paper-with-me

홈 › Papers

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

2019-06-04 · ACL 2019 7 · Chinnadhurai Sankar, Sandeep Subramanian, Christopher Pal, Sarath Chandar, Yoshua Bengio

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain engineering. A common criticism of these systems is that they seldom understand or use the available dialog history effectively. In this paper, we take an empirical approach to understanding how these models use the available dialog history by studying the sensitivity of the models to artificially introduced unnatural changes or perturbations to their context at test time. We experiment with 10 different types of perturbations on 4 multi-turn dialog datasets and find that commonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most perturbations such as missing or reordering utterances, shuffling words, etc. Also, by open-sourcing our code, we believe that it will serve as a useful diagnostic tool for evaluating dialog systems in the future.

📄 PDF Abstract BibTeX arXiv:1906.01603

Code (1)

chinnadhurai/ParlAI 공식 구현

Tasks

Diagnostic

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Integrating Dialog History into End-to-End Spoken Language Understanding Systems

2021-08-18 · Jatin Ganhotra, Samuel Thomas, Hong-Kwang J. Kuo, Sachindra Joshi 외

End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on …

Intent RecognitionSpoken Language Understanding

CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems

2024-05-24 · Abbas Ghaddar, David Alfonso-Hermelo, Philippe Langlais, Mehdi Rezagholizadeh 외

In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, whi…

DiagnosticHallucinationHallucination Evaluation

A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents

2018-12-02 · Heriberto Cuayáhuitl, Seonghan Ryu, Donghyeon Lee, Jihie Kim

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context window…

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

2024-10-28 · Wei-Nan Zhang, Yiming Cui, Kaiyan Zhang, Yifa Wang 외

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous wor…

Dialogue Generation

Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History

2024-10-22 · Mingi Sung, Seungmin Lee, Jiwon Kim, Sejoon Kim

Translating conversational text, particularly in customer support contexts, presents unique challenges due to its informal and unstructured nature. We propose a context-aware LLM translation system that leverages convers…

Conversation SummarizationTranslation