Abstract
Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set of sentences labeled with abstract semantic annotations. These annotations encode the underlying embedded semantic structural relations without explicit word/semantic tag alignment. The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations. The learning framework is applied on two statistical models, the conditional random fields (CRFs) and the hidden Markov support vector machines (HM-SVMs). Our experimental results on the DARPA communicator data show that both CRFs and HM-SVMs outperform the baseline approach, previously proposed hidden vector state (HVS) model which is also trained on abstract semantic annotations. In addition, the proposed framework shows superior performance than two other baseline approaches, a hybrid framework combining HVS and HM-SVMs and discriminative training of HVS, with a relative error reduction rate of about 25% and 15% being achieved in F-measure.
Highlights
Given a sentence such as “I want to fly from Denver to Chicago,” its semantic meaning can be represented as FROMLOC(CITY(Denver)) TOLOC(CITY(Chicago)).Natural language understanding can be considered as a mapping problem where the aim is to map a sentence to its semantic meaning representation as shown above
We propose a learning framework based on expectation maximization (EM) to train statistical models from abstract semantic annotations as Sentences and their abstract annotations
Experiments have been conducted on the DARPA communicator data which were collected in 461 days
Summary
Given a sentence such as “I want to fly from Denver to Chicago,” its semantic meaning can be represented as FROMLOC(CITY(Denver)) TOLOC(CITY(Chicago)). Conditional random fields (CRFs), as one representative example, define a conditional probability distribution over label sequence given an observation sequence, rather than a joint distribution over both label and observation sequences [3] Another example is the hidden Markov support vector machines (HM-SVMs) [4]. It motivates the investigation of train statistical models on abstract semantic annotations without the use of expensive token-style annotations This is a highly challenging problem because the derivation from each sentence to its abstract semantic annotation is not annotated in the training data and is considered hidden. We propose a novel learning framework to train statistical models from unaligned data. It generates semantic parses by computing expectations using initial model parameters.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
