Transformer-based open-domain dialog models have become increasingly popular in recent years. These models typically represent context as a concatenation of a dialog history. However, there is no criterion to decide how many utterances should be kept adequate in a context. We try to figure out how the choice of context length affects the model. We experiment on three questions from coarse to fine: (i) Does longer context help model training? (ii) Is it necessary to change the training context length when dealing with dialogs of different context lengths? (iii) Do different dialog samples have the same preference for context length? Our experimental results show that context length, an often overlooked setting, deserves attention when implementing Transformer-based dialog models.
Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made on the prior distribution is incompatible with these distributions, thus restricting the diversity of generated responses. These models also suffer from posterior collapse, i.e., the decoder tends to ignore latent variables and directly access information captured in the encoder through the cross-attention mechanism. In this work, we propose Dior-CVAE, a hierarchical conditional variational autoencoder (CVAE) with diffusion priors to address these challenges. We employ a diffusion model to increase the complexity of the prior distribution and its compatibility with the distributions produced by a PLM. Also, we propose memory dropout to the cross-attention mechanism, which actively encourages the use of latent variables for response generation. Overall, experiments across two commonly used open-domain dialog datasets show that our method can generate more diverse responses without large-scale dialog pre-training. Code is available at https://github.com/UKPLab/dior-cvae.
Automatic evaluation of open-domain dialogs remains an unsolved problem. Moreover, existing methods do not correlate strongly with human annotations. This paper presents a new automated evaluation method using follow-ups: we measure the probability that a language model will continue the conversation with a fixed set of follow-ups (e.g., not really relevant here, what are you trying to say). When compared against twelve existing methods, our new evaluation achieves the highest correlation with human evaluations.
As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-parametric memory allows models to grow dramatically with a sub-linear increase in computational cost and GPU memory requirements. Recent models such as RAG and REALM have introduced retrieval into conditional generation. These models incorporate neural initial retrieval from a corpus of passages. We build on this line of research, proposing Re2G, which combines both neural initial retrieval and reranking into a BART-based sequence-to-sequence generation. Our reranking approach also permits merging retrieval results from sources with incomparable scores, enabling an ensemble of BM25 and neural initial retrieval. To train our system end-to-end, we introduce a novel variation of knowledge distillation to train the initial retrieval, reranker, and generation using only ground truth on the target sequence output. We find large gains in four diverse tasks: zero-shot slot filling, question answering, fact-checking, and dialog, with relative gains of 9% to 34% over the previous state-of-the-art on the KILT leaderboard. We make our code available as open source at https://github.com/IBM/kgi-slot-filling/tree/re2g.
We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog. In contrast with earlier models such as DialoGPT, GODEL leverages a new phase of grounded pre-training designed to better support adapting GODEL to a wide range of downstream dialog tasks that require information external to the current conversation (e.g., a database or document) to produce good responses. Experiments against an array of benchmarks that encompass task-oriented dialog, conversational QA, and grounded open-domain dialog show that GODEL outperforms state-of-the-art pre-trained dialog models in few-shot fine-tuning setups, in terms of both human and automatic evaluation. A novel feature of our evaluation methodology is the introduction of a notion of utility that assesses the usefulness of responses (extrinsic evaluation) in addition to their communicative features (intrinsic evaluation). We show that extrinsic evaluation offers improved inter-annotator agreement and correlation with automated metrics. Code and data processing scripts are publicly available.
Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers' personalities and emotions after cognitive processing have an important influence on conversation. However, most existing datasets for conversational AI ignore human personalities and emotions, or only consider part of them. It's difficult for dialogue systems to understand speakers' personalities and emotions although large-scale pre-training language models have been widely used. In order to consider both personalities and emotions in the process of conversation generation, we propose CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic. These knowledge covers gender, Big Five personality traits, 13 emotions, 19 dialogue acts and 10 scenes. CPED contains more than 12K dialogues of 392 speakers from 40 TV shows. We release the textual dataset with audio features and video features according to the copyright claims, privacy issues, terms of service of video platforms. We provide detailed description of the CPED construction process and introduce three tasks for conversational AI, including personality recognition, emotion recognition in conversations as well as personalized and emotional conversation generation. Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation. Our motivation is to propose a dataset to be widely adopted by the NLP community as a new open benchmark for conversational AI research. The full dataset is available at https://github.com/scutcyr/CPED.
Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zero-shot performance on unseen tasks. Instructions have been shown to enable good performance on unseen tasks and datasets in both large and small language models. Dialogue is an especially interesting area to explore instruction tuning because dialogue systems perform multiple kinds of tasks related to language (e.g., natural language understanding and generation, domain-specific interaction), yet instruction tuning has not been systematically explored for dialogue-related tasks. We introduce InstructDial, an instruction tuning framework for dialogue, which consists of a repository of 48 diverse dialogue tasks in a unified text-to-text format created from 59 openly available dialogue datasets. Next, we explore cross-task generalization ability on models tuned on InstructDial across diverse dialogue tasks. Our analysis reveals that InstructDial enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection, and even better performance in a few-shot setting. To ensure that models adhere to instructions, we introduce novel meta-tasks. We establish benchmark zero-shot and few-shot performance of models trained using the proposed framework on multiple dialogue tasks.
