Related papers: Sentence-level Event Detection without Triggers vi…
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step,…
In this paper, we introduce an event-driven trading strategy that predicts stock movements by detecting corporate events from news articles. Unlike existing models that utilize textual features (e.g., bag-of-words) and sentiments to…
Event extraction involves the detection and extraction of both the event triggers and corresponding event arguments. Existing systems often decompose event extraction into multiple subtasks, without considering their possible interactions.…
An important task for designing QA systems is answer sentence selection (AS2): selecting the sentence containing (or constituting) the answer to a question from a set of retrieved relevant documents. In this paper, we propose three novel…
LLM-based conversational systems have become a popular gateway for information access, yet most existing chatbots struggle to handle news-related trending queries effectively. To improve user experience, an effective trending query…
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token…
We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models,…
[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize…
Automatic extraction of temporal relations between event pairs is an important task for several natural language processing applications such as Question Answering, Information Extraction, and Summarization. Since most existing methods are…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…
We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…
With the rapid progress of large language models (LLMs) and the huge amount of text they generated, it becomes more and more impractical to manually distinguish whether a text is machine-generated. Given the growing use of LLMs in social…
In this paper we introduce a method to detect words or phrases in a given sequence of alphabets without knowing the lexicon. Our linear time unsupervised algorithm relies entirely on statistical relationships among alphabets in the input…
We present an architecture for voice trigger detection for virtual assistants. The main idea in this work is to exploit information in words that immediately follow the trigger phrase. We first demonstrate that by including more audio…
Sentence-level relation extraction aims to identify the relation between two entities for a given sentence. The existing works mostly focus on obtaining a better entity representation and adopting a multi-label classifier for relation…
Recall the classical text generation works, the generation framework can be briefly divided into two phases: \textbf{idea reasoning} and \textbf{surface realization}. The target of idea reasoning is to figure out the main idea which will be…
In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of…
Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on…
Social media is becoming a primary medium to discuss what is happening around the world. Therefore, the data generated by social media platforms contain rich information which describes the ongoing events. Further, the timeliness associated…
Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…