Search Results for author:
Found 78 papers, 56 papers with code
KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
To address these problems, we propose a knowledge-aware fine-tuning (KnowTuning) method to improve fine-grained and coarse-grained knowledge awareness of LLMs.
A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts
We propose a neural Modular Task-oriented Dialogue System(MTDS) framework, in which a few expert bots are combined to generate the response for a given dialogue context.
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions.
Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
In this paper, we first investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR.
Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers
Furthermore, our approach surpasses the performance of existing supervised methods like monoT5 and is on par with the state-of-the-art zero-shot methods.
Neural Attentive Session-based Recommendation
Specifically, we explore a hybrid encoder with an attention mechanism to model the user's sequential behavior and capture the user's main purpose in the current session, which are combined as a unified session representation later.
Ranked #10 on
Session-Based Recommendations
on yoochoose1/64
Neural Att entive Session-based Recommendation
Specifically, we explore a hybrid encoder with an attention mechanism to model the user’s sequential behavior and capture the user’s main purpose in the current session, which are combined as a unified session representation later.
RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation
RepeatNet integrates a regular neural recommendation approach in the decoder with a new repeat recommendation mechanism that can choose items from a user's history and recommends them at the right time.
Knowledge Bridging for Empathetic Dialogue Generation
Finally, to generate the empathetic response, we propose an emotional cross-attention mechanism to learn the emotional dependencies from the emotional context graph.
EmpDG: Multiresolution Interactive Empathetic Dialogue Generation
In response to this problem, we propose a multi-resolution adversarial model -- EmpDG, to generate more empathetic responses.
EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation
In response to this problem, we propose a multi-resolution adversarial model {--} EmpDG, to generate more empathetic responses.
ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
(1) there is no dataset with large-scale medical dialogues that covers multiple medical services and contains fine-grained medical labels (i. e., intents, actions, slots, values), and (2) there is no set of established benchmarks for MDSs for multi-domain, multi-service medical dialogues.
Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems
The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like.
RefNet: A Reference-aware Network for Background Based Conversation
In this paper, we propose a Reference-aware Network (RefNet) to address the two issues.
Wizard of Search Engine: Access to Information Through Conversations with Search Engines
(2) We release a benchmark dataset, called wizard of search engine (WISE), which allows for comprehensive and in-depth research on all aspects of CIS.
Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss
Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses.
Membership Inference Attacks Against Recommender Systems
In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference.
Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
We propose a variational Bayesian method to approximate posterior distributions over dialogue-specific subgraphs, which not only leverages the dialogue corpus for restructuring missing entity relations but also dynamically selects knowledge based on the dialogue context.
Conversations with Search Engines: SERP-based Conversational Response Generation
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner.
On the User Behavior Leakage from Recommender System Exposure
Given the fact that system exposure data could be widely accessed from a relatively larger scope, we believe that the user past behavior privacy has a high risk of leakage in recommender systems.
Contrastive Learning Reduces Hallucination in Conversations
MixCL effectively reduces the hallucination of LMs in conversations and achieves the highest performance among LM-based dialogue agents in terms of relevancy and factuality.
Semi-Supervised Variational Reasoning for Medical Dialogue Generation
We propose an end-to-end variational reasoning approach to medical dialogue generation.
Answering Ambiguous Questions via Iterative Prompting
To provide feasible answers to an ambiguous question, one approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity.
Query Resolution for Conversational Search with Limited Supervision
Context from the conversational history can be used to arrive at a better expression of the current turn query, defined as the task of query resolution.
Mixed Information Flow for Cross-domain Sequential Recommendations
One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains.
Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation
We conduct extensive experiments to evaluate the performance of representative sequential recommendation models in the setting of lifelong sequences.
Generative Retrieval as Multi-Vector Dense Retrieval
Both methods compute relevance as a sum of products of query and document vectors and an alignment matrix.
Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
Given a conversational context and background knowledge, we first learn a topic transition vector to encode the most likely text fragments to be used in the next response, which is then used to guide the local KS at each decoding timestamp.
