77 citations · 732 across the 55 of their papers we have counts for
15 papers · 1 filter
Attribute Controlled Dialogue Prompting
Runcheng Liu, Ahmad Rashid, Ivan Kobyzev +2
Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and…
CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation
Md Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar +3
Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by le…
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
Md Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh +3
Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained…
Robust Embeddings Via Distributions
Kira A. Selby, Yinong Wang, Ruizhe Wang +4
Despite recent monumental advances in the field, many Natural Language Processing (NLP) models still struggle to perform adequately on noisy domains. We propose a novel probabilist…
Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
Nabiha Asghar, Ivan Kobyzev, Jesse Hoey +2
State-of-the-art neural dialogue systems excel at syntactic and semantic modelling of language, but often have a hard time establishing emotional alignment with the human interacta…
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté +7
Playing text-based games requires skills in processing natural language and sequential decision making. Achieving human-level performance on text-based games remains an open challe…
Unsupervised Multilingual Alignment using Wasserstein Barycenter
Xin Lian, Kshitij Jain, Jakub Truszkowski +2
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is t…
Progressive Memory Banks for Incremental Domain Adaptation
Nabiha Asghar, Lili Mou, Kira A. Selby +3
This paper addresses the problem of incremental domain adaptation (IDA) in natural language processing (NLP). We assume each domain comes one after another, and that we could only…
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
Bolin Wei, Shuai Lu, Lili Mou +4
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equal…
Variational Attention for Sequence-to-Sequence Models
Hareesh Bahuleyan, Lili Mou, Olga Vechtomova +1
The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural…
Affective Neural Response Generation
Nabiha Asghar, Pascal Poupart, Jesse Hoey +2
Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue…
Order-Planning Neural Text Generation From Structured Data
Lei Sha, Lili Mou, Tianyu Liu +4
Generating texts from structured data (e.g., a table) is important for various natural language processing tasks such as question answering and dialog systems. In recent studies, r…
Discovering Conversational Dependencies between Messages in Dialogs
Wenchao Du, Pascal Poupart, Wei Xu
We investigate the task of inferring conversational dependencies between messages in one-on-one online chat, which has become one of the most popular forms of customer service. We…
Deep Active Learning for Dialogue Generation
Nabiha Asghar, Pascal Poupart, Xin Jiang +1
We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning…
Self-Adaptive Hierarchical Sentence Model
Han Zhao, Zhengdong Lu, Pascal Poupart
The ability to accurately model a sentence at varying stages (e.g., word-phrase-sentence) plays a central role in natural language processing. As an effort towards this goal we pro…