Related papers: Annotation-Inspired Implicit Discourse Relation Cl…
Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…
Implicit Discourse Relation Recognition (IDRR) aims at classifying the relation sense between two arguments without an explicit connective. Recently, the ConnPrompt~\cite{Wei.X:et.al:2022:COLING} has leveraged the powerful prompt learning…
Natural language processing has greatly benefited from the introduction of the attention mechanism. However, standard attention models are of limited interpretability for tasks that involve a series of inference steps. We describe an…
Relation extraction models suffer from limited qualified training data. Using human annotators to label sentences is too expensive and does not scale well especially when dealing with large datasets. In this paper, we use Auxiliary…
Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document…
The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the context of large language models automating people-sensitive…
Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon…
Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain…
Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. We propose to train models for…
With a growing need for robust and general discourse structures in many downstream tasks and real-world applications, the current lack of high-quality, high-quantity discourse trees poses a severe shortcoming. In order the alleviate this…
Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a…
Response generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm of adapting such extremely large…
Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…
Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the…
This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a…
Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and…
Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…
Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this paper, we present…
Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language models (LLMs), excel at capturing semantic correlations within…
Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…