Fréderic Godin


pdf bib
Learning When Not to Answer: a Ternary Reward Structure for Reinforcement Learning Based Question Answering
Fréderic Godin | Anjishnu Kumar | Arpit Mittal
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)

In this paper, we investigate the challenges of using reinforcement learning agents for question-answering over knowledge graphs for real-world applications. We examine the performance metrics used by state-of-the-art systems and determine that they are inadequate for such settings. More specifically, they do not evaluate the systems correctly for situations when there is no answer available and thus agents optimized for these metrics are poor at modeling confidence. We introduce a simple new performance metric for evaluating question-answering agents that is more representative of practical usage conditions, and optimize for this metric by extending the binary reward structure used in prior work to a ternary reward structure which also rewards an agent for not answering a question rather than giving an incorrect answer. We show that this can drastically improve the precision of answered questions while only not answering a limited number of previously correctly answered questions. Employing a supervised learning strategy using depth-first-search paths to bootstrap the reinforcement learning algorithm further improves performance.


pdf bib
Predefined Sparseness in Recurrent Sequence Models
Thomas Demeester | Johannes Deleu | Fréderic Godin | Chris Develder
Proceedings of the 22nd Conference on Computational Natural Language Learning

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this advantage does not hold during training. We propose techniques to enforce sparseness upfront in recurrent sequence models for NLP applications, to also benefit training. First, in language modeling, we show how to increase hidden state sizes in recurrent layers without increasing the number of parameters, leading to more expressive models. Second, for sequence labeling, we show that word embeddings with predefined sparseness lead to similar performance as dense embeddings, at a fraction of the number of trainable parameters.

pdf bib
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?
Fréderic Godin | Kris Demuynck | Joni Dambre | Wesley De Neve | Thomas Demeester
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us to compare convolutional neural networks and bidirectional long short-term memory networks. We evaluate and compare these models for the task of morphological tagging on three morphologically different languages and show that these models implicitly discover understandable linguistic rules.


pdf bib
Improving Language Modeling using Densely Connected Recurrent Neural Networks
Fréderic Godin | Joni Dambre | Wesley De Neve
Proceedings of the 2nd Workshop on Representation Learning for NLP

In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2-layer LSTM model trained with dropout (Zaremba et al., 2014). In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions.


pdf bib
Multimedia Lab @ ACL WNUT NER Shared Task: Named Entity Recognition for Twitter Microposts using Distributed Word Representations
Fréderic Godin | Baptist Vandersmissen | Wesley De Neve | Rik Van de Walle
Proceedings of the Workshop on Noisy User-generated Text