To this end, we propose a search-and-learning approach that leverages pretrained language models but inserts the missing slots to improve the semantic coverage.

Data-to-Text Generation

Simulated annealing for optimization of graphs and sequences

no code implementations1 Oct 2021 Xianggen Liu, Pengyong Li, Fandong Meng, Hao Zhou, Huasong Zhong, Jie zhou, Lili Mou, Sen Song

The key idea is to integrate powerful neural networks into metaheuristics (e. g., simulated annealing, SA) to restrict the search space in discrete optimization.

Paraphrase Generation

Simulated Annealing for Emotional Dialogue Systems

no code implementations22 Sep 2021 Chengzhang Dong, Chenyang Huang, Osmar Zaïane, Lili Mou

Explicitly modeling emotions in dialogue generation has important applications, such as building empathetic personal companions.

Dialogue Generation

Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

1 code implementation18 Sep 2021 Zijun Wu, Zi Xuan Zhang, Atharva Naik, Zhijian Mei, Mauajama Firdaus, Lili Mou

In this work, we address the explainability of NLI by weakly supervised logical reasoning, and propose an Explainable Phrasal Reasoning (EPR) approach.

Explanation Generation Logical Reasoning +1

Semi-Supervised and Unsupervised Sense Annotation via Translations

no code implementations RANLP 2021 Bradley Hauer, Grzegorz Kondrak, Yixing Luan, Arnob Mallik, Lili Mou

Our two unsupervised methods refine sense annotations produced by a knowledge-based WSD system via lexical translations in a parallel corpus.

Machine Translation Translation +1

A Globally Normalized Neural Model for Semantic Parsing

no code implementations ACL (spnlp) 2021 Chenyang Huang, Wei Yang, Yanshuai Cao, Osmar Zaïane, Lili Mou

In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing.

Semantic Parsing

Generalized Equivariance and Preferential Labeling for GNN Node Classification

1 code implementation23 Feb 2021 Zeyu Sun, Wenjie Zhang, Lili Mou, Qihao Zhu, Yingfei Xiong, Lu Zhang

Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content.

General Classification Graph Classification +1

Formality Style Transfer with Shared Latent Space

1 code implementation COLING 2020 Yunli Wang, Yu Wu, Lili Mou, Zhoujun Li, WenHan Chao

Conventional approaches for formality style transfer borrow models from neural machine translation, which typically requires massive parallel data for training.

Formality Style Transfer Machine Translation +2

Stylized Text Generation: Approaches and Applications

no code implementations ACL 2020 Lili Mou, Olga Vechtomova

We start from the definition of style and different settings of stylized text generation, illustrated with various applications.

Style Transfer Text Generation

TreeGen: A Tree-Based Transformer Architecture for Code Generation

2 code implementations22 Nov 2019 Zeyu Sun, Qihao Zhu, Yingfei Xiong, Yican Sun, Lili Mou, Lu Zhang

TreeGen outperformed the previous state-of-the-art approach by 4. 5 percentage points on HearthStone, and achieved the best accuracy among neural network-based approaches on ATIS (89. 1%) and GEO (89. 6%).

Code Generation Semantic Parsing

Adversarial Learning on the Latent Space for Diverse Dialog Generation

1 code implementation COLING 2020 Kashif Khan, Gaurav Sahu, Vikash Balasubramanian, Lili Mou, Olga Vechtomova

Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation but also being able to generate fluent sentences during inference.

Stylized Text Generation Using Wasserstein Autoencoders with a Mixture of Gaussian Prior

no code implementations10 Nov 2019 Amirpasha Ghabussi, Lili Mou, Olga Vechtomova

Moreover, we can train our model on relatively small datasets and learn the latent representation of a specified class by adding external data with other styles/classes to our dataset.

Text Generation

Harnessing Pre-Trained Neural Networks with Rules for Formality Style Transfer

no code implementations IJCNLP 2019 Yunli Wang, Yu Wu, Lili Mou, Zhoujun Li, WenHan Chao

Formality text style transfer plays an important role in various NLP applications, such as non-native speaker assistants and child education.

Formality Style Transfer Style Transfer

An Imitation Learning Approach to Unsupervised Parsing

1 code implementation ACL 2019 Bowen Li, Lili Mou, Frank Keller

In our work, we propose an imitation learning approach to unsupervised parsing, where we transfer the syntactic knowledge induced by the PRPN to a Tree-LSTM model with discrete parsing actions.

Imitation Learning Language Modelling +1

A Grammar-Based Structural CNN Decoder for Code Generation

1 code implementation14 Nov 2018 Zeyu Sun, Qihao Zhu, Lili Mou, Yingfei Xiong, Ge Li, Lu Zhang

In this paper, we propose a grammar-based structural convolutional neural network (CNN) for code generation.

Code Generation Semantic Parsing

CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling

1 code implementation14 Nov 2018 Ning Miao, Hao Zhou, Lili Mou, Rui Yan, Lei LI

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements.

Text Generation

Progressive Memory Banks for Incremental Domain Adaptation

1 code implementation ICLR 2020 Nabiha Asghar, Lili Mou, Kira A. Selby, Kevin D. Pantasdo, Pascal Poupart, Xin Jiang

The memory bank provides a natural way of IDA: when adapting our model to a new domain, we progressively add new slots to the memory bank, which increases the number of parameters, and thus the model capacity.

