Building intelligent open domain dialog system is a trending and resurgent interest due to the availability of huge amount of conversational data and recent progress on conversational AI. It allows the user to take a conversation anywhere.

Open Domain Chatbot

Personalizing Dialogue Agents: I have a dog, do you have pets too?

Abstract: Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i)condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.

Authors: Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, Jason Weston (Montreal Institute for Learning Algorithms, Facebook AI Research)

Jointly Optimizing Diversity and Relevance in Neural Response Generation

Abstract: Although recent neural conversation models have shown great potential, they often generate bland and generic responses. While various approaches have been explored to diversify the output of the conversation model, the improvement often comes at the cost of decreased relevance. In this paper, we propose a SpaceFusion model to jointly optimize diversity and relevance that essentially fuses the latent space of a sequence-to-sequence model and that of an autoencoder model by leveraging novel regularization terms. As a result, our approach induces a latent space in which the distance and direction from the predicted response vector roughly match the relevance and diversity, respectively. This property also lends itself well to an intuitive visualization of the latent space. Both automatic and human evaluation results demonstrate that the proposed approach brings significant improvement compared to strong baselines in both diversity and relevance.

Authors: Xiang Gao, Sungjin Lee, Yizhe Zhang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan (Microsoft Research)

Regularization

AutoEncoder

Conversation

Unifying Human and Statistical Evaluation for Natural Language Generation

Abstract: How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models that simply plagiarize from the training set. On the other hand, statistical evaluation (i.e., perplexity) captures diversity but not quality, as models that occasionally emit low quality samples would be insufficiently penalized. In this paper, we propose a unified framework which evaluates both diversity and quality, based on the optimal error rate of predicting whether a sentence is human- or machine-generated. We demonstrate that this error rate can be efficiently estimated by combining human and statistical evaluation, using an evaluation metric which we call HUSE. On summarization and chit-chat dialogue, we show that (i) HUSE detects diversity defects which fool pure human evaluation and that (ii) techniques such as annealing for improving quality actually decrease HUSE due to decreased diversity.

Authors: Tatsunori B. Hashimoto, Hugh Zhang, Percy Liang (Stanford University)

Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses 

Abstract: Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response quality. Yet having an accurate automatic evaluation procedure is crucial for dialogue research, as it allows rapid prototyping and testing of new models with fewer expensive human evaluations. In response to this challenge, we formulate automatic dialogue evaluation as a learning problem. We present an evaluation model (ADEM) that learns to predict human-like scores to input responses, using a new dataset of human response scores. We show that the ADEM model's predictions correlate significantly, and at a level much higher than word-overlap metrics such as BLEU, with human judgements at both the utterance and system-level. We also show that ADEM can generalize to evaluating dialogue models unseen during training, an important step for automatic dialogue evaluation.

Authors: Ryan Lowe, Michael Noseworthy, Iulian V. Serban, Nicolas Angelard-Gontier, Yoshua Bengio, Joelle Pineau (McGill University, Universite de Montreal)

Google's Meena: Open Dialog systems | Daniel Adiwardana

Daniel Adiwardana, senior research engineer of Google Brain and the first author of the notable paper "Towards a Human-like Open-Domain Chatbot", introduces Meena, Google's new open-domain chatbot. 

Abstract: We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated. 

Neural Network

Transformer: Attention Is All You Need (Paper Explained)

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Authors: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, Ashish Vaswani (Google Brain, University of Toronto)

Constituency Parsing

Convolutional Neural Networks

Convolutions

Machine Translation

Adafactor: Adaptive Learning Rates with Sublinear Memory Cost

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter second-moment estimators requires memory equal to the number of parameters. For the case of neural network weight matrices, we propose maintaining only the per-row and per-column sums of these moving averages, and estimating the per-parameter second moments based on these sums. We demonstrate empirically that this method produces similar results to the baseline. Secondly, we show that adaptive methods can produce larger-than-desired updates when the decay rate of the second moment accumulator is too slow. We propose update clipping and a gradually increasing decay rate scheme as remedies. Combining these methods and dropping momentum, we achieve comparable results to the published Adam regime in training the Transformer model on the WMT 2014 English-German machine translation task, while using very little auxiliary storage in the optimizer. Finally, we propose scaling the parameter updates based on the scale of the parameters themselves.

