Multinomial Adversarial Networks for Multi-Domain Text Classification

By Xilun Chen, Claire Cardie. 2018

139 citations recorded by the source corpus.

Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains. Worse still, for some domains there may not be any annotated data at all. In this work, we propose a multinomial adversarial network (MAN) to tackle this real-world problem of multi-domain text classification (MDTC) in which labeled data may exist for multiple domains, but in insufficient amounts to train effective classifiers for one or more of the domains. We provide theoretical justifications for the MAN framework, proving that different instances of MANs are essentially minimizers of various f-divergence metrics (Ali and Silvey, 1966) among multiple probability distributions. MANs are thus a theoretically sound generalization of traditional adversarial networks that discriminate over two distributions. More specifically, for the MDTC task, MAN learns features that are invariant across multiple domains by resorting to its ability to reduce the divergence among the feature distributions of each domain. We present experimental results showing that MANs significantly outperform the prior art on the MDTC task. We also show that MANs achieve state-of-the-art performance for domains with no labeled data.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

An Adversarial Winograd Schema Challenge at Scale (2019, result): “This approach is also reminiscent of recent work in NLP on adversarial learning (Chen and Cardie, 2018; Belinkov and Bisk, 2018; Elazar and Goldberg, 2018).”
PADA: A Prompt-based Autoregressive Approach for Adaptation to Unseen Domains (2021, methodology): “More recently, adversarial-based methods used unlabeled data to align the source domains to the target domains (Zhao et al., 2018; Chen and Cardie, 2018).”
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference (2019, background): “Recent work in NLP aims to build more robust systems using adversarial methods (Alzantot et al., 2018; Chen & Cardie, 2018; Belinkov & Bisk, 2018, i.a. ).”
Multi-View Domain Adapted Sentence Embeddings for Low-Resource Unsupervised Duplicate Question Detection (2019, methodology): “BM25 is a tough baseline for DQD: In terms of MAP, it is better than or comparable to 14We also experiment with Multinomial Adversarial Networks (MAN) (Chen and Cardie, 2018), a multi-source multitarget framework that can be trained on all 24 forums jointly.”
Domain-agnostic Question-Answering with Adversarial Training (2019, background): “classification (Chen et al., 2016; Liu et al., 2017; Chen and Cardie, 2018), and relation extraction (Wu et al.”