activity
20192022
most citedPrompt-driven efficient Open-set Semi-supervised Learning

2 citations · 3 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV20222 cited

Prompt-driven efficient Open-set Semi-supervised Learning

Haoran Li, Chun-Mei Feng, Tao Zhou +2

Open-set semi-supervised learning (OSSL) has attracted growing interest, which investigates a more practical scenario where out-of-distribution (OOD) samples are only contained in…

cs.CL2022

You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas

Haoran Li, Yangqiu Song, Lixin Fan

Social chatbots, also known as chit-chat chatbots, evolve rapidly with large pretrained language models. Despite the huge progress, privacy concerns have arisen recently: training…

cs.CL2021

ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining

Alexander R. Fabbri, Faiaz Rahman, Imad Rizvi +4

While online conversations can cover a vast amount of information in many different formats, abstractive text summarization has primarily focused on modeling solely news articles.…

cs.CL2020

Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation

Alexander R. Fabbri, Simeng Han, Haoyuan Li +5

Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks. However, these models are typicall…

cs.CL2020

Conversational Semantic Parsing

Armen Aghajanyan, Jean Maillard, Akshat Shrivastava +8

The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries. Due to the limitations of the repr…

cs.CL2020

MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark

Haoran Li, Abhinav Arora, Shuohui Chen +3

Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets su…