AdaDelta

Adafactor

RMSProp

Adam

EMNLP 2020: Experience Grounds Language

Experience Grounds Language
Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph Turian
https://twitter.com/ybisk

Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle tasks after being trained on text alone, successful linguistic communication relies on a shared experience of the world. It is this shared experience that makes utterances meaningful.
Natural language processing is a diverse field, and progress throughout its development has come from new representational theories, modeling techniques, data collection paradigms, and tasks. We posit that the present success of representation learning approaches trained on large, text-only corpora requires the parallel tradition of research on the broader physical and social context of language to address the deeper questions of communication.

EMNLP 2020 #NLProc Natural Language Processing

Natural Language Processing

Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high variance of the predictive function. However, such a simple trade-off does not adequately describe deep learning models that simultaneously attain low bias and variance in the heavily overparameterized regime. A primary obstacle in explaining this behavior is that deep learning algorithms typically involve multiple sources of randomness whose individual contributions are not visible in the total variance. To enable fine-grained analysis, we describe an interpretable, symmetric decomposition of the variance into terms associated with the randomness from sampling, initialization, and the labels. Moreover, we compute the high-dimensional asymptotic behavior of this decomposition for random feature kernel regression, and analyze the strikingly rich phenomenology that arises. We find that the bias decreases monotonically with the network width, but the variance terms exhibit non-monotonic behavior and can diverge at the interpolation boundary, even in the absence of label noise. The divergence is caused by the \emph{interaction} between sampling and initialization and can therefore be eliminated by marginalizing over samples (i.e. bagging) \emph{or} over the initial parameters (i.e. ensemble learning).

Speakers: Ben Adlam, Jeffrey Pennington

What makes a good conversation? How controllable attributes affect human judgments

Abstract: A good conversation requires balance -- between simplicity and detail; staying on topic and changing it; asking questions and answering them. Although dialogue agents are commonly evaluated via human judgments of overall quality, the relationship between quality and these individual factors is less well-studied. In this work, we examine two controllable neural text generation methods, conditional training and weighted decoding, in order to control four important attributes for chitchat dialogue: repetition, specificity, response-relatedness and question-asking. We conduct a large-scale human evaluation to measure the effect of these control parameters on multi-turn interactive conversations on the PersonaChat task. We provide a detailed analysis of their relationship to high-level aspects of conversation, and show that by controlling combinations of these variables our models obtain clear improvements in human quality judgments.

Authors: Abigail See, Stephen Roller, Douwe Kiela, Jason Weston (Stanford University, Facebook AI Research)

Text Generation

Solving Compositional Reinforcement Learning Problems via Task Reduction

  We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems. SIR is based on two core ideas: task reduction and self-imitation. Task reduction tackles a hard-to-solve task by actively reducing it to an easier task whose solution is known by the RL agent. Once the original hard task is successfully solved by task reduction, the agent naturally obtains a self-generated solution trajectory to imitate. By continuously collecting and imitating such demonstrations, the agent is able to progressively expand the solved subspace in the entire task space. Experiment results show that SIR can significantly accelerate and improve learning on a variety of challenging sparse-reward continuous-control problems with compositional structures. Code and videos are available at https://sites.google.com/view/sir-compositional. 

Speakers: Yunfei Li, Huazhe Xu, Yilin Wu, Xiaolong Wang, Yi Wu

Tensor2Tensor for Neural Machine Translation

Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model.

