Related papers: Metaphor Detection via Explicit Basic Meanings Mod…
Estimating the Most Important Person (MIP) in any social event setup is a challenging problem mainly due to contextual complexity and scarcity of labeled data. Moreover, the causality aspects of MIP estimation are quite subjective and…
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In…
Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it…
Recently, utilizing large language models (LLMs) for metaphor detection has achieved promising results. However, these methods heavily rely on the capabilities of closed-source LLMs, which come with relatively high inference costs and…
In this paper, we propose methods for discovering semantic differences in words appearing in two corpora based on the norms of contextualized word vectors. The key idea is that the coverage of meanings is reflected in the norm of its mean…
We present a fairly large, Potential Idiomatic Expression (PIE) dataset for Natural Language Processing (NLP) in English. The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation…
We present the first openly available multimodal metaphor annotated corpus. The corpus consists of videos including audio and subtitles that have been annotated by experts. Furthermore, we present a method for detecting metaphors in the new…
Handling implicit language is essential for natural language processing systems to achieve precise text understanding and facilitate natural interactions with users. Despite its importance, the absence of a metric for accurately measuring…
Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…
When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and…
Emotion recognition is the task of classifying perceived emotions in people. Previous works have utilized various nonverbal cues to extract features from images and correlate them to emotions. Of these cues, situational context is…
Sentence embedding techniques aim to encode key concepts of a sentence's meaning in a vector space. However, the majority of evaluation approaches for sentence embedding quality rely on the use of additional classifiers or downstream tasks.…
Masked Image Modeling (MIM) has become a ubiquitous self-supervised vision paradigm. In this work, we show that MIM objectives cause the learned representations to retain non-semantic information, which ultimately hurts performance during…
Deep learning models are widely used for image analysis. While they offer high performance in terms of accuracy, people are concerned about if these models inappropriately make inferences using irrelevant features that are not encoded from…
This paper introduces an objective metric for evaluating a parsing scheme. It is based on Shannon's original work with letter sequences, which can be extended to part-of-speech tag sequences. It is shown that this regular language is an…
Image captioning (IC) systems, which automatically generate a text description of the salient objects in an image (real or synthetic), have seen great progress over the past few years due to the development of deep neural networks. IC plays…
Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model's capabilities of generating human-like texts keep evolving. This…
Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language. This paper introduces two new tasks to address this shortcoming by…
We developed on example-based method of metonymy interpretation. One advantages of this method is that a hand-built database of metonymy is not necessary because it instead uses examples in the form ``Noun X no Noun Y (Noun Y of Noun X).''…
Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context -- context from sentences other than those currently being translated. However, while many current methods…