Dialogue

Parameter-efficient low-resource dialogue state tracking by prompt tuning

Mingyu Derek Ma, Jiun-Yu Kao, Shuyang Gao, Arpit Gupta, Di Jin, Tagyoung Chung, Violet Peng

Interspeech 2023

2023

Dialogue state tracking (DST) is an important step in dialogue management to keep track of users’ beliefs. Existing works fine-tune all language model (LM) parameters to tackle the DST task, which requires significant data and computing resources for training and hosting. The cost grows exponentially in the real-world deployment where dozens of fine-tuned LM are used for different domains and tasks. To

Conversational AI

Diable: Efficient dialogue state tracking as operations on tables

Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Lluís Marquez

ACL Findings 2023

2023

Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn. This approach is inefficient, especially when the number of slots is large and the conversation is long. In this paper, we propose Diable, a new task formalisation

Conversational AI

Teaching virtual robots to follow natural-language instructions

Qiaozi (QZ) Gao, Gaurav Sukhatme

January 23, 2023

Two Alexa AI papers present novel methodologies that use vision and language understanding to improve embodied task completion in simulated environments.

Conversational AI

Intent induction from conversations for task-oriented dialogue track at DSTC 11

James Gung, Raphael Shu, Emily Moeng, Wesley Rose, Salvatore Romeo, Yassine Benajiba, Arshit Gupta, Saab Mansour, Yi Zhang

ACL 2023 Workshop on the Eleventh Dialog System Technology Challenge (DSTC11)

2023

With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states. However, a lack of dedicated benchmarks and standardized evaluation has made progress difficult to track and comparisons between systems difficult to make. This challenge track1 , held as

Conversational AI

Self-supervised pre-training and semi-supervised learning for extractive dialog summarization

Yingying Zhuang, Jiecheng Song, Narayanan Sadagopan, Anurag Beniwal

Web Conference 2023 Workshop on Natural-Language Processing for Social Media

2023

Language model pre-training has led to state-of-the-art performance in text summarization. While a variety of pre-trained transformer models are available nowadays, they are mostly trained on documents. In this study we introduce self-supervised pre-training to enhance the BERT model’s semantic and structural understanding of dialog texts from social media. We also propose a semisupervised teacher-student

Conversational AI

External knowledge acquisition for end-to-end document-oriented dialog systems

Tuan M. Lai, Giuseppe Castellucci, Saar Kuzi, Heng Ji, Oleg Rokhlenko

EACL 2023

2023

End-to-end neural models for conversational AI often assume that a response can be generated by considering only the knowledge acquired by the model during training. Document-oriented conversational models make a similar assumption by conditioning the input on the document and assuming that any other knowledge is captured in the model’s weights. However, a conversation may refer to external knowledge sources

Conversational AI

Conversational text-to-SQL: An odyssey into state-of-the-art and challenges ahead

Sree Hari Krishnan Parthasarathi, Lu Zeng, Dilek Hakkani-Tür

ICASSP 2023

2023

Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family, in conjunction with constrained decoding. With multi-tasking (MT) over coherent tasks with discrete prompts during training, we improve over specialized text-to-SQL T5-family models

Machine learning

Contextual dynamic prompting for response generation in task-oriented dialog systems

Sandesh Swamy, Narges Tabari, Chacha Chen, Rashmi Gangadharaiah

EACL 2023

2023

Response generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm of adapting such extremely large language models would be by fine-tuning on the downstream tasks which is not only time-consuming but also involves significant resources and access to fine-tuning data.

Conversational AI

Improving open-domain dialogue evaluation with a causal inference model

Cat P. Le, Luke Dai, Michael Johnston, Yang Liu, Marilyn Walker, Reza Ghanadan

IWSDS 2023

2023

Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those they give can be highly subjective. Post-hoc ratings by experts are an alternative, but these can be both expensive and complex to collect. Here, we explore the creation

Conversational AI

Taming continuous posteriors for latent variational dialogue policies

Marin Vlastelica, Patrick Ernst, Gyorgy Szarvas

AAAI 2023

2023

Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optimizing dialogue success. Until now, categorical posteriors have been argued to be one of the main drivers of performance. In this work we revisit Gaussian variational posteriors for latent-action RL and show that they can yield

Conversational AI

Dialogue

Work with us