Neural Machine Translation by Jointly Learning to Align and Translate | Paper Explained

Neural machine translation is a recently proposed approach to machine
translation. Unlike the traditional statistical machine translation, the neural
machine translation aims at building a single neural network that can be
jointly tuned to maximize the translation performance. The models proposed
recently for neural machine translation often belong to a family of
encoder-decoders and consists of an encoder that encodes a source sentence into
a fixed-length vector from which a decoder generates a translation. In this
paper, we conjecture that the use of a fixed-length vector is a bottleneck in
improving the performance of this basic encoder-decoder architecture, and
propose to extend this by allowing a model to automatically (soft-)search for
parts of a source sentence that are relevant to predicting a target word,
without having to form these parts as a hard segment explicitly. With this new
approach, we achieve a translation performance comparable to the existing
state-of-the-art phrase-based system on the task of English-to-French
translation. Furthermore, qualitative analysis reveals that the
(soft-)alignments found by the model agree well with our intuition.

Hierarchical Neural Story Generation

Abstract: We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text. We gain further improvements with a novel form of model fusion that improves the relevance of the story to the prompt, and adding a new gated multi-scale self-attention mechanism to model long-range context. Experiments show large improvements over strong baselines on both automated and human evaluations. Human judges prefer stories generated by our approach to those from a strong non-hierarchical model by a factor of two to one.

Authors: Angela Fan, Mike Lewis, Yann Dauphin (Facebook AI Research)

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

Modern neural networks are often regarded as complex black-box functions whose behavior is difficult to understand owing to their nonlinear dependence on the data and the nonconvexity in their loss landscapes. In this work, we show that these common perceptions can be completely false in the early phase of learning. In particular, we formally prove that, for a class of well-behaved input distributions, the early-time learning dynamics of a two-layer fully-connected neural network can be mimicked by training a simple linear model on the inputs. We additionally argue that this surprising simplicity can persist in networks with more layers and with convolutional architecture, which we verify empirically. Key to our analysis is to bound the spectral norm of the difference between the Neural Tangent Kernel (NTK) at initialization and an affine transform of the data kernel; however, unlike many previous results utilizing the NTK, we do not require the network to have disproportionately large width, and the network is allowed to escape the kernel regime later in training.

Speakers: Wei Hu, Lechao Xiao, Ben Adlam, Jeffrey Pennington

Countering Language Drift with Seeded Iterated Learning

Supervised learning methods excel at capturing statistical properties of language when trained over large text corpora. Yet, these models often produce inconsistent outputs in goal-oriented language settings as they are not trained to complete the underlying task. Moreover, as soon as the agents are finetuned to maximize task completion, they suffer from the so-called language drift phenomenon: they slowly lose syntactic and semantic properties of language as they only focus on solving the task. In this paper, we propose a generic approach to counter language drift by using iterated learning. We iterate between fine-tuning agents with interactive training steps, and periodically replacing them with new agents that are seeded from last iteration and trained to imitate the latest finetuned models. Iterated learning does not require external syntactic constraint nor semantic knowledge, making it a valuable task-agnostic finetuning protocol. We first explore iterated learning in the Lewis Game. We then scale-up the approach in the translation game. In both settings, our results show that iterated learn-ing drastically counters language drift as well as it improves the task completion metric.

Speakers: Yuchen Lu, Soumye Singhal, Florian Strub, Aaron Courville, Olivier Pietquin

Distilling the Knowledge in a Neural Network | Paper Explained

Video review of NIPS 2014 paper "Distilling the Knowledge in a Neural Network" authored by Geoffrey Hinton, Oriol Vinyals, and Jeff Dean.
Abstract: A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier to deploy and we develop this approach further using a different compression technique. We achieve some surprising results on MNIST and we show that we can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model. We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel.



Other recommended papers

Tensor2Tensor for Neural Machine Translation

Crossminds Chrome Extension

Other recommended papers

Tensor2Tensor for Neural Machine Translation

Crossminds Chrome Extension

Subscribe to Our Newsletter