Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems

2017-09-01 · EMNLP 2017 9 · Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao, Rui Yan

The study on human-computer conversation systems is a hot research topic nowadays. One of the prevailing methods to build the system is using the generative Sequence-to-Sequence (Seq2Seq) model through neural networks. However, the standard Seq2Seq model is prone to generate trivial responses. In this paper, we aim to generate a more meaningful and informative reply when answering a given question. We propose an implicit content-introducing method which incorporates additional information into the Seq2Seq model in a flexible way. Specifically, we fuse the general decoding and the auxiliary cue word information through our proposed hierarchical gated fusion unit. Experiments on real-life data demonstrate that our model consistently outperforms a set of competitive baselines in terms of BLEU scores and human evaluation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Short-Text Conversation

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…

Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation

2016-07-04 · COLING 2016 12 · Lili Mou, Yiping Song, Rui Yan, Ge Li 외

Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate …

Position Short-Text Conversation

Disentangling Content from Style to Overcome Shortcut Learning: A Hybrid Generative-Discriminative Learning Framework

2025-09-15 · Siming Fu, Sijun Dong, Xiaoliang Meng arxiv

Despite the remarkable success of Self-Supervised Learning (SSL), its generalization is fundamentally hindered by Shortcut Learning, where models exploit superficial features like texture instead of intrinsic structure. …

Self-Supervised Learning

Fusion Segment Transformer: Bi-Directional Attention Guided Fusion Network for AI-Generated Music Detection

2026-01-20 · Yumin Kim, Seonghyeon Go arxiv

With the rise of generative AI technology, anyone can now easily create and deploy AI-generated music, which has heightened the need for technical solutions to address copyright and ownership issues. While existing works…

Neural Attention for Learning to Rank Questions in Community Question Answering

2016-12-01 · COLING 2016 12 · Salvatore Romeo, Giovanni Da San Martino, Alberto Barr{\'o}n-Cede{\~n}o, Aless Moschitti 외

In real-world data, e.g., from Web forums, text is often contaminated with redundant or irrelevant content, which leads to introducing noise in machine learning algorithms. In this paper, we apply Long Short-Term Memory …

Community Question Answering Learning-To-Rank Natural Language Inference Position+3

Context Enhanced Short Text Matching using Clickthrough Data

2022-03-03 · Mao Yan Chen, Haiyun Jiang, Yujiu Yang

The short text matching task employs a model to determine whether two short texts have the same semantic meaning or intent. Existing short text matching models usually rely on the content of short texts which are lack in…

Text Matching