Improving Multi-label Malevolence Detection in Dialogues through Multi-faceted Label Correlation Enhancement
The detection of malevolent dialogue responses is attracting growing interest.
Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
Recommender systems that learn from implicit feedback often use large volumes of a single type of implicit user feedback, such as clicks, to enhance the prediction of sparse target behavior such as purchases.
Improving Background Based Conversation with Context-aware Knowledge Pre-selection
The latter generate responses thatare natural but not necessarily effective in leveraging background knowledge.
A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles
We find that CoMemNN is able to enrich user profiles effectively, which results in an improvement of 3. 06% in terms of response selection accuracy compared to state-of-the-art methods.
Learning to Ask Conversational Questions by Optimizing Levenshtein Distance
Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e. g., anaphora and ellipsis.
Towards Explainable Conversational Recommender Systems
To achieve this, we conduct manual and automatic approaches to extend these dialogues and construct a new CRS dataset, namely Explainable Recommendation Dialogues (E-ReDial).
Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
Then, we introduce a penalty to items with high exposure probability to avoid the overestimation of user preference for biased samples.
Attribute-aware Diversification for Sequential Recommendations
Users prefer diverse recommendations over homogeneous ones.
Contrastive State Augmentations for Reinforcement Learning-Based Recommender Systems
For the second issue, we propose introducing contrastive signals between augmented states and the state randomly sampled from other sessions to improve the state representation learning further.
A Self-Correcting Sequential Recommender
STEAM first corrects an input item sequence by adjusting the misclicked and/or missed items.
Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
Instead of generating a response from scratch, P2-Net generates system responses by paraphrasing template-based responses.
A Human-machine Collaborative Framework for Evaluating Malevolence in Dialogues
HMCEval casts dialogue evaluation as a sample assignment problem, where we need to decide to assign a sample to a human or a machine for evaluation.
Generative Knowledge Selection for Knowledge-Grounded Dialogues
However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets.
Few-Shot Electronic Health Record Coding through Graph Contrastive Learning
We seek to improve the performance for both frequent and rare ICD codes by using a contrastive graph-based EHR coding framework, CoGraph, which re-casts EHR coding as a few-shot learning task.
Debiasing Learning for Membership Inference Attacks Against Recommender Systems
To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (1) a difference vector generator, (2) a disentangled encoder, (3) a weight estimator, and (4) an attack model.
UMSE: Unified Multi-scenario Summarization Evaluation
Experimental results across three typical scenarios on the benchmark dataset SummEval indicate that our UMSE can achieve comparable performance with several existing strong methods which are specifically designed for each scenario.
Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs.
Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems
Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities.
Iteratively Learning Representations for Unseen Entities with Inter-Rule Correlations
Recent work on knowledge graph completion (KGC) focused on learning embeddings of entities and relations in knowledge graphs.
Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning
Multiple defendants in a criminal fact description generally exhibit complex interactions, and cannot be well handled by existing Legal Judgment Prediction (LJP) methods which focus on predicting judgment results (e. g., law articles, charges, and terms of penalty) for single-defendant cases.
A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
To address this, we propose a neural topical expansion framework, namely Persona Exploration and Exploitation (PEE), which is able to extend the predefined user persona description with semantically correlated content before utilizing them to generate dialogue responses.
Feature-Level Debiased Natural Language Understanding
We also propose a dynamic negative sampling strategy to capture the dynamic influence of biases by employing a bias-only model to dynamically select the most similar biased negative samples.
On the Effectiveness of Unlearning in Session-Based Recommendation
On the one hand, these approaches cannot achieve satisfying unlearning effects due to the collaborative correlations and sequential connections between the unlearning item and the remaining items in the session.
Generative News Recommendation
In this paper, we propose a novel generative news recommendation paradigm that includes two steps: (1) Leveraging the internal knowledge and reasoning capabilities of the Large Language Model (LLM) to perform high-level matching between candidate news and user representation; (2) Generating a coherent and logically structured narrative based on the associations between related news and user interests, thus engaging users in further reading of the news.
