Related papers: FrameBERT: Conceptual Metaphor Detection with Fram…
The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa…
Frame Semantic Role Labeling (FSRL) identifies arguments and labels them with frame semantic roles defined in FrameNet. Previous researches tend to divide FSRL into argument identification and role classification. Such methods usually model…
FrameNet is a computational linguistics resource composed of semantic frames, high-level concepts that represent the meanings of words. In this paper, we present an approach to gather frame disambiguation annotations in sentences using a…
Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words…
Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…
We introduce Conceptual Metaphor Theory (CMT) as a framework for enhancing large language models (LLMs) through cognitive prompting in complex reasoning tasks. CMT leverages metaphorical mappings to structure abstract reasoning, improving…
Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While understanding linguistic metaphors has advanced significantly, grasping multimodal metaphors, such as…
We present two deep learning approaches to narrative text understanding for character relationship modelling. The temporal evolution of these relations is described by dynamic word embeddings, that are designed to learn semantic changes…
Semantic segmentation is a computer vision task that associates a label with each pixel in an image. Modern approaches tend to introduce class embeddings into semantic segmentation for deeply utilizing category semantics, and regard…
Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…
We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings. The results of our experiments in the domain specific…
We present end-to-end neural models for detecting metaphorical word use in context. We show that relatively standard BiLSTM models which operate on complete sentences work well in this setting, in comparison to previous work that used more…
Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…
In most cases, word embeddings are learned only from raw tokens or in some cases, lemmas. This includes pre-trained language models like BERT. To investigate on the potential of capturing deeper relations between lexical items and…
Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…
Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…
This paper presents Amnestic Forgery, an ontology for metaphor semantics, based on MetaNet, which is inspired by the theory of Conceptual Metaphor. Amnestic Forgery reuses and extends the Framester schema, as an ideal ontology design…
We introduce an extensive dataset for multilingual probing of morphological information in language models (247 tasks across 42 languages from 10 families), each consisting of a sentence with a target word and a morphological tag as the…
Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…
We present a resource for the task of FrameNet semantic frame disambiguation of over 5,000 word-sentence pairs from the Wikipedia corpus. The annotations were collected using a novel crowdsourcing approach with multiple workers per sentence…