Tracking the World State with Recurrent Entity Networks

By Mikael Henaff, Jason Aaron Edward Weston, Arthur Szlam, Antoine Bordes, Yann LeCun. 2016

236 citations recorded by the source corpus.

We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data. For language understanding tasks, it can reason on-the-fly as it reads text, not just when it is required to answer a question or respond as is the case for a Memory Network (Sukhbaatar et al., 2015). Like a Neural Turing Machine or Differentiable Neural Computer (Graves et al., 2014; 2016) it maintains a fixed size memory and can learn to perform location and content-based read and write operations. However, unlike those models it has a simple parallel architecture in which several memory locations can be updated simultaneously. The EntNet sets a new state-of-the-art on the bAbI tasks, and is the first method to solve all the tasks in the 10k training examples setting. We also demonstrate that it can solve a reasoning task which requires a large number of supporting facts, which other methods are not able to solve, and can generalize past its training horizon. It can also be practically used on large scale datasets such as Children's Book Test, where it obtains competitive performance, reading the story in a single pass.

Subfields: Artificial Intelligence, Natural Language Processing, Model Architectures

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

In Natural Language Processing

In Model Architectures

Citations in the corpus

Universal Transformers (2018, methodology): “To encode the input, similar to [14], we first encode each fact in the story by applying a learned multiplicative positional mask to each word’s embeddding, and summing up all emebeddings.”
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge (2018, background): “It has stimulated work on use of memory network neural architectures (Weston et al., 2014), supporting a form of multistep reasoning where a neural memory propagates information from one step to another (e.g. Henaff et al., 2016; Seo et al., 2017a).”
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, background): “While in machine learning some read, write memory architectures have been developed (Graves, Wayne, and Danihelka, 2014; Henaff et al., 2017) they have mostly not been successful so far at scaling to realistic large-scale dialogue tasks.”
A simple neural network module for relational reasoning (2017, neutral): “…task, Memory Networks pass 14 / 20, DNC 18 / 20, Sparse DNC 19 / 20, and EntNet 16 / 20 (the authors of EntNets report state-of-the-art at 20 / 20; however, unlike previously reported results this was not done with joint training on all tasks, where they instead achieve 16 / 20) [42, 9, 34, 13].”
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs (2022, background): “…that training entity-centric neural architectures on text with entity coreference information yields more entity-aware LLMs, both in recurrent (Henaff et al., 2017; Ji et al., 2017; Yang et al., 2017; Liu et al., 2019) and Transformer-based models (Févry et al., 2020; De Cao et al., 2020;…”
Evaluating Theory of Mind in Question Answering (2018, methodology): “We also report results of two relevant memory-augmented neural network models on our tasks, EntNet (Henaff et al., 2017)”
ParlAI: A Dialog Research Software Platform (2017, neutral): “Overall, while DrQA can solve some of the bAbI tasks and performs well on SQuAD, it does not match the best performing methods on bAbI (Seo et al., 2016; Henaff et al., 2016), and multitasking does not help.”
On the Binding Problem in Artificial Neural Networks (2020, methodology): “Other memory-based approaches take a step towards GNNs by updating each memory location in parallel (Henaff et al., 2017; Kaiser and Sutskever, 2016) or incorporate specialized structure for reasoning into the processor, e.g. for the purpose of visual question answering using a read-only memory…”
Recurrent Independent Mechanisms (2019, methodology): “Separate Recurrent Models: EnTNet (Henaff et al., 2016) and IndRNN (Li et al.”
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension (2018, methodology): “When applying existing state-of-the-art systems, such as Recurrent Entity Networks (Hena ﬀ et al., 2016) and Query-reduction Networks (Seo et al., 2017b), we ﬁnd that they do not perform well on ProPara and the results are only slightly better than the majority baselines.”
Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge (2020, background): “…have been incorporated into different types of memory networks operating over latent parameters (Weston et al., 2014; Miller et al., 2016), entity memories (Henaff et al., 2016; Févry et al., 2020), relations (Logan et al., 2019), and embedded text passages (Guu et al., 2020; Lewis et al., 2020).”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, background): “…literature, such multi-hop reading comprehension tasks are frequently solved via end-to-end differentiable (deep learning) models (Sukhbaatar et al., 2015; Peng et al., 2015; Seo et al., 2016b; Raison et al., 2018; Henaff et al., 2016; Kumar et al., 2016; Graves et al., 2016; Dhingra et al., 2018).”
Recurrent Relational Networks (2017, neutral): “8 EntNet [Henaff et al., 2016] 5 9 .”
Modeling Naive Psychology of Characters in Simple Commonsense Stories (2018, methodology): “REN We use the “tied” recurrent entity network from Henaff et al. (2017).”
Dynamic Entity Representations in Neural Language Models (2017, methodology): “A similar updating scheme has been used by Henaff et al. (2016) for the “memory blocks” in their recurrent entity network models.”
What Context Features Can Transformer Language Models Use? (2021, positive): “…be informatively summarized in ﬁxed-sized vectors; our ﬁnding that most usable information is carried by nouns is consistent with earlier ﬁndings about both specialized neural architectures (Henaff et al., 2016) and discourse representations in feature-based models (Barzilay and La-pata, 2008).”
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (2019, background): “, 2018): a bidirectional EntNet (Henaff et al., 2016) with external “memory chains” with a delayed memory update mechanism to track entities.”