Search Results for author:
Found 120 papers, 56 papers with code
MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification
For the meta learner, it requires a good generalization ability so as to quickly adapt to new tasks.
Selective Temporal Knowledge Graph Reasoning
Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently.
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
However, limiting perturbations to a single level of granularity may reduce the flexibility of adversarial examples, thereby diminishing the potential threat of the attack.
Class-Incremental Few-Shot Event Detection
Therefore, this paper proposes a new task, called class-incremental few-shot event detection.
Are Large Language Models Good at Utility Judgments?
Retrieval-augmented generation (RAG) is considered to be a promising approach to alleviate the hallucination issue of large language models (LLMs), and it has received widespread attention from researchers recently.
Listwise Generative Retrieval Models via a Sequential Learning Process
Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the $i$-th docid given the (preceding) top $i-1$ docids.
KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction
After instruction tuning, KnowCoder further exhibits strong generalization ability on unseen schemas and achieves up to $\textbf{12. 5%}$ and $\textbf{21. 9%}$, compared to sota baselines, under the zero-shot setting and the low resource setting, respectively.
CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance.
MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning
Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge.
When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
This motivates us to enhance the LLMs' ability to perceive their knowledge boundaries to help RA.
A Unified Causal View of Instruction Tuning
The key idea is to learn task-required causal factors and only use those to make predictions for a given task.
Reproducibility Analysis and Enhancements for Multi-Aspect Dense Retriever with Aspect Learning
MADRAL was evaluated on proprietary data and its code was not released, making it challenging to validate its effectiveness on other datasets.
RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication.
Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off
We decompose the robust ranking error into two components, i. e., a natural ranking error for effectiveness evaluation and a boundary ranking error for assessing adversarial robustness.
A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval
Dense retrieval methods have been mostly focused on unstructured text and less attention has been drawn to structured data with various aspects, e. g., products with aspects such as category and brand.
CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval
The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently.
Retrieval-Augmented Code Generation for Universal Information Extraction
Therefore, in this paper, we propose a universal retrieval-augmented code generation framework based on LLMs, called Code4UIE, for IE tasks.
An In-Context Schema Understanding Method for Knowledge Base Question Answering
The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base.
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification
We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.
CIR at the NTCIR-17 ULTRE-2 Task
The Chinese academy of sciences Information Retrieval team (CIR) has participated in the NTCIR-17 ULTRE-2 task.
A Comparative Study of Training Objectives for Clarification Facet Generation
In this paper, we aim to conduct a systematic comparative study of various types of training objectives, with different properties of not only whether it is permutation-invariant but also whether it conducts sequential prediction and whether it can control the count of output facets.
ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction
To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations.
Nested Event Extraction upon Pivot Element Recogniton
Since existing NEE datasets (e. g., Genia11) are limited to specific domains and contain a narrow range of event types with nested structures, we systematically categorize nested events in the generic domain and construct a new NEE dataset, called ACE2005-Nest.
Continual Learning for Generative Retrieval over Dynamic Corpora
We put forward a novel Continual-LEarner for generatiVE Retrieval (CLEVER) model and make two major contributions to continual learning for GR: (i) To encode new documents into docids with low computational cost, we present Incremental Product Quantization, which updates a partial quantization codebook according to two adaptive thresholds; and (ii) To memorize new documents for querying without forgetting previous knowledge, we propose a memory-augmented learning mechanism, to form meaningful connections between old and new documents.
Inducing Causal Structure for Abstractive Text Summarization
The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.
Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval
Extensive experiments on two real-world datasets (product and mini-program search) show that our approach can outperform competitive baselines both treating aspect values as classes and conducting the same MLM for aspect and content strings.
L^2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations
First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection.
Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method
The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query.
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.
On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective
Recently, we have witnessed generative retrieval increasingly gaining attention in the information retrieval (IR) field, which retrieves documents by directly generating their identifiers.
Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies
Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI; and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning.
Semantic Structure Enhanced Event Causality Identification
This is a very challenging task, because causal relations are usually expressed by implicit associations between events.
Few-shot Link Prediction on N-ary Facts
Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs).
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.
Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models
In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic.
A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning
Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity, such as a document retriever, passage retriever, sentence retriever, and entity retriever, may help to achieve better performance on the end-to-end task.
Ensemble Ranking Model with Multiple Pretraining Strategies for Web Search
Then we fine-tune several pre-trained models and train an ensemble model to aggregate all the predictions from various pre-trained models with human-annotation data in the fine-tuning stage.
Feature-Enhanced Network with Hybrid Debiasing Strategies for Unbiased Learning to Rank
Unbiased learning to rank (ULTR) aims to mitigate various biases existing in user clicks, such as position bias, trust bias, presentation bias, and learn an effective ranker.
