most citedAutomatic Evaluation and Moderation of Open-domain Dialogue Systems

15 citations · 15 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL2023

Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation

Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky

An ideal length-extrapolatable Transformer language model can handle sequences longer than the training length without any fine-tuning. Such long-context utilization capability rel…

cs.CL2023

Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings

Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen +2

The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further e…

cs.CL2023

Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation

Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky +1

Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transform…

eess.AS2023

A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech

Li-Wei Chen, Shinji Watanabe, Alexander Rudnicky

Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the co…

cs.CL202115 cited

Automatic Evaluation and Moderation of Open-domain Dialogue Systems

Chen Zhang, João Sedoc, Luis Fernando D'Haro +2

The development of Open-Domain Dialogue Systems (ODS)is a trending topic due to the large number of research challenges, large societal and business impact, and advances in the und…