Related papers: Event Presence Prediction Helps Trigger Detection …

Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes their joint modeling a standard part of training such…

A sound event detection (SED) method typically takes as an input a sequence of audio frames and predicts the activities of sound events in each frame. In real-life recordings, the sound events exhibit some temporal structure: for instance,…

Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word…

In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance on downstream tasks…

Event temporal relation extraction~(ETRE) is usually formulated as a multi-label classification task, where each type of relation is simply treated as a one-hot label. This formulation ignores the meaning of relations and wipes out their…

Event Extraction (EE), aiming to identify and classify event triggers and arguments from event mentions, has benefited from pre-trained language models (PLMs). However, existing PLM-based methods ignore the information of trigger/argument…

Electronic Health Records are large repositories of valuable clinical data, with a significant portion stored in unstructured text format. This textual data includes clinical events (e.g., disorders, symptoms, findings, medications and…

Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…

Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the…

In the domain of time series analysis, particularly in event detection tasks, current methodologies predominantly rely on segmentation-based approaches, which predict the class label for each individual timesteps and use the changepoints of…

Extracting the reported events from text is one of the key research themes in natural language processing. This process includes several tasks such as event detection, argument extraction, role labeling. As one of the most important topics…

We present a context aware object detection method based on a retrieve-and-transform scene layout model. Given an input image, our approach first retrieves a coarse scene layout from a codebook of typical layout templates. In order to…

Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. However, modeling human language at higher-levels of context…

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

An important task for the design of Question Answering systems is the selection of the sentence containing (or constituting) the answer from documents relevant to the asked question. Most previous work has only used the target sentence to…

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random…

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…

Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding…