Towards Socially Intelligent Agents with Mental State Transition and Human Utility

Building a socially intelligent agent involves many challenges, one of which is to track the agent's mental state transition and teach the agent to make rational decisions guided by its utility like a human. Towards this end, we propose to incorporate a mental state parser and utility model into dialogue agents. The hybrid mental state parser extracts information from both the dialogue and event observations and maintains a graphical representation of the agent's mind; Meanwhile, the utility model is a ranking model that learns human preferences from a crowd-sourced social commonsense dataset, Social IQA. Empirical results show that the proposed model attains state-of-the-art performance on the dialogue/action/emotion prediction task in the fantasy text-adventure game dataset, LIGHT. We also show example cases to demonstrate: (\textit{i}) how the proposed mental state parser can assist agent's decision by grounding on the context like locations and objects, and (\textit{ii}) how the utility model can help the agent make reasonable decisions in a dilemma. To the best of our knowledge, we are the first work that builds a socially intelligent agent by incorporating a hybrid mental state parser for both discrete events and continuous dialogues parsing and human-like utility modeling.

ChainCQG: Flow-Aware Conversational Question Generation

Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these. However, conversational question-answering remains challenging due to the lack of realistic, domain-specific training data. Inspired by this bottleneck, we focus on conversational question generation as a means to generate synthetic conversations for training and evaluation purposes. We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. Specifically, we design ChainCQG as a two-stage architecture that learns question-answer representations across multiple dialogue turns using a flow propagation training strategy.ChainCQG significantly outperforms both answer-aware and answer-unaware SOTA baselines (e.g., up to 48% BLEU-1 improvement). Additionally, our model is able to generate different types of questions, with improved fluidity and coreference alignment.

Continual Learning in Task-Oriented Dialogue Systems

Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings, such as intent recognition, state tracking, natural language generation, and end-to-end. Moreover, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform comparably well but they both achieve inferior performance to the multi-task learning baseline, in where all the data are shown at once, showing that continual learning in task-oriented dialogue systems is a challenging task. Furthermore, we reveal several trade-offs between different continual learning methods in term of parameter usage and memory size, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released together with several baselines to promote more research in this direction.

Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

Despite the recent success of large-scale language models on various downstream NLP tasks, the repetition and inconsistency problems still persist in dialogue response generation. Previous approaches have attempted to avoid repetition by penalizing the language model's undesirable behaviors in the loss function. However, these methods focus on token-level information and can lead to incoherent responses and uninterpretable behaviors. To alleviate these issues, we propose to apply reinforcement learning to refine an MLE-based language model without user simulators, and distill sentence-level information about repetition, inconsistency and task relevance through rewards. In addition, to better accomplish the dialogue task, the model learns from human demonstration to imitate intellectual activities such as persuasion, and selects the most persuasive responses. Experiments show that our model outperforms previous state-of-the-art dialogue models on both automatic metrics and human evaluation results on a donation persuasion task, and generates more diverse, consistent and persuasive conversations according to the user feedback.

Gunrock 2.0: A User Adaptive Social Conversational System

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understanding. Its dialog management is a hierarchical model that handles various topics, such as movies, music, and sports. The system-level dialog manager can handle question detection, acknowledgment, error handling, and additional functions, making downstream modules much easier to design and implement. The dialog manager also adapts its topic selection to accommodate different users' profile information, such as inferred gender and personality. The generation model is a mix of templates and neural generation models. Gunrock 2.0 is able to achieve an average rating of 3.73 at its latest build from May 29th to June 4th.

Memformer: The Memory-Augmented Transformer

Transformer models have obtained remarkable accomplishments in various NLP tasks. However, these models have efficiency issues on long sequences, as the complexity of their self-attention module scales quadratically with the sequence length. To remedy the limitation, we present Memformer, a novel language model that utilizes a single unified memory to encode and retrieve past information. It includes a new optimization scheme, Memory Replay Back-Propagation, which promotes long-range back-propagation through time with a significantly reduced memory requirement. Memformer achieves $\mathcal{O}(n)$ time complexity and $\mathcal{O}(1)$ space complexity in processing long sequences, meaning that the model can handle an infinite length sequence during inference. Our model is also compatible with other self-supervised tasks to further improve the performance on language modeling. Experimental results show that Memformer outperforms the previous long-range sequence models on WikiText-103, including Transformer-XL and compressive Transformer.

Structured Attention for Unsupervised Dialogue Structure Induction

Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics. Advancement made in this area is critical for dialogue system design and discourse analysis. It can also be extended to solve grammatical inference. In this work, we propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias. Experiments show that on two-party dialogue datasets, VRNN with structured attention learns semantic structures that are similar to templates used to generate this dialogue corpus. While on multi-party dialogue datasets, our model learns an interactive structure demonstrating its capability of distinguishing speakers or addresses, automatically disentangling dialogues without explicit human annotation.

INSPIRED: Toward Sociable Recommendation Dialog Systems

In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge when developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated with such sociable strategies. Therefore, we present INSPIRED, a new dataset of 1,001 human-human dialogs for movie recommendation with measures for successful recommendations. To better understand how humans make recommendations in communication, we design an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs. Our analysis shows that sociable recommendation strategies, such as sharing personal opinions or communicating with encouragement, more frequently lead to successful recommendations. Based on our dataset, we train end-to-end recommendation dialog systems with and without our strategy labels. In both automatic and human evaluation, our model with strategy incorporation outperforms the baseline model. This work is a first step for building sociable recommendation dialog systems with a basis of social science theories.

Code to Comment "Translation": Data, Metrics, Baselining & Evaluation

The relationship of comments to code, and in particular, the task of generating useful comments given the code, has long been of interest. The earliest approaches have been based on strong syntactic theories of comment-structures, and relied on textual templates. More recently, researchers have applied deep learning methods to this task, and specifically, trainable generative translation models which are known to work very well for Natural Language translation (e.g., from German to English). We carefully examine the underlying assumption here: that the task of generating comments sufficiently resembles the task of translating between natural languages, and so similar models and evaluation metrics could be used. We analyze several recent code-comment datasets for this task: CodeNN, DeepCom, FunCom, and DocString. We compare them with WMT19, a standard dataset frequently used to train state of the art natural language translators. We found some interesting differences between the code-comment data and the WMT19 natural language data. Next, we describe and conduct some studies to calibrate BLEU (which is commonly used as a measure of comment quality). using "affinity pairs" of methods, from different projects, in the same project, in the same class, etc; Our study suggests that the current performance on some datasets might need to be improved substantially. We also argue that fairly naive information retrieval (IR) methods do well enough at this task to be considered a reasonable baseline. Finally, we make some suggestions on how our findings might be used in future research in this area.

ALICE: Active Learning with Contrastive Natural Language Explanations

Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine communication interface: classification labels, each of which only provides several bits of information. We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning. ALICE learns to first use active learning to select the most informative pairs of label classes to elicit contrastive natural language explanations from experts. Then it extracts knowledge from these explanations using a semantic parser. Finally, it incorporates the extracted knowledge through dynamically changing the learning model's structure. We applied ALICE in two visual recognition tasks, bird species classification and social relationship classification. We found by incorporating contrastive explanations, our models outperform baseline models that are trained with 40-100% more training data. We found that adding 1 explanation leads to similar performance gain as adding 13-30 labeled training data points.