Related papers: Semi-supervised News Discourse Profiling with Cont…
We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs. Our key observation is that the functional roles of sentences used for profiling news discourse signify…
Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives high-quality sentence…
Informational bias is widely present in news articles. It refers to providing one-sided, selective or suggestive information of specific aspects of certain entity to guide a specific interpretation, thereby biasing the reader's opinion.…
We propose a self-supervised learning method for long text documents based on contrastive learning. A key to our method is Shuffle and Divide (SaD), a simple text augmentation algorithm that sets up a pretext task required for contrastive…
Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience.…
Most event extraction methods have traditionally relied on an annotated set of event types. However, creating event ontologies and annotating supervised training data are expensive and time-consuming. Previous work has proposed…
Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constraint brought by this assumption is weak, and a good sentence…
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined…
Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with…
Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most…
Disinformation is often presented in long textual articles, especially when it relates to domains such as health, often seen in relation to COVID-19. These articles are typically observed to have a number of trustworthy sentences among…
Scientific articles are long text documents organized into sections, each describing aspects of the research. Analyzing scientific production has become progressively challenging due to the increase in the number of available articles.…
Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…
We address an important gap in detecting political bias in news articles. Previous works that perform document classification can be influenced by the writing style of each news outlet, leading to overfitting and limited generalizability.…
Discourse parsing could not yet take full advantage of the neural NLP revolution, mostly due to the lack of annotated datasets. We propose a novel approach that uses distant supervision on an auxiliary task (sentiment classification), to…
Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this work, we perform an extensive analysis on sentence-level…
The widely studied task of Natural Language Inference (NLI) requires a system to recognize whether one piece of text is textually entailed by another, i.e. whether the entirety of its meaning can be inferred from the other. In current NLI…
Researchers and financial professionals require robust computerized tools that allow users to rapidly operationalize and assess the semantic textual content in financial news. However, existing methods commonly work at the document-level…
The evaluation of cross-lingual semantic search models is often limited to existing datasets from tasks such as information retrieval and semantic textual similarity. We introduce Cross-Lingual Semantic Discrimination (CLSD), a lightweight…
In this paper, we revisit the challenging problem of unsupervised single-document summarization and study the following aspects: Integer linear programming (ILP) based algorithms, Parameterized normalization of term and sentence scores, and…