Search Results for author:
Found 79 papers, 29 papers with code
From spoken dialogue to formal summary: An utterance rewriting for dialogue summarization
Firstly, an utterance rewriter is conducted to complete the ellipsis content of dialogue content and then obtain the rewriting utterances.
Adaptive Bridge between Training and Inference for Dialogue Generation
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.
Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion
In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score.
Contextual Molecule Representation Learning from Chemical Reaction Knowledge
REMO offers a novel solution to MRL by exploiting the underlying shared patterns in chemical reactions as \textit{context} for pre-training, which effectively infers meaningful representations of common chemistry knowledge.
Equivariant Flow Matching with Hybrid Probability Transport
The generation of 3D molecules requires simultaneously deciding the categorical features~(atom types) and continuous features~(atom coordinates).
Protein-ligand binding representation learning from fine-grained interactions
The binding between proteins and ligands plays a crucial role in the realm of drug discovery.
Elastic Information Bottleneck
Comparing IB and DIB on these terms, we prove that DIB's SG bound is tighter than IB's while DIB's RD is larger than IB's.
Sliced Denoising: A Physics-Informed Molecular Pre-Training Method
By aligning with physical principles, SliDe shows a 42\% improvement in the accuracy of estimated force fields compared to current state-of-the-art denoising methods, and thus outperforms traditional baselines on various molecular property prediction tasks.
Delta Score: Improving the Binding Assessment of Structure-Based Drug Design Methods
Structure-based drug design (SBDD) stands at the forefront of drug discovery, emphasizing the creation of molecules that target specific binding pockets.
UniMAP: Universal SMILES-Graph Representation Learning
Molecular representation learning is fundamental for many drug related applications.
ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design.
DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
Virtual screening, which identifies potential drugs from vast compound databases to bind with a particular protein pocket, is a critical step in AI-assisted drug discovery.
Fractional Denoising for 3D Molecular Pre-training
Theoretically, the objective is equivalent to learning the force field, which is revealed helpful for downstream tasks.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
Multimodal Molecular Pretraining via Modality Blending
Self-supervised learning has recently gained growing interest in molecular modeling for scientific tasks such as AI-assisted drug discovery.
Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
Generating desirable molecular structures in 3D is a fundamental problem for drug discovery.
Visual Transformation Telling
In this paper, we propose a new visual reasoning task, called Visual Transformation Telling (VTT).
Visual Reasoning: from State to Transformation
Such \textbf{state driven} visual reasoning has limitations in reflecting the ability to infer the dynamics between different states, which has shown to be equally important for human cognition in Piaget's theory.
Multi-video Moment Ranking with Multimodal Clue
In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference.
Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
Comparative loss is essentially a ranking loss on top of the task-specific losses of the full and ablated models, with the expectation that the task-specific loss of the full model is minimal.
PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction
In our implementation, we adopt both the state-of-the-art molecule embedding models under the supervised learning paradigm and the pretraining paradigm as the molecule representation module of PEMP, respectively.
When Does Group Invariant Learning Survive Spurious Correlations?
Motivated by this, we design a new group invariant learning method, which constructs groups with statistical independence tests, and reweights samples by group label proportion to meet the criteria.
LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback
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
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.
Adaptive Bridge between Training and Inference for Dialogue
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.
Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types
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
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
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.
Transductive Learning for Unsupervised Text Style Transfer
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.
Adaptive Information Seeking for Open-Domain Question Answering
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus.
Ranked #3 on
Question Answering
on HotpotQA
Toward the Understanding of Deep Text Matching Models for Information Retrieval
We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models.
A Discriminative Semantic Ranker for Question Retrieval
However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance.
Pre-Trained Models: Past, Present and Future
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI).
Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition
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.
Sketch and Customize: A Counterfactual Story Generator
In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending.
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our BriVL model.
Ranked #1 on
Image Retrieval
on RUC-CAS-WenLan
Probing Product Description Generation via Posterior Distillation
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
We employ 16 linguistic tasks to probe a unified retrieval model over these three retrieval tasks to answer this question.
Learning to Truncate Ranked Lists for Information Retrieval
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.
User-Inspired Posterior Network for Recommendation Reason Generation
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.
Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
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.
Dynamic-K Recommendation with Personalized Decision Boundary
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
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).
Beyond Language: Learning Commonsense from Images for Reasoning
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.
Modeling Topical Relevance for Multi-Turn Dialogue Generation
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.
Continual Domain Adaptation for Machine Reading Comprehension
To tackle such a challenge, in this work, we introduce the \textit{Continual Domain Adaptation} (CDA) task for MRC.
Query Understanding via Intent Description Generation
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.
Ranking Enhanced Dialogue Generation
To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.
On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation
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.
Match$^2$: A Matching over Matching Model for Similar Question Identification
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.
Robust Reinforcement Learning with Wasserstein Constraint
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics.
L2R2: Leveraging Ranking for Abductive Reasoning
To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities.
On Layer Normalization in the Transformer Architecture
This motivates us to remove the warm-up stage for the training of Pre-LN Transformers.
SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
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.
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
Then, the self-attention mechanism is utilized to update both the context and masked response representation.
Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile
Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications.
Controlling Risk of Web Question Answering
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.
Outline Generation: Understanding the Inherent Content Structure of Documents
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.
HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
However, the performances of such models are not so good as that in the RC task.
Learning to Control the Specificity in Neural Response Generation
In conversation, a general response (e. g., {``}I don{'}t know{''}) could correspond to a large variety of input utterances.
Tailored Sequence to Sequence Models to Different Conversation Scenarios
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.
Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
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
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.
MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server
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.
Locally Smoothed Neural Networks
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.
DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR).
A Deep Investigation of Deep IR Models
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.
MatchZoo: A Toolkit for Deep Text Matching
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.
Spherical Paragraph Model
Representing texts as fixed-length vectors is central to many language processing tasks.
Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising
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
Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it.
Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
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
Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language.
Text Matching as Image Recognition
An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score.
A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
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.
Stochastic Rank Aggregation
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.
Statistical Consistency of Ranking Methods in A Rank-Differentiable Probability Space
This paper is concerned with the statistical consistency of ranking methods.
Ranking Measures and Loss Functions in Learning to Rank
We show that these loss functions are upper bounds of the measure-based ranking errors.
