Min‐Yen Kan

The CL-SciSumm Shared Task 2018: Results and Key Insights

2018 · arXiv (Cornell University)

This overview describes the official results of the CL-SciSumm Shared Task 2018 -- the first medium-scale shared task on scientific document summarization in the computational linguistics (CL) domain. This year, the dataset comprised 60 annotated …

CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation

2023 · arXiv (Cornell University)

Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance. Given recent developments in Large Language Models (LLMs), models such as ChatGPT demonstrate zero-shot capability on many …

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models

2024 · arXiv (Cornell University)

Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused …

Beyond Memorization: The Challenge of Random Memory Access in Language Models

2024

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks.However, the mechanisms underlying knowledge storage and memory access within their parameters remain elusive.In this paper, we investigate whether …

TriRank

2015

Most existing collaborative filtering techniques have focused on modeling the binary relation of users to items by extracting from user ratings. Aside from users' ratings, their affiliated reviews often provide the rationale for their ratings …

Fast Matrix Factorization for Online Recommendation with Implicit Feedback

2016

This paper contributes improvements on both the effectiveness and efficiency of Matrix Factorization (MF) methods for implicit feedback. We highlight two critical issues of existing works. First, due to the large space of unobserved feedback, …

Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures

2018

Existing solutions to task-oriented dialogue systems follow pipeline designs which introduce architectural complexity and fragility. We propose a novel, holistic, extendable framework based on a single sequence-to-sequence (seq2seq) model which can be optimized with supervised …

BiRank: Towards Ranking on Bipartite Graphs

2016 · IEEE Transactions on Knowledge and Data Engineering

The bipartite graph is a ubiquitous data structure that can model the relationship between two entity types: for instance, users and items, queries and webpages. In this paper, we study the problem of ranking vertices …

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

2020

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. …

Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen

2020

The curse of knowledge can impede communication between experts and laymen. We propose a new task of expertise style transfer and contribute a manually annotated dataset with the goal of alleviating such cognitive biases. Solving …