Modeling Sequential Recommendation as Missing Information Imputation
To address the limitation of sequential recommenders with side information, we define a way to fuse side information and alleviate the problem of missing side information by proposing a unified task, namely the missing information imputation (MII), which randomly masks some feature fields in a given sequence of items, including item IDs, and then forces a predictive model to recover them.
Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related Features
To address this limitation, recent studies enable generalization to an unseen target domain with only a few labeled examples using data augmentation techniques.
Learning Robust Sequential Recommenders through Confident Soft Labels
CSRec contains a teacher module that generates high-quality and confident soft labels and a student module that acts as the target recommender and is trained on the combination of dense, soft labels and sparse, one-hot labels.
Entity Linking for Queries by Searching Wikipedia Sentences
The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the similar sentences as candidate entities for the query.
A Redundancy-Aware Sentence Regression Framework for Extractive Summarization
Existing sentence regression methods for extractive summarization usually model sentence importance and redundancy in two separate processes.
Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation
The generated comments can be regarded as explanations for the recommendation results.
Improving End-to-End Sequential Recommendations with Intent-aware Diversification
Then, we design an Intent-aware Diversity Promoting (IDP) loss to supervise the learning of the IIM module and force the model to take recommendation diversity into consideration during training.
Improving Outfit Recommendation with Co-supervision of Fashion Generation
FARM improves visual understanding by incorporating the supervision of generation loss, which we hypothesize to be able to better encode aesthetic information.
Parallel Split-Join Networks for Shared-account Cross-domain Sequential Recommendations
We study sequential recommendation in a particularly challenging context, in which multiple individual users share asingle account (i. e., they have a shared account) and in which user behavior is available in multiple domains (i. e., recommendations are cross-domain).
Meta Matrix Factorization for Federated Rating Predictions
Given a user, we first obtain a collaborative vector by collecting useful information with a collaborative memory module.
Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology
In this paper, we define the task of Malevolent Dialogue Response Detection and Classification (MDRDC).
Cross-Domain Contract Element Extraction with a Bi-directional Feedback Clause-Element Relation Network
First, contract elements are far more fine-grained than named entities, which hinders the transfer of extractors.
Cross-Domain Named Entity Recognition
named-entity-recognition
+4
Improving Transformer-based Sequential Recommenders through Preference Editing
By doing so, the SR model is able to learn how to identify common and unique user preferences, and thereby do better user preference extraction and representation.
Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding
In this work, we propose a simple yet effective attention guiding mechanism to improve the performance of PLM by encouraging attention towards the established goals.
Rethinking Reinforcement Learning for Recommendation: A Prompt Perspective
As reinforcement learning (RL) naturally fits this objective -- maximizing an user's reward per session -- it has become an emerging topic in recommender systems.
Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues
Specifically, it improves 2. 06% and 1. 00% of F1 score on the two datasets, compared with the strongest baseline with only 5% labeled data.
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.
RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem.
Zero-Shot Position Debiasing for Large Language Models
Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality.
Privacy-Preserving Sequential Recommendation with Collaborative Confusion
Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence.
A Multi-Agent Conversational Recommender System
First, we design a multi-agent act planning framework, which can control the dialogue flow based on four LLM-based agents.
Knowledge Graph Enhanced Large Language Model Editing
Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge.
Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models' scale and the diversity of tasks increase.
Learning to Use Tools via Cooperative and Interactive Agents
Tool learning empowers large language models (LLMs) as agents to use external tools to extend their capability.
Enhanced Generative Recommendation via Content and Collaboration Integration
However, existing generative recommendation approaches still encounter challenges in (i) effectively integrating user-item collaborative signals and item content information within a unified generative framework, and (ii) executing an efficient alignment between content information and collaborative signals.
Offline Trajectory Generalization for Offline Reinforcement Learning
Then we propose four strategies to use World Transformers to generate high-rewarded trajectory simulation by perturbing the offline data.
