Search Results for author:
Found 24 papers, 4 papers with code
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.
Interactive Latent Knowledge Selection for E-Commerce Product Copywriting Generation
As the multi-modal e-commerce is thriving, high-quality advertising product copywriting has gain more attentions, which plays a crucial role in the e-commerce recommender, advertising and even search platforms. The advertising product copywriting is able to enhance the user experience by highlighting the product’s characteristics with textual descriptions and thus to improve the likelihood of user click and purchase.
Summarizing Dialogues with Negative Cues
In this work, rather than directly forcing a summarization system to merely pay more attention to the salient pieces, we propose to explicitly have the model perceive the redundant parts of an input dialogue history during the training phase.
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.
Automatic Scene-based Topic Channel Construction System for E-Commerce
To conduct scene marketing for e-commerce platforms, this work presents a novel product form, scene-based topic channel which typically consists of a list of diverse products belonging to the same usage scenario and a topic title that describes the scenario with marketing words.
Intelligent Online Selling Point Extraction for E-Commerce Recommendation
In addition, this kind of product description should be eye-catching to the readers.
Automatic Product Copywriting for E-Commerce
It consists of two main components: 1) natural language generation, which is built from a transformer-pointer network and a pre-trained sequence-to-sequence model based on millions of training data from our in-house platform; and 2) copywriting quality control, which is based on both automatic evaluation and human screening.
Learning to Generate Visual Questions with Noisy Supervision
The task of visual question generation (VQG) aims to generate human-like neural questions from an image and potentially other side information (e. g., answer type or the answer itself).
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.
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.
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization
To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task.
Ranked #3 on
Text Summarization
on SAMSum
Improving Sequential Recommendation Consistency with Self-Supervised Imitation
In this paper, we propose a model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation.
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.
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.
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.
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.
Collaborative Group Learning
Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima.
Group-wise Contrastive Learning for Neural Dialogue Generation
Neural dialogue response generation has gained much popularity in recent years.
Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems
Though reinforcement learning~(RL) naturally fits the problem of maximizing the long term rewards, applying RL to optimize long-term user engagement is still facing challenges: user behaviors are versatile and difficult to model, which typically consists of both instant feedback~(e. g. clicks, ordering) and delayed feedback~(e. g. dwell time, revisit); in addition, performing effective off-policy learning is still immature, especially when combining bootstrapping and function approximation.
Deep Reinforcement Learning for Page-wise Recommendations
In particular, we propose a principled approach to jointly generate a set of complementary items and the corresponding strategy to display them in a 2-D page; and propose a novel page-wise recommendation framework based on deep reinforcement learning, DeepPage, which can optimize a page of items with proper display based on real-time feedback from users.
Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
Users' feedback can be positive and negative and both types of feedback have great potentials to boost recommendations.
Deep Reinforcement Learning for List-wise Recommendations
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services.
