Language Adaptation for Entity Relation Classification via Adversarial Neural Networks

Entity relation classification aims to classify the semantic relationship between two marked entities in a given sentence,and plays a vital role in various natural language processing applications.However,existing studies focus on exploiting mono-lingual data in English,due to the lack of labeled data in other languages.How to effectively benefit from a richly-labeled language to help a poorly-labeled language is still an open problem.In this paper,we come up with a language adaptation framework for cross-lingual entity relation classification.The basic idea is to employ adversarial neural networks(AdvNN)to transfer feature representations from one language to another.Especially,such a language adaptation framework enables feature imitation via the competition between a sentence encoder and a rival language discriminator to generate effective representations.To verify the effectiveness of AdvNN,we introduce two kinds of adversarial structures,dual-channel AdvNN and single-channel AdvNN.Experimental results on the ACE 2005 multilingual training corpus show that our single-channel AdvNN achieves the best performance on both unsupervised and semi-supervised scenarios,yielding an improvement of 6.61%and 2.98%over the state-of-the-art,respectively.Compared with baselines which directly adopt a machine translation module,we find that both dual-channel and single-channel AdvNN significantly improve the performances(F1)of cross-lingual entity relation classification.Moreover,extensive analysis and discussion demonstrate the appropriateness and effectiveness of different parameter settings in our language adaptation framework.

A Novel Similarity Measure to Induce Semantic Classes and Its Application for Language Model Adaptation in a Dialogue System

In this paper,we propose a novel co-occurrence probabilities based similarity measure for inducing semantic classes.Clustering with the new similarity measure outperforms the widely used distance based on Kullback-Leibler divergence in precision,recall and F1 evaluation.In our experiments,we induced semantic classes from unannotated in-domain corpus and then used the induced classes and structures to generate large in-domain corpus which was then used for language model adaptation.Character recognition rate was improved from 85.2% to 91%.We imply a new measure to solve the lack of domain data problem by first induction then generation for a dialogue system.