We study a conversational reasoning model that strategically traverses through a largescale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes. For this study, we collect a new Open-ended Dialog ↔ KG parallel corpus called OpenDialKG, where each utterance from 15K human-to-human roleplaying dialogs is manually annotated with ground-truth reference to corresponding entities and paths from a large-scale KG with 1M+ facts. We then propose the DialKG Walker model that learns the symbolic transitions of dialog contexts as structured traversals over KG, and predicts natural entities to introduce given previous dialog contexts via a novel domain-agnostic, attention-based graph path decoder. Automatic and human evaluations show that our model can retrieve more natural and human-like responses than the state-ofthe-art baselines or rule-based models, in both in-domain and cross-domain tasks. The proposed model also generates a KG walk path for each entity retrieved, providing a natural way to explain conversational reasoning.

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-tosequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset. * Alphabetical by first name † Work done while on leave from Ohio State University 1 Also see https://ehudreiter.com/2018/11/ 12/hallucination-in-neural-nlg/. Reference 1 JJ's Pub is not family friendly, but has a high customer rating of 5 out of 5. It is a restaurant near the Crowne Plaza Hotel. Reference 2 JJ's Pub is not a family friendly restaurant. It has a high customer rating of 5 out of 5. You can find it near the Crowne Plaza Hotel. E2E MR name[JJ's Pub] rating[5 out of 5] familyFriendly[no] eatType[restaurant] near[Crowne Plaza Hotel] Our MR for Reference 1 CONTRAST [ INFORM [ name[JJ's Pub] familyFriendly[no] ] INFORM [ rating[5 out of 5] ] ] INFORM [ eatType[restaurant] near[Crowne Plaza Hotel] ]

This paper presents a first-order logic learning approach to determine rhetorical relations between discourse segments. Beyond linguistic cues and lexical information, our approach exploits compositional semantics and segment discourse structure data. We report a statistically significant improvement in classifying relations over attribute-value learning paradigms such as Decision Trees, RIP-PER and Naive Bayes. For discourse parsing, our modified shift-reduce parsing model that uses our relation classifier significantly outperforms a right-branching majority-class baseline.

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data.In this paper, we propose a slot description enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes dialogue context and slots with a pre-trained self-attentive encoder, and generates slot values in an auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information across slots to facilitate cross-domain knowledge transfer. Experimental results on the MultiWOZ dataset show that our proposed method significantly improves existing stateof-the-art results in the zero-shot cross-domain setting.

Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the crosstask knowledge from general question answering (QA) corpora for the zero-shot DST task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multichoice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation, which enable our model to handle "none" value slots in the zero-shot DST setting. The extensive experiments show that our approaches substantially improve the existing zero-shot and few-shot results on MultiWoz. Moreover, compared to the fully trained baseline on the Schema-Guided Dialogue dataset, our approach shows better generalization ability in unseen domains.