Related papers: On the Importance of Word and Sentence Representat…
Recent models for unsupervised representation learning of text have employed a number of techniques to improve contextual word representations but have put little focus on discourse-level representations. We propose CONPONO, an…
This paper introduces the first multi-lingual and multi-label classification model for implicit discourse relation recognition (IDRR). Our model, HArch, is evaluated on the recently released DiscoGeM 2.0 corpus and leverages hierarchical…
In recent years, more research has been devoted to studying the subtask of the complete shallow discourse parsing, such as indentifying discourse connective and arguments of connective. There is a need to design a full discourse parser to…
Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis. Most of the current work adopted multi-task learning to aid IDRR through explicit discourse…
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom or top-level…
Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by…
Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words.…
Marrying topic models and language models exposes language understanding to a broader source of document-level context beyond sentences via topics. While introducing topical semantics in language models, existing approaches incorporate…
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…
Although pre-trained contextualized language models such as BERT achieve significant performance on various downstream tasks, current language representation still only focuses on linguistic objective at a specific granularity, which may…
Discourse relation classification is an especially difficult task without explicit context markers (Prasad et al., 2008). Current approaches to implicit relation prediction solely rely on two neighboring sentences being targeted, ignoring…
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…
In the era of digitalization, as individuals increasingly rely on digital platforms for communication and news consumption, various actors employ linguistic strategies to influence public perception. While models have become proficient at…
Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…
Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…
Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis. The critical step for IDRR is to learn high-quality discourse relation representations between two…
Online discourse is often perceived as polarized and unproductive. While some conversational discourse parsing frameworks are available, they do not naturally lend themselves to the analysis of contentious and polarizing discussions.…
Despite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet limited. In this…
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text…
Discourse structures are beneficial for various NLP tasks such as dialogue understanding, question answering, sentiment analysis, and so on. This paper presents a deep sequential model for parsing discourse dependency structures of…