Search Results for author: Yanyan Lan

Found 58 papers, 22 papers with code

Adaptive Bridge between Training and Inference for Dialogue Generation

no code implementations EMNLP 2021 Haoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan

Although exposure bias has been widely studied in some NLP tasks, it faces its unique challenges in dialogue response generation, the representative one-to-various generation scenario. In real human dialogue, there are many appropriate responses for the same context, not only with different expressions, but also with different topics.

Dialogue Generation Response Generation

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

1 code implementation25 Apr 2022 Yunchang Zhu, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng

Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be.

Uncertainty Calibration for Ensemble-Based Debiasing Methods

no code implementations NeurIPS 2021 Ruibin Xiong, Yimeng Chen, Liang Pang, Xueqi Chen, Yanyan Lan

Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target.

Fact Verification

Adaptive Bridge between Training and Inference for Dialogue

no code implementations22 Oct 2021 Haoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan

Although exposure bias has been widely studied in some NLP tasks, it faces its unique challenges in dialogue response generation, the representative one-to-various generation scenario.

Dialogue Generation Response Generation

Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types

no code implementations11 Oct 2021 Shentong Mo, Xi Fu, Chenyang Hong, Yizhen Chen, Yuxuan Zheng, Xiangru Tang, Zhiqiang Shen, Eric P Xing, Yanyan Lan

The core problem is to model how regulatory elements interact with each other and its variability across different cell types.

Multi-modal Self-supervised Pre-training for Large-scale Genome Data

no code implementations NeurIPS Workshop AI4Scien 2021 Shentong Mo, Xi Fu, Chenyang Hong, Yizhen Chen, Yuxuan Zheng, Xiangru Tang, Yanyan Lan, Zhiqiang Shen, Eric Xing

In this work, we propose a simple yet effective approach for pre-training genome data in a multi-modal and self-supervised manner, which we call GeneBERT.

FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning

no code implementations Findings (EMNLP) 2021 Xu Wang, Hainan Zhang, Shuai Zhao, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Bo Cheng, Yanyan Lan

Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model to prefer a candidate that is logically consistent with the speaker's history logic.

Reading Comprehension

Transductive Learning for Unsupervised Text Style Transfer

1 code implementation EMNLP 2021 Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang, HuaWei Shen, Xueqi Cheng

The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.

Style Transfer Text Style Transfer +1

Adaptive Information Seeking for Open-Domain Question Answering

1 code implementation EMNLP 2021 Yunchang Zhu, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng

Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus.

Open-Domain Question Answering

Toward the Understanding of Deep Text Matching Models for Information Retrieval

no code implementations16 Aug 2021 Lijuan Chen, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models.

Information Retrieval Semantic Text Matching +1

A Discriminative Semantic Ranker for Question Retrieval

no code implementations18 Jul 2021 Yinqiong Cai, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Yanyan Lan, Xueqi Cheng

However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance.

Question Answering Re-Ranking

Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition

no code implementations NAACL 2021 Haolan Zhan, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Yongjun Bao, Yanyan Lan

In particular, a sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data.

Response Generation

Sketch and Customize: A Counterfactual Story Generator

1 code implementation2 Apr 2021 Changying Hao, Liang Pang, Yanyan Lan, Yan Wang, Jiafeng Guo, Xueqi Cheng

In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending.

Text Generation

Probing Product Description Generation via Posterior Distillation

no code implementations2 Mar 2021 Haolan Zhan, Hainan Zhang, Hongshen Chen, Lei Shen, Zhuoye Ding, Yongjun Bao, Weipeng Yan, Yanyan Lan

To tackle this problem, we propose an adaptive posterior network based on Transformer architecture that can utilize user-cared information from customer reviews.

A Linguistic Study on Relevance Modeling in Information Retrieval

no code implementations1 Mar 2021 Yixing Fan, Jiafeng Guo, Xinyu Ma, Ruqing Zhang, Yanyan Lan, Xueqi Cheng

We employ 16 linguistic tasks to probe a unified retrieval model over these three retrieval tasks to answer this question.

Information Retrieval Natural Language Understanding +1

Learning to Truncate Ranked Lists for Information Retrieval

no code implementations25 Feb 2021 Chen Wu, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xueqi Cheng

One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search.

