Related papers: Structured Dialogue Discourse Parsing
Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures,…
Existing neural models for dialogue response generation assume that utterances are sequentially organized. However, many real-world dialogues involve multiple interlocutors (i.e., multi-party dialogues), where the assumption does not hold…
To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the…
Recently, there is rising interest in modelling the interactions of two sentences with deep neural networks. However, most of the existing methods encode two sequences with separate encoders, in which a sentence is encoded with little or no…
Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…
Predicting the structure of a discourse is challenging because relations between discourse segments are often implicit and thus hard to distinguish computationally. I extend previous work to classify implicit discourse relations by…
Language models generate reasoning sequentially, preventing them from decoupling irrelevant exploration paths during search. We introduce Tree-Structured Language Modeling (TSLM), which uses special tokens to encode branching structure,…
A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts and opinions. As sentences are normally consist of multiple text segments, correct understanding of the theme of a…
Nowadays, with the booming development of the Internet, people benefit from its convenience due to its open and sharing nature. A large volume of natural language texts is being generated by users in various forms, such as search queries,…
Neural dialog models have exhibited strong performance, however their end-to-end nature lacks a representation of the explicit structure of dialog. This results in a loss of generalizability, controllability and a data-hungry nature.…
Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which…
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…
The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sentences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We introduce both a…
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic…
With a growing number of BERTology work analyzing different components of pre-trained language models, we extend this line of research through an in-depth analysis of discourse information in pre-trained and fine-tuned language models. We…
Dialogue policies play a crucial role in developing task-oriented dialogue systems, yet their development and maintenance are challenging and typically require substantial effort from experts in dialogue modeling. While in many situations,…
Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these…
How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an…
Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…
Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history. Most existing works primarily focus on post-training and fine-tuning tailored for cross-encoders.…