Robustness Testing of Language Understanding in Dialog Systems

Most language understanding models in dialog systems are trained on a small amount of annotated training data, and evaluated in a small set from the same distribution. However, these models can lead to system failure or undesirable outputs when being exposed to natural perturbation in practice. In this paper, we conduct comprehensive evaluation and analysis with respect to the robustness of natural language understanding models, and introduce three important aspects related to language understanding in real-world dialog systems, namely, language variety, speech characteristics, and noise perturbation. We propose a model-agnostic toolkit LAUG to approximate natural perturbation for testing the robustness issues in dialog systems. Four data augmentation approaches covering the three aspects are assembled in LAUG, which reveals critical robustness issues in state-of-the-art models. The augmented dataset through LAUG can be used to facilitate future research on the robustness testing of language understanding in dialog systems.

ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning

Pre-trained Language Models (PLMs) have shown strong performance in various downstream Natural Language Processing (NLP) tasks. However, PLMs still cannot well capture the factual knowledge in the text, which is crucial for understanding the whole text, especially for document-level language understanding tasks. To address this issue, we propose a novel contrastive learning framework named ERICA in pre-training phase to obtain a deeper understanding of the entities and their relations in text. Specifically, (1) to better understand entities, we propose an entity discrimination task that distinguishes which tail entity can be inferred by the given head entity and relation. (2) Besides, to better understand relations, we employ a relation discrimination task which distinguishes whether two entity pairs are close or not in relational semantics. Experimental results demonstrate that our proposed ERICA framework achieves consistent improvements on several document-level language understanding tasks, including relation extraction and reading comprehension, especially under low resource setting. Meanwhile, ERICA achieves comparable or better performance on sentence-level tasks. We will release the datasets, source codes and pre-trained language models for further research explorations.

AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text

Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some characters or words in the original examples, only substitution is insufficient to uncover all robustness issues of models. In this paper, we present AdvExpander, a method that crafts new adversarial examples by expanding text, which is complementary to previous substitution-based methods. We first utilize linguistic rules to determine which constituents to expand and what types of modifiers to expand with. We then expand each constituent by inserting an adversarial modifier searched from a CVAE-based generative model which is pre-trained on a large scale corpus. To search adversarial modifiers, we directly search adversarial latent codes in the latent space without tuning the pre-trained parameters. To ensure that our adversarial examples are label-preserving for text matching, we also constrain the modifications with a heuristic rule. Experiments on three classification tasks verify the effectiveness of AdvExpander and the validity of our adversarial examples. AdvExpander crafts a new type of adversarial examples by text expansion, thereby promising to reveal new robustness issues.

CPM: A Large-scale Generative Chinese Pre-trained Language Model

Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot of attention due to the capacity of few-shot (even zero-shot) learning. However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available. In this technical report, we release the Chinese Pre-trained Language Model (CPM) with generative pre-training on large-scale Chinese training data. To the best of our knowledge, CPM, with 2.6 billion parameters and 100GB Chinese training data, is the largest Chinese pre-trained language model, which could facilitate several downstream Chinese NLP tasks, such as conversation, essay generation, cloze test, and language understanding. Extensive experiments demonstrate that CPM achieves strong performance on many NLP tasks in the settings of few-shot (even zero-shot) learning. The code and parameters are available at https://github.com/TsinghuaAI/CPM-Generate.

Reinforced Molecular Optimization with Neighborhood-Controlled Grammars

A major challenge in the pharmaceutical industry is to design novel molecules with specific desired properties, especially when the property evaluation is costly. Here, we propose MNCE-RL, a graph convolutional policy network for molecular optimization with molecular neighborhood-controlled embedding grammars through reinforcement learning. We extend the original neighborhood-controlled embedding grammars to make them applicable to molecular graph generation and design an efficient algorithm to infer grammatical production rules from given molecules. The use of grammars guarantees the validity of the generated molecular structures. By transforming molecular graphs to parse trees with the inferred grammars, the molecular structure generation task is modeled as a Markov decision process where a policy gradient strategy is utilized. In a series of experiments, we demonstrate that our approach achieves state-of-the-art performance in a diverse range of molecular optimization tasks and exhibits significant superiority in optimizing molecular properties with a limited number of property evaluations.