Information Retrieval

User-Inspired Posterior Network for Recommendation Reason Generation

no code implementations16 Feb 2021 Haolan Zhan, Hainan Zhang, Hongshen Chen, Lei Shen, Yanyan Lan, Zhuoye Ding, Dawei Yin

A simple and effective way is to extract keywords directly from the knowledge-base of products, i. e., attributes or title, as the recommendation reason.

Question Answering

Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching

1 code implementation16 Jan 2021 Liang Pang, Yanyan Lan, Xueqi Cheng

However, these models designed for short texts cannot well address the long-form text matching problem, because there are many contexts in long-form texts can not be directly aligned with each other, and it is difficult for existing models to capture the key matching signals from such noisy data.

Community Question Answering Information Retrieval +3

Dynamic-K Recommendation with Personalized Decision Boundary

no code implementations25 Dec 2020 Yan Gao, Jiafeng Guo, Yanyan Lan, Huaming Liao

The ranking objective is the same as existing methods, i. e., to create a ranking list of items according to users' interests.

Transformation Driven Visual Reasoning

1 code implementation CVPR 2021 Xin Hong, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i. e.~Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views).

Visual Question Answering Visual Reasoning +1

Beyond Language: Learning Commonsense from Images for Reasoning

1 code implementation Findings of the Association for Computational Linguistics 2020 Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP.

Language Modelling Question Answering

Modeling Topical Relevance for Multi-Turn Dialogue Generation

no code implementations27 Sep 2020 Hainan Zhang, Yanyan Lan, Liang Pang, Hongshen Chen, Zhuoye Ding, Dawei Yin

Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly.

Dialogue Generation

Query Understanding via Intent Description Generation

1 code implementation25 Aug 2020 Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xue-Qi Cheng

To address this new task, we propose a novel Contrastive Generation model, namely CtrsGen for short, to generate the intent description by contrasting the relevant documents with the irrelevant documents given a query.

Information Retrieval

Continual Domain Adaptation for Machine Reading Comprehension

no code implementations25 Aug 2020 Lixin Su, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Yanyan Lan, Xue-Qi Cheng

To tackle such a challenge, in this work, we introduce the \textit{Continual Domain Adaptation} (CDA) task for MRC.

Continual Learning Domain Adaptation +2

Ranking Enhanced Dialogue Generation

no code implementations13 Aug 2020 Changying Hao, Liang Pang, Yanyan Lan, Fei Sun, Jiafeng Guo, Xue-Qi Cheng

To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.

Dialogue Generation Response Generation

On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation

no code implementations ICML 2020 Jianing Li, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng

We prove that under certain conditions, a linear combination of quality and diversity constitutes a divergence metric between the generated distribution and the real distribution.

Text Generation

Match$^2$: A Matching over Matching Model for Similar Question Identification

no code implementations21 Jun 2020 Zizhen Wang, Yixing Fan, Jiafeng Guo, Liu Yang, Ruqing Zhang, Yanyan Lan, Xue-Qi Cheng, Hui Jiang, Xiaozhao Wang

However, it has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i. e., there could be different ways to ask a same question or different questions sharing similar expressions.

Community Question Answering

Robust Reinforcement Learning with Wasserstein Constraint

no code implementations1 Jun 2020 Linfang Hou, Liang Pang, Xin Hong, Yanyan Lan, Zhi-Ming Ma, Dawei Yin

Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics.

reinforcement-learning

L2R2: Leveraging Ranking for Abductive Reasoning

1 code implementation22 May 2020 Yunchang Zhu, Liang Pang, Yanyan Lan, Xue-Qi Cheng

To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities.

Language Modelling Learning-To-Rank +1

SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval

2 code implementations12 Dec 2019 Liang Pang, Jun Xu, Qingyao Ai, Yanyan Lan, Xue-Qi Cheng, Ji-Rong Wen

In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents.

Information Retrieval Learning-To-Rank

Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile

no code implementations9 Jul 2019 Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng

Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications.

Language Modelling

Controlling Risk of Web Question Answering

no code implementations24 May 2019 Lixin Su, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xue-Qi Cheng

Web question answering (QA) has become an indispensable component in modern search systems, which can significantly improve users' search experience by providing a direct answer to users' information need.

