Asja Fischer


2021

pdf bib
Insertion-based Tree Decoding
Denis Lukovnikov | Asja Fischer
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing
Denis Lukovnikov | Sina Daubener | Asja Fischer
Findings of the Association for Computational Linguistics: EMNLP 2021

While neural networks are ubiquitous in state-of-the-art semantic parsers, it has been shown that most standard models suffer from dramatic performance losses when faced with compositionally out-of-distribution (OOD) data. Recently several methods have been proposed to improve compositional generalization in semantic parsing. In this work we instead focus on the problem of detecting compositionally OOD examples with neural semantic parsers, which, to the best of our knowledge, has not been investigated before. We investigate several strong yet simple methods for OOD detection based on predictive uncertainty. The experimental results demonstrate that these techniques perform well on the standard SCAN and CFQ datasets. Moreover, we show that OOD detection can be further improved by using a heterogeneous ensemble.

2018

pdf bib
Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge
Debanjan Chaudhuri | Agustinus Kristiadi | Jens Lehmann | Asja Fischer
Proceedings of the 22nd Conference on Computational Natural Language Learning

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting. The architecture applies context level attention and incorporates additional external knowledge provided by descriptions of domain-specific words. It uses a bi-directional Gated Recurrent Unit (GRU) for encoding context and responses and learns to attend over the context words given the latent response representation and vice versa. In addition, it incorporates external domain specific information using another GRU for encoding the domain keyword descriptions. This allows better representation of domain-specific keywords in responses and hence improves the overall performance. Experimental results show that our model outperforms all other state-of-the-art methods for response selection in multi-turn conversations.