Search Results for author:
Found 70 papers, 42 papers with code
Text Matching as Image Recognition
An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score.
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.
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.
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
We evaluate the multilingual knowledge editing generalization capabilities of existing methods on MLaKE.
GraphEdit: Large Language Models for Graph Structure Learning
Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data by generating novel graph structures.
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.
LLMDet: A Third Party Large Language Models Generated Text Detection Tool
By jointly analyzing the proxy perplexities of LLMs, we can determine the source of the generated text.
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
Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks
This paper proposes a novel framework named \textbf{Search-in-the-Chain} (SearChain) for the interaction between LLM and IR to solve the challenges.
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).
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).
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.
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks.
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.
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.
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.
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.
Unifying Bias and Unfairness in Information Retrieval: A Survey of Challenges and Opportunities with Large Language Models
With the rapid advancement of large language models (LLMs), information retrieval (IR) systems, such as search engines and recommender systems, have undergone a significant paradigm shift.
Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains
Four popular text matching methods have been exploited in the paper.
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching
Enjoying the partial transport properties of OPT, the selected key sentences can not only effectively enhance the matching accuracy, but also be explained as the rationales for the matching results.
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling
It encodes the text corpus into a latent space, capturing current and future information from both source and target text.
LLMs may Dominate Information Access: Neural Retrievers are Biased Towards LLM-Generated Texts
We refer to this category of biases in neural retrieval models towards the LLM-generated text as the \textbf{source bias}.
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval.
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.
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space
Multi-aspect controllable text generation aims to generate fluent sentences that possess multiple desired attributes simultaneously.
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.
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.
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.
Beyond Memorization: The Challenge of Random Memory Access in Language Models
Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question answering, we reveal that LMs manage to sequentially access their memory while encountering challenges in randomly accessing memorized content.
Qsnail: A Questionnaire Dataset for Sequential Question Generation
Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure.
SCTc-TE: A Comprehensive Formulation and Benchmark for Temporal Event Forecasting
Temporal complex event forecasting aims to predict the future events given the observed events from history.
Stable Knowledge Editing in Large Language Models
The premise of localization results in an incomplete knowledge editing, whereas an isolated assumption may impair both other knowledge and general abilities.
Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
In generalization stage, matching model explores the essential matching signals by being trained on diverse matching tasks.
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.
Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
The emergence of large language models (LLMs) further improves the capabilities of open-domain dialogue systems and can generate fluent, coherent, and diverse responses.
List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
First, it is hard to share the contextual information of the ranking list between the two tasks.
Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action.
PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation
However, generating personalized responses is still a challenging task since the leverage of predefined persona information is often insufficient.
SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation
Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue.
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.
Large Scale Purchase Prediction with Historical User Actions on B2C Online Retail Platform
This paper describes the solution of Bazinga Team for Tmall Recommendation Prize 2014.
Combination of Diverse Ranking Models for Personalized Expedia Hotel Searches
The ICDM Challenge 2013 is to apply machine learning to the problem of hotel ranking, aiming to maximize purchases according to given hotel characteristics, location attractiveness of hotels, user's aggregated purchase history and competitive online travel agency information for each potential hotel choice.
Continual Match Based Training in Pommerman: Technical Report
We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.
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.
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.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
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.
Robust Reinforcement Learning with Wasserstein Constraint
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics.
Ranking Enhanced Dialogue Generation
To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.
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.
Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm
Experimental results base on three publicly available benchmarks showed that in both of the implementations, Pre-Rank can respectively outperform the underlying ranking models and achieved state-of-the-art performances.
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.
METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each specific aspect in a given sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
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.
NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework
Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts.
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.
Visual Transformation Telling
In this paper, we propose a new visual reasoning task, called Visual Transformation Telling (VTT).
BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval
Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context.
Plot Retrieval as an Assessment of Abstract Semantic Association
Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots.
Do LLMs Implicitly Exhibit User Discrimination in Recommendation? An Empirical Study
Recently, Large Language Models (LLMs) have enhanced user interaction, enabling seamless information retrieval and recommendations.
De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks.
AI-Generated Images Introduce Invisible Relevance Bias to Text-Image Retrieval
Furthermore, our subsequent exploration reveals that the inclusion of AI-generated images in the training data of the retrieval models exacerbates the invisible relevance bias.
Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models
A careful and balanced integration of the parametric knowledge within LLMs with external information is crucial to alleviate hallucinations.
Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
The relevance between the video and query is partial, mainly evident in two aspects: (1) Scope: The untrimmed video contains information-rich frames, and not all are relevant to the query.
Event-aware Video Corpus Moment Retrieval
Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos using the natural language query.
Can Small Language Models be Good Reasoners for Sequential Recommendation?
We encode the generated rationales from the student model into a dense vector, which empowers recommendation in both ID-based and ID-agnostic scenarios.
Thermal-NeRF: Neural Radiance Fields from an Infrared Camera
In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit representation for 3D scene reconstruction.
Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation
In the first case, the agent is required to give the type and parameters of the probability distribution through the problem description, and then give the sampling sequence.
Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
Their ability to execute intricate compositional reasoning tasks is also constrained, culminating in a stagnation of learning progression for these models.
