相关论文: Using textual clues to improve metaphor processing

Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects. In particular, a great deal of semantic information is carried in the relationships between objects. We have…

Metaphors are part of everyday language and shape the way in which we conceptualize the world. Moreover, they play a multifaceted role in communication, making their understanding and generation a challenging task for language models (LMs).…

The ability to compare the semantic similarity between text corpora is important in a variety of natural language processing applications. However, standard methods for evaluating these metrics have yet to be established. We propose a set…

In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text token…

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Large Vision-Language Models (VLMs) have demonstrated strong capabilities in tasks requiring a fine-grained understanding of literal meaning in images and text, such as visual question-answering or visual entailment. However, there has been…

We propose a benchmark to assess the capability of large language models to reason with conventional metaphors. Our benchmark combines the previously isolated topics of metaphor detection and commonsense reasoning into a single task that…

Metaphorical meaning is not a flat mapping between concepts, but a complex cognitive phenomenon that integrates multiple levels of interpretation. In this paper, we propose a stratified model of metaphor processing that treats meaning as an…

We address here the treatment of metonymic expressions from a knowledge representation perspective, that is, in the context of a text understanding system which aims to build a conceptual representation from texts according to a domain…

In this paper, we propose three novel models to enhance word embedding by implicitly using morphological information. Experiments on word similarity and syntactic analogy show that the implicit models are superior to traditional explicit…

In this paper, we explore the usage of Word Embedding semantic resources for Information Retrieval (IR) task. This embedding, produced by a shallow neural network, have been shown to catch semantic similarities between words (Mikolov et…

Retrieving relevant plots from the book for a query is a critical task, which can improve the reading experience and efficiency of readers. Readers usually only give an abstract and vague description as the query based on their own…

Despite enormous progress in Natural Language Processing (NLP), our field is still lacking a common deep semantic representation scheme. As a result, the problem of meaning and understanding is typically sidestepped through more simple,…

Image-text matching has been a hot research topic bridging the vision and language areas. It remains challenging because the current representation of image usually lacks global semantic concepts as in its corresponding text caption. To…

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties…

Methods for learning word representations using large text corpora have received much attention lately due to their impressive performance in numerous natural language processing (NLP) tasks such as, semantic similarity measurement, and…

In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the…

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image--caption coherence relations, we…