Overview of the Ninth Dialog System Technology Challenge: DSTC9

This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in dialog systems, namely, 1. Task-oriented dialog Modeling with unstructured knowledge access, 2. Multi-domain task-oriented dialog, 3. Interactive evaluation of dialog, and 4. Situated interactive multi-modal dialog. This paper describes the task definition, provided datasets, baselines and evaluation set-up for each track. We also summarize the results of the submitted systems to highlight the overall trends of the state-of-the-art technologies for the tasks.

Bridging the Gap between Conversational Reasoning and Interactive Recommendation

There have been growing interests in building a conversational recommender system, where the system simultaneously interacts with the user and explores the user's preference throughout conversational interactions. Recommendation and conversation were usually treated as two separate modules with limited information exchange in existing works, which hinders the capability of both systems: (1) dialog merely incorporated recommendation entities without being guided by an explicit recommendation-oriented policy; (2) recommendation utilized dialog only as a form of interaction instead of improving recommendation effectively. To address the above issues, we propose a novel recommender dialog model: CR-Walker. In order to view the two separate systems within a unified framework, we seek high-level mapping between hierarchical dialog acts and multi-hop knowledge graph reasoning. The model walks on a large-scale knowledge graph to form a reasoning tree at each turn, then mapped to dialog acts to guide response generation. With such a mapping mechanism as a bridge between recommendation and conversation, our framework maximizes the mutual benefit between two systems: dialog as an enhancement to recommendation quality and explainability, recommendation as a goal and enrichment to dialog semantics. Quantitative evaluation shows that our model excels in conversation informativeness and recommendation effectiveness, at the same time explainable on the policy level.

MultiWOZ 2.3: A multi-domain task-oriented dataset enhanced with annotation corrections and co-reference annotation

Task-oriented dialogue systems have made unprecedented progress with multiple state-of-the-art (SOTA) models underpinned by a number of publicly available MultiWOZ datasets. Dialogue state annotations are error-prone, leading to sub-optimal performance. Various efforts have been put in rectifying the annotation errors presented in the original MultiWOZ dataset. In this paper, we introduce MultiWOZ 2.3, in which we differentiate incorrect annotations in dialogue acts from dialogue states, identifying a lack of co-reference when publishing the updated dataset. To ensure consistency between dialogue acts and dialogue states, we implement co-reference features and unify annotations of dialogue acts and dialogue states. We update the state of the art performance of natural language understanding and dialog state tracking on MultiWOZ 2.3, where the results show significant improvements than on previous versions of MultiWOZ datasets (2.0-2.2).

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a method called ARPER (Adaptively Regularized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on ElasticWeight Consolidation. Extensive experiments to continually learn new domains and intents are conducted on MultiWoZ-2.0 to benchmark ARPER with a wide range of techniques. Empirical results demonstrate that ARPER significantly outperforms other methods by effectively mitigating the detrimental catastrophic forgetting issue.

Stylized Dialogue Response Generation Using Stylized Unpaired Texts

Generating stylized responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when the target style is embedded only in unpaired texts that cannot be directly used to train the dialogue model. This paper proposes a stylized dialogue generation method that can capture stylistic features embedded in unpaired texts. Specifically, our method can produce dialogue responses that are both coherent to the given context and conform to the target style. In this study, an inverse dialogue model is first introduced to predict possible posts for the input responses, and then this inverse model is used to generate stylized pseudo dialogue pairs based on these stylized unpaired texts. Further, these pseudo pairs are employed to train the stylized dialogue model with a joint training process, and a style routing approach is proposed to intensify stylistic features in the decoder. Automatic and manual evaluations on two datasets demonstrate that our method outperforms competitive baselines in producing coherent and style-intensive dialogue responses.