Rich Event Modeling for Script Event Prediction
Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants.
Visual Named Entity Linking: A New Dataset and A Baseline
Since each entity often contains rich visual and textual information in KBs, we thus propose three different sub-tasks, i. e., visual to visual entity linking (V2VEL), visual to textual entity linking (V2TEL), and visual to visual-textual entity linking (V2VTEL).
LegoNet: A Fast and Exact Unlearning Architecture
However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance.
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning
This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps.
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction
CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures.
Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models
When sampling top-ranked results (excluding the labeled positives) as negatives from a stronger retriever, the performance of the learned NRM becomes even worse.
Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval
Unlike the promising results in NLP, we find that these methods cannot achieve comparable performance to full fine-tuning at both stages when updating less than 1\% of the original model parameters.
A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval
Empirical results show that our method can significantly outperform the state-of-the-art autoencoder-based language models and other pre-trained models for dense retrieval.
CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
We show that a strong generative retrieval model can be learned with a set of adequately designed pre-training tasks, and be adopted to improve a variety of downstream KILT tasks with further fine-tuning.
Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation.
Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction
% Therefore, in this work, we propose to drop out the decoder and introduce a novel contrastive span prediction task to pre-train the encoder alone.
GERE: Generative Evidence Retrieval for Fact Verification
This classical approach has clear drawbacks as follows: i) a large document index as well as a complicated search process is required, leading to considerable memory and computational overhead; ii) independent scoring paradigms fail to capture the interactions among documents and sentences in ranking; iii) a fixed number of sentences are selected to form the final evidence set.
PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models
We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list.
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.
A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty
By reducing the weights of the majority classes, such instances would become more difficult to learn and hurt the overall performance consequently.
What is Event Knowledge Graph: A Survey
Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG).
Pre-training Methods in Information Retrieval
The core of information retrieval (IR) is to identify relevant information from large-scale resources and return it as a ranked list to respond to the user's information need.
Interpreting Dense Retrieval as Mixture of Topics
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success.
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space.
Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning
In self-supervised learning frameworks, deep networks are optimized to align different views of an instance that contains the similar visual semantic information.
Integrating Deep Event-Level and Script-Level Information for Script Event Prediction
In this paper, we propose a Transformer-based model, called MCPredictor, which integrates deep event-level and script-level information for script event prediction.
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict
Based on this dual-channel framework, we design the Dual-Channel Network~(DC-Net) to recognize sentiment conflict.
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.
Are Neural Ranking Models Robust?
So we raise the question in this work: Are neural ranking models robust?
FedMatch: Federated Learning Over Heterogeneous Question Answering Data
A possible solution to this dilemma is a new approach known as federated learning, which is a privacy-preserving machine learning technique over distributed datasets.
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size.
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.
Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts.
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.
Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity).
B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval
The basic idea of PROP is to construct the \textit{representative words prediction} (ROP) task for pre-training inspired by the query likelihood model.
Optimizing Dense Retrieval Model Training with Hard Negatives
ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance.
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.
Semantic Models for the First-stage Retrieval: A Comprehensive Review
We believe it is the right time to survey current status, learn from existing methods, and gain some insights for future development.
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.
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.
Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings
To resolve event coreference, existing methods usually calculate the similarities between event mentions and between specific kinds of event arguments.
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).
PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval
Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR).
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.
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.
NeuInfer: Knowledge Inference on N-ary Facts
It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s).
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.
IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.
Event Detection with Multi-Order Graph Convolution and Aggregated Attention
Syntactic relations are broadly used in many NLP tasks.
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.
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.
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.
MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching
Text matching is the core problem in many natural language processing (NLP) tasks, such as information retrieval, question answering, and conversation.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
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.
Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
Our models and research findings provide new insights on how to utilize external knowledge with deep neural models for response selection and have implications for the design of the next generation of information-seeking conversation systems.
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.
Learning a Deep Listwise Context Model for Ranking Refinement
Specifically, we employ a recurrent neural network to sequentially encode the top results using their feature vectors, learn a local context model and use it to re-rank the top results.
Unbiased Learning to Rank with Unbiased Propensity Estimation
We find that the problem of estimating a propensity model from click data is a dual problem of unbiased learning to rank.
aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model
As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term Memory Models (LSTMs) have recently been proposed for semantic matching of questions and answers.
Ranked #12 on
Question Answering
on TrecQA
A Deep Relevance Matching Model for Ad-hoc Retrieval
Specifically, our model employs a joint deep architecture at the query term level for relevance matching.
Ranked #14 on
Ad-Hoc Information Retrieval
on TREC Robust04
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.
Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
We further evaluate the neural matching models in the next question prediction task in conversations.
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.
