paper-with-me

Papers

Mitigating the Negative Impact of Over-association for Conversational Query Production

2024-09-29 · Ante Wang, Linfeng Song, Zijun Min, Ge Xu, Xiaoli Wang, Junfeng Yao, Jinsong Su

Conversational query generation aims at producing search queries from dialogue histories, which are then used to retrieve relevant knowledge from a search engine to help knowledge-based dialogue systems. Trained to maximize the likelihood of gold queries, previous models suffer from the data hunger issue, and they tend to both drop important concepts from dialogue histories and generate irrelevant concepts at inference time. We attribute these issues to the over-association phenomenon where a large number of gold queries are indirectly related to the dialogue topics, because annotators may unconsciously perform reasoning with their background knowledge when generating these gold queries. We carefully analyze the negative effects of this phenomenon on pretrained Seq2seq query producers and then propose effective instance-level weighting strategies for training to mitigate these issues from multiple perspectives. Experiments on two benchmarks, Wizard-of-Internet and DuSinc, show that our strategies effectively alleviate the negative effects and lead to significant performance gains (2%-5% across automatic metrics and human evaluation). Further analysis shows that our model selects better concepts from dialogue histories and is 10 times more data efficient than the baseline. The code is available at https://github.com/DeepLearnXMU/QG-OverAsso.

📄 PDF Abstract BibTeX arXiv:2409.19572

Code (1)

deeplearnxmu/qg-overasso 공식 구현 pytorch

Tasks

Attribute

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Combating Semantic Contamination in Learning with Label Noise

2024-12-16 · Wenxiao Fan, Kan Li

Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these met…

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?

2024-03-07 · Ibrahim Alabdulmohsin, Xiao Wang, Andreas Steiner, Priya Goyal 외

We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffirm prior conclusions that CLIP models can…

Image to textImage-to-Text RetrievalRetrievalText Retrieval

Mitigating Pooling Bias in E-commerce Search via False Negative Estimation

2023-11-11 · Xiaochen Wang, Xiao Xiao, Ruhan Zhang, Xuan Zhang 외

Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained throug…

LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History

2024-02-28 · Akash Gupta, Ivaxi Sheth, Vyas Raina, Mark Gales 외

With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by user…

The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI

2024-10-07 · Merlin Stein, Jamie Bernardi, Connor Dunlop

Language-based AI systems are diffusing into society, bringing positive and negative impacts. Mitigating negative impacts depends on accurate impact assessments, drawn from an empirical evidence base that makes causal co…

Management