Related papers: Detecting Multiword Expression Type Helps Lexical …
Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. With only a few demonstration examples, these LLMs can quickly adapt to target tasks without expensive gradient updates. Common…
This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations. Although metaphor processing has gained significant…
In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that focus solely on either text or speech features, MM-KWS…
One of the biggest challenges of natural language generation (NLG) is the proper handling of named entities. Named entities are a common source of grammar mistakes such as wrong prepositions, wrong article handling, or incorrect entity…
Classic lexical-matching-based QA metrics are slowly being phased out because they punish succinct or informative outputs just because those answers were not provided as ground truth. Recently proposed neural metrics can evaluate semantic…
Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such, they are subject to curse of multilinguality, a loss of…
The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However, existing harmful…
Multimodal image-text memes are prevalent on the internet, serving as a unique form of communication that combines visual and textual elements to convey humor, ideas, or emotions. However, some memes take a malicious turn, promoting hateful…
Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…
Vulnerability Detection (VD) using machine learning faces a significant challenge: the vast diversity of vulnerability types. Each Common Weakness Enumeration (CWE) represents a unique category of vulnerabilities with distinct…
Modern neural networks (NNs), trained on extensive raw sentence data, construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors. These representations are expected to capture…
Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire…
Beyond individual languages, multilingual natural language processing (NLP) research increasingly aims to develop models that perform well across languages generally. However, evaluating these systems on all the world's languages is…
Word embeddings have advanced the state of the art in NLP across numerous tasks. Understanding the contents of dense neural representations is of utmost interest to the computational semantics community. We propose to focus on relating…
Bilingual word embeddings, which representlexicons of different languages in a shared em-bedding space, are essential for supporting se-mantic and knowledge transfers in a variety ofcross-lingual NLP tasks. Existing approachesto training…
While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical…
User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written…
The subword complexity of a finite word $w$ of length $N$ is a function which associates to each $n\le N$ the number of all distinct subwords of $w$ having the length $n$. We define the \emph{maximal complexity} C(w) as the maximum of the…
Word-level quality estimation (WQE) aims to automatically identify fine-grained error spans in machine-translated outputs and has found many uses, including assisting translators during post-editing. Modern WQE techniques are often…
Reading is a complex process which requires proper understanding of texts in order to create coherent mental representations. However, comprehension problems may arise due to hard-to-understand sections, which can prove troublesome for…