Machine Reading Comprehension Question Answering

Outline Generation: Understanding the Inherent Content Structure of Documents

no code implementations24 May 2019 Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xue-Qi Cheng

To generate a sound outline, an ideal OG model should be able to capture three levels of coherence, namely the coherence between context paragraphs, that between a section and its heading, and that between context headings.

Structured Prediction

Tailored Sequence to Sequence Models to Different Conversation Scenarios

no code implementations ACL 2018 Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng

In this paper, we propose two tailored optimization criteria for Seq2Seq to different conversation scenarios, i. e., the maximum generated likelihood for specific-requirement scenario, and the conditional value-at-risk for diverse-requirement scenario.

Dialogue Generation Response Generation

Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

2 code implementations SIGIR '18 2018 Yixing Fan, Jiafeng Guo, Yanyan Lan, Jun Xu, ChengXiang Zhai, Xue-Qi Cheng

The local matching layer focuses on producing a set of local relevance signals by modeling the semantic matching between a query and each passage of a document.

A Tree Search Algorithm for Sequence Labeling

1 code implementation29 Apr 2018 Yadi Lao, Jun Xu, Yanyan Lan, Jiafeng Guo, Sheng Gao, Xue-Qi Cheng

Inspired by the success and methodology of the AlphaGo Zero, MM-Tag formalizes the problem of sequence tagging with a Monte Carlo tree search (MCTS) enhanced Markov decision process (MDP) model, in which the time steps correspond to the positions of words in a sentence from left to right, and each action corresponds to assign a tag to a word.

Chunking Decision Making +2

MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server

no code implementations22 Apr 2018 Guoxin Cui, Jun Xu, Wei Zeng, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations.

Quantization reinforcement-learning

Locally Smoothed Neural Networks

1 code implementation22 Nov 2017 Liang Pang, Yanyan Lan, Jun Xu, Jiafeng Guo, Xue-Qi Cheng

The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields.

Face Verification Question Answering +1

A Deep Investigation of Deep IR Models

no code implementations24 Jul 2017 Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng

Therefore, it is necessary to identify the difference between automatically learned features by deep IR models and hand-crafted features used in traditional learning to rank approaches.

Information Retrieval Learning-To-Rank

MatchZoo: A Toolkit for Deep Text Matching

1 code implementation23 Jul 2017 Yixing Fan, Liang Pang, Jianpeng Hou, Jiafeng Guo, Yanyan Lan, Xue-Qi Cheng

In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared with previous methods.

Ad-Hoc Information Retrieval Information Retrieval +2

Spherical Paragraph Model

no code implementations18 Jul 2017 Ruqing Zhang, Jiafeng Guo, Yanyan Lan, Jun Xu, Xue-Qi Cheng

Representing texts as fixed-length vectors is central to many language processing tasks.

Representation Learning Sentiment Analysis

Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising

no code implementations23 Nov 2016 Jia Zhang, Zheng Wang, Qian Li, Jialin Zhang, Yanyan Lan, Qiang Li, Xiaoming Sun

In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers.

A Study of MatchPyramid Models on Ad-hoc Retrieval

1 code implementation15 Jun 2016 Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng

Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it.

Machine Translation Paraphrase Identification +3

Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

1 code implementation15 Apr 2016 Shengxian Wan, Yanyan Lan, Jun Xu, Jiafeng Guo, Liang Pang, Xue-Qi Cheng

In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i. e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position.

Semantic Regularities in Document Representations

no code implementations24 Mar 2016 Fei Sun, Jiafeng Guo, Yanyan Lan, Jun Xu, Xue-Qi Cheng

Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language.

Text Matching as Image Recognition

7 code implementations20 Feb 2016 Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, Xue-Qi Cheng

An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score.

Ad-Hoc Information Retrieval Text Matching

A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

1 code implementation26 Nov 2015 Shengxian Wan, Yanyan Lan, Jiafeng Guo, Jun Xu, Liang Pang, Xue-Qi Cheng

Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.

Information Retrieval Question Answering +1

Stochastic Rank Aggregation

no code implementations26 Sep 2013 Shuzi Niu, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng

Traditional rank aggregation methods are deterministic, and can be categorized into explicit and implicit methods depending on whether rank information is explicitly or implicitly utilized.

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