Accurate automatic evaluation metrics for open-domain dialogs are in high demand. Existing model-based metrics for system response evaluation are trained on human annotated data, which is cumbersome to collect. In this work, we propose to use information that can be automatically extracted from the next user utterance, such as its sentiment or whether the user explicitly ends the conversation, as a proxy to measure the quality of the previous system response. This allows us to train on a massive set of dialogs with weak supervision, without requiring manual system turn quality annotations. Experiments show that our model is comparable to models trained on human annotated data. Furthermore, our model generalizes across both spoken and written open-domain dialog corpora collected from real and paid users.
Humans often employ figurative language use in communication, including during interactions with dialog systems. Thus, it is important for real-world dialog systems to be able to handle popular figurative language constructs like metaphor and simile. In this work, we analyze the performance of existing dialog models in situations where the input dialog context exhibits use of figurative language. We observe large gaps in handling of figurative language when evaluating the models on two open domain dialog datasets. When faced with dialog contexts consisting of figurative language, some models show very large drops in performance compared to contexts without figurative language. We encourage future research in dialog modeling to separately analyze and report results on figurative language in order to better test model capabilities relevant to real-world use. Finally, we propose lightweight solutions to help existing models become more robust to figurative language by simply using an external resource to translate figurative language to literal (non-figurative) forms while preserving the meaning to the best extent possible.
In transfer learning, it is imperative to achieve strong alignment between a pre-trained model and a downstream task. Prior work has done this by proposing task-specific pre-training objectives, which sacrifices the inherent scalability of the transfer learning paradigm. We instead achieve strong alignment by simultaneously modifying both the pre-trained model and the formulation of the downstream task, which is more efficient and preserves the scalability of transfer learning. We present GenSF (Generative Slot Filling), which leverages a generative pre-trained open-domain dialog model for slot filling. GenSF (1) adapts the pre-trained model by incorporating inductive biases about the task and (2) adapts the downstream task by reformulating slot filling to better leverage the pre-trained model's capabilities. GenSF achieves state-of-the-art results on two slot filling datasets with strong gains in few-shot and zero-shot settings. We achieve a 9 F1 score improvement in zero-shot slot filling. This highlights the value of strong alignment between the pre-trained model and the downstream task.
Multiple different responses are often plausible for a given open domain dialog context. Prior work has shown the importance of having multiple valid reference responses for meaningful and robust automated evaluations. In such cases, common practice has been to collect more human written references. However, such collection can be expensive, time consuming, and not easily scalable. Instead, we propose a novel technique for automatically expanding a human generated reference to a set of candidate references. We fetch plausible references from knowledge sources, and adapt them so that they are more fluent in context of the dialog instance in question. More specifically, we use (1) a commonsense knowledge base to elicit a large number of plausible reactions given the dialog history (2) relevant instances retrieved from dialog corpus, using similar past as well as future contexts. We demonstrate that our automatically expanded reference sets lead to large improvements in correlations of automated metrics with human ratings of system outputs for DailyDialog dataset.
Open-domain dialog systems have a user-centric goal: to provide humans with an engaging conversation experience. User engagement is one of the most important metrics for evaluating open-domain dialog systems, and could also be used as real-time feedback to benefit dialog policy learning. Existing work on detecting user disengagement typically requires hand-labeling many dialog samples. We propose HERALD, an efficient annotation framework that reframes the training data annotation process as a denoising problem. Specifically, instead of manually labeling training samples, we first use a set of labeling heuristics to label training samples automatically. We then denoise the weakly labeled data using the Shapley algorithm. Finally, we use the denoised data to train a user engagement detector. Our experiments show that HERALD improves annotation efficiency significantly and achieves 86% user disengagement detection accuracy in two dialog corpora.
The capacity of empathy is crucial to the success of open-domain dialog systems. Due to its nature of multi-dimensionality, there are various factors that relate to empathy expression, such as communication mechanism, dialog act and emotion. However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling. In this paper, we propose a multi-factor hierarchical framework, CoMAE, for empathetic response generation, which models the above three key factors of empathy expression in a hierarchical way. We show experimentally that our CoMAE-based model can generate more empathetic responses than previous methods. We also highlight the importance of hierarchical modeling of different factors through both the empirical analysis on a real-life corpus and the extensive experiments. Our codes and used data are available at https://github.com/chujiezheng/CoMAE.
