In this paper, we describe our systems for solving the two Doc2Dial shared task: knowledge identification and response generation. We proposed several pre-processing and post-processing methods, and we experimented with data augmentation by pre-training the models on other relevant datasets. Our best model for knowledge identification outperformed the baseline by 10.5+ f1-score on the test-dev split, and our best model for response generation outperformed the baseline by 11+ Sacrebleu score on the test-dev split.
Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training. Recent works only propose lightweight model updates as models may already possess useful knowledge from past experience, but a challenge remains in understanding what parts and to what extent models should be refined for a given task. In this paper, we investigate what models learn from commonsense reasoning datasets. We measure the impact of three different adaptation methods on the generalization and accuracy of models. Our experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers. We observe that alternative adaptation methods like prefix-tuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.
The field of question answering (QA) has seen rapid growth in new tasks and modeling approaches in recent years. Large scale datasets and focus on challenging linguistic phenomena have driven development in neural models, some of which have achieved parity with human performance in limited cases. However, an examination of state-of-the-art model output reveals that a gap remains in reasoning ability compared to a human, and performance tends to degrade when models are exposed to less-constrained tasks. We are interested in more clearly defining the strengths and limitations of leading models across diverse QA challenges, intending to help future researchers with identifying pathways to generalizable performance. We conduct extensive qualitative and quantitative analyses on the results of four models across four datasets and relate common errors to model capabilities. We also illustrate limitations in the datasets we examine and discuss a way forward for achieving generalizable models and datasets that broadly test QA capabilities.
Non-extractive commonsense QA remains a challenging AI task, as it requires systems to reason about, synthesize, and gather disparate pieces of information, in order to generate responses to queries. Recent approaches on such tasks show increased performance, only when models are either pre-trained with additional information or when domain-specific heuristics are used, without any special consideration regarding the knowledge resource type. In this paper, we perform a survey of recent commonsense QA methods and we provide a systematic analysis of popular knowledge resources and knowledge-integration methods, across benchmarks from multiple commonsense datasets. Our results and analysis show that attention-based injection seems to be a preferable choice for knowledge integration and that the degree of domain overlap, between knowledge bases and datasets, plays a crucial role in determining model success.
This paper presents a new corpus and a robust deep learning architecture for a task in reading comprehension, passage completion, on multiparty dialog. Given a dialog in text and a passage containing factual descriptions about the dialog where mentions of the characters are replaced by blanks, the task is to fill the blanks with the most appropriate character names that reflect the contexts in the dialog. Since there is no dataset that challenges the task of passage completion in this genre, we create a corpus by selecting transcripts from a TV show that comprise 1,681 dialogs, generating passages for each dialog through crowdsourcing, and annotating mentions of characters in both the dialog and the passages. Given this dataset, we build a deep neural model that integrates rich feature extraction from convolutional neural networks into sequence modeling in recurrent neural networks, optimized by utterance and dialog level attentions. Our model outperforms the previous state-of-the-art model on this task in a different genre using bidirectional LSTM, showing a 13.0+% improvement for longer dialogs. Our analysis shows the effectiveness of the attention mechanisms and suggests a direction to machine comprehension on multiparty dialog.