Domain Adaptation

JUMPER: Learning When to Make Classification Decisions in Reading

no code implementations6 Jul 2018 Xianggen Liu, Lili Mou, Haotian Cui, Zhengdong Lu, Sen Song

Both the classification result and when to make the classification are part of the decision process, which is controlled by a policy network and trained with reinforcement learning.

General Classification text-classification +1

Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation

1 code implementation NAACL 2019 Hareesh Bahuleyan, Lili Mou, Hao Zhou, Olga Vechtomova

The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the posterior and prior.

Text Generation

Variational Attention for Sequence-to-Sequence Models

2 code implementations COLING 2018 Hareesh Bahuleyan, Lili Mou, Olga Vechtomova, Pascal Poupart

The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural network.

Modeling Past and Future for Neural Machine Translation

1 code implementation TACL 2018 Zaixiang Zheng, Hao Zhou, Shu-Jian Huang, Lili Mou, Xin-yu Dai, Jia-Jun Chen, Zhaopeng Tu

The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents.

Machine Translation NMT +1

Affective Neural Response Generation

no code implementations12 Sep 2017 Nabiha Asghar, Pascal Poupart, Jesse Hoey, Xin Jiang, Lili Mou

Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content.

Response Generation Word Embeddings

Order-Planning Neural Text Generation From Structured Data

1 code implementation1 Sep 2017 Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui

Generating texts from structured data (e. g., a table) is important for various natural language processing tasks such as question answering and dialog systems.

Question Answering Table-to-Text Generation

RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems

1 code implementation11 Jan 2017 Chongyang Tao, Lili Mou, Dongyan Zhao, Rui Yan

Open-domain human-computer conversation has been attracting increasing attention over the past few years.

Dialogue Evaluation Retrieval

Coupling Distributed and Symbolic Execution for Natural Language Queries

no code implementations ICML 2017 Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin

Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning.

Natural Language Queries

Dialogue Session Segmentation by Embedding-Enhanced TextTiling

no code implementations13 Oct 2016 Yiping Song, Lili Mou, Rui Yan, Li Yi, Zinan Zhu, Xiaohua Hu, Ming Zhang

In human-computer conversation systems, the context of a user-issued utterance is particularly important because it provides useful background information of the conversation.

Word Embeddings

Compressing Neural Language Models by Sparse Word Representations

1 code implementation ACL 2016 Yunchuan Chen, Lili Mou, Yan Xu, Ge Li, Zhi Jin

Such approaches are time- and memory-intensive because of the large numbers of parameters for word embeddings and the output layer.

Language Modelling Word Embeddings

StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation

no code implementations15 Apr 2016 Xiang Li, Lili Mou, Rui Yan, Ming Zhang

In this paper, we propose StalemateBreaker, a conversation system that can proactively introduce new content when appropriate.

How Transferable are Neural Networks in NLP Applications?

no code implementations EMNLP 2016 Lili Mou, Zhao Meng, Rui Yan, Ge Li, Yan Xu, Lu Zhang, Zhi Jin

Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain.

Transfer Learning

Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation

no code implementations COLING 2016 Yan Xu, Ran Jia, Lili Mou, Ge Li, Yunchuan Chen, Yangyang Lu, Zhi Jin

However, existing neural networks for relation classification are usually of shallow architectures (e. g., one-layer convolutional neural networks or recurrent networks).

Classification Data Augmentation +2

Backward and Forward Language Modeling for Constrained Sentence Generation

no code implementations21 Dec 2015 Lili Mou, Rui Yan, Ge Li, Lu Zhang, Zhi Jin

Provided a specific word, we use RNNs to generate previous words and future words, either simultaneously or asynchronously, resulting in two model variants.

Language Modelling Machine Translation +3

On End-to-End Program Generation from User Intention by Deep Neural Networks

no code implementations25 Oct 2015 Lili Mou, Rui Men, Ge Li, Lu Zhang, Zhi Jin

This paper envisions an end-to-end program generation scenario using recurrent neural networks (RNNs): Users can express their intention in natural language; an RNN then automatically generates corresponding code in a characterby-by-character fashion.

A Comparative Study on Regularization Strategies for Embedding-based Neural Networks

no code implementations EMNLP 2015 Hao Peng, Lili Mou, Ge Li, Yunchuan Chen, Yangyang Lu, Zhi Jin

This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP.

Distilling Word Embeddings: An Encoding Approach

no code implementations15 Jun 2015 Lili Mou, Ran Jia, Yan Xu, Ge Li, Lu Zhang, Zhi Jin

Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems.

Word Embeddings

Convolutional Neural Networks over Tree Structures for Programming Language Processing

8 code implementations18 Sep 2014 Lili Mou, Ge Li, Lu Zhang, Tao Wang, Zhi Jin

Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community.

Building Program Vector Representations for Deep Learning

1 code implementation11 Sep 2014 Lili Mou, Ge Li, Yuxuan Liu, Hao Peng, Zhi Jin, Yan Xu, Lu Zhang

In this pioneering paper, we propose the "coding criterion" to build program vector representations, which are the premise of deep learning for program analysis.

Representation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.