Now, the pre-training technique is ubiquitous in natural language processing field. ProphetNet is a pre-training based natural language generation method which shows powerful performance on English text summarization and question generation tasks. In this paper, we extend ProphetNet into other domains and languages, and present the ProphetNet family pre-training models, named ProphetNet-X, where X can be English, Chinese, Multi-lingual, and so on. We pre-train a cross-lingual generation model ProphetNet-Multi, a Chinese generation model ProphetNet-Zh, two open-domain dialog generation models ProphetNet-Dialog-En and ProphetNet-Dialog-Zh. And also, we provide a PLG (Programming Language Generation) model ProphetNet-Code to show the generation performance besides NLG (Natural Language Generation) tasks. In our experiments, ProphetNet-X models achieve new state-of-the-art performance on 10 benchmarks. All the models of ProphetNet-X share the same model structure, which allows users to easily switch between different models. We make the code and models publicly available, and we will keep updating more pre-training models and finetuning scripts.
The task of long-form question answering (LFQA) involves retrieving documents relevant to a given question and using them to generate a paragraph-length answer. While many models have recently been proposed for LFQA, we show in this paper that the task formulation raises fundamental challenges regarding evaluation and dataset creation that currently preclude meaningful modeling progress. To demonstrate these challenges, we first design a new system that relies on sparse attention and contrastive retriever learning to achieve state-of-the-art performance on the ELI5 LFQA dataset. While our system tops the public leaderboard, a detailed analysis reveals several troubling trends: (1) our system's generated answers are not actually grounded in the documents that it retrieves; (2) ELI5 contains significant train / validation overlap, as at least 81% of ELI5 validation questions occur in paraphrased form in the training set; (3) ROUGE-L is not an informative metric of generated answer quality and can be easily gamed; and (4) human evaluations used for other text generation tasks are unreliable for LFQA. We offer suggestions to mitigate each of these issues, which we hope will lead to more rigorous LFQA research and meaningful progress in the future.
Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is difficult as each task might require computationally expensive indexing of custom knowledge sources, in addition to dedicated infrastructure. To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures. We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance. We find that a shared dense vector index coupled with a seq2seq model is a strong baseline, outperforming more tailor-made approaches for fact checking, open-domain question answering and dialogue, and yielding competitive results on entity linking and slot filling, by generating disambiguated text. KILT data and code are available at https://github.com/facebookresearch/KILT.
Large end-to-end neural open-domain chatbots are becoming increasingly popular. However, research on building such chatbots has typically assumed that the user input is written in nature and it is not clear whether these chatbots would seamlessly integrate with automatic speech recognition (ASR) models to serve the speech modality. We aim to bring attention to this important question by empirically studying the effects of various types of synthetic and actual ASR hypotheses in the dialog history on TransferTransfo, a state-of-the-art Generative Pre-trained Transformer (GPT) based neural open-domain dialog system from the NeurIPS ConvAI2 challenge. We observe that TransferTransfo trained on written data is very sensitive to such hypotheses introduced to the dialog history during inference time. As a baseline mitigation strategy, we introduce synthetic ASR hypotheses to the dialog history during training and observe marginal improvements, demonstrating the need for further research into techniques to make end-to-end open-domain chatbots fully speech-robust. To the best of our knowledge, this is the first study to evaluate the effects of synthetic and actual ASR hypotheses on a state-of-the-art neural open-domain dialog system and we hope it promotes speech-robustness as an evaluation criterion in open-domain dialog.
It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research. Standard language generation metrics have been shown to be ineffective for dialog. This paper introduces the FED metric (fine-grained evaluation of dialog), an automatic evaluation metric which uses DialoGPT, without any fine-tuning or supervision. It also introduces the FED dataset which is constructed by annotating a set of human-system and human-human conversations with eighteen fine-grained dialog qualities. The FED metric (1) does not rely on a ground-truth response, (2) does not require training data and (3) measures fine-grained dialog qualities at both the turn and whole dialog levels. FED attains moderate to strong correlation with human judgement at both levels.
The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in dialog. In this study, we analyze the internal representations learned by neural open-domain dialog systems and evaluate the quality of these representations for learning basic conversational skills. Our results suggest that standard open-domain dialog systems struggle with answering questions, inferring contradiction, and determining the topic of conversation, among other tasks. We also find that the dyadic, turn-taking nature of dialog is not fully leveraged by these models. By exploring these limitations, we highlight the need for additional research into architectures and training methods that can better capture high-level information about dialog.
Open Domain dialog system evaluation is one of the most important challenges in dialog research. Existing automatic evaluation metrics, such as BLEU are mostly reference-based. They calculate the difference between the generated response and a limited number of available references. Likert-score based self-reported user rating is widely adopted by social conversational systems, such as Amazon Alexa Prize chatbots. However, self-reported user rating suffers from bias and variance among different users. To alleviate this problem, we formulate dialog evaluation as a comparison task. We also propose an automatic evaluation model CMADE (Comparison Model for Automatic Dialog Evaluation) that automatically cleans self-reported user ratings as it trains on them. Specifically, we first use a self-supervised method to learn better dialog feature representation, and then use KNN and Shapley to remove confusing samples. Our experiments show that CMADE achieves 89.2% accuracy in the dialog comparison task.