中文
相关论文

相关论文: To Word Senses and Beyond: Inducing Concepts with …

200 篇论文

We evaluate LLMs' language understanding capacities on simple inference tasks that most humans find trivial. Specifically, we target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii)…

计算与语言 · 计算机科学 2024-04-12 Victoria Basmov , Yoav Goldberg , Reut Tsarfaty

This paper presents a multilingual study of word meaning representations in context. We assess the ability of both static and contextualized models to adequately represent different lexical-semantic relations, such as homonymy and synonymy.…

计算与语言 · 计算机科学 2021-06-30 Marcos Garcia

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

计算与语言 · 计算机科学 2023-11-06 Chen Shani , Jilles Vreeken , Dafna Shahaf

Lexical substitution is the task of generating meaningful substitutes for a word in a given textual context. Contextual word embedding models have achieved state-of-the-art results in the lexical substitution task by relying on contextual…

机器学习 · 计算机科学 2022-04-04 George Michalopoulos , Ian McKillop , Alexander Wong , Helen Chen

Many of the existing approaches for program comprehension rely on the linguistic information found in source code, such as identifier names and comments. Semantic clustering is one such technique for modularization of the system that relies…

软件工程 · 计算机科学 2017-08-08 Amir Saeidi , Jurriaan Hage , Ravi Khadka , Slinger Jansen

This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…

计算与语言 · 计算机科学 2022-06-20 Josiah Wang , Pranava Madhyastha , Josiel Figueiredo , Chiraag Lala , Lucia Specia

Various applications in computational linguistics and artificial intelligence rely on high-performing word sense disambiguation techniques to solve challenging tasks such as information retrieval, machine translation, question answering,…

计算与语言 · 计算机科学 2021-01-11 Mohannad AlMousa , Rachid Benlamri , Richard Khoury

Word Sense Disambiguation (WSD) is a historical task in computational linguistics that has received much attention over the years. However, with the advent of Large Language Models (LLMs), interest in this task (in its classical definition)…

计算与语言 · 计算机科学 2025-03-12 Pierpaolo Basile , Lucia Siciliani , Elio Musacchio , Giovanni Semeraro

Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent…

计算与语言 · 计算机科学 2026-04-16 Zhichen Liu , Yongyuan Li , Yang Xu

Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for…

计算与语言 · 计算机科学 2018-10-16 Myeongjun Jang , Pilsung Kang

Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised…

计算与语言 · 计算机科学 2016-12-20 Antonio Jimeno Yepes

This work presents an unsupervised approach for improving WordNet that builds upon recent advances in document and sense representation via distributional semantics. We apply our methods to construct Wordnets in French and Russian,…

计算与语言 · 计算机科学 2017-05-02 Mikhail Khodak , Andrej Risteski , Christiane Fellbaum , Sanjeev Arora

Word representations are created using analogy context-based statistics and lexical relations on words. Word representations are inputs for the learning models in Natural Language Understanding (NLU) tasks. However, to understand language,…

人工智能 · 计算机科学 2019-01-23 Anupiya Nugaliyadde , Kok Wai Wong , Ferdous Sohel , Hong Xie

The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks has proven to be very…

计算与语言 · 计算机科学 2023-12-04 Pablo Gamallo

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

计算与语言 · 计算机科学 2024-10-15 Jian Gu , Aldeida Aleti , Chunyang Chen , Hongyu Zhang

Most popular word embedding techniques involve implicit or explicit factorization of a word co-occurrence based matrix into low rank factors. In this paper, we aim to generalize this trend by using numerical methods to factor higher-order…

机器学习 · 统计学 2017-09-19 Eric Bailey , Shuchin Aeron

As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD…

计算与语言 · 计算机科学 2022-10-17 Ying Su , Hongming Zhang , Yangqiu Song , Tong Zhang

We present a word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora. The result is a corpus which is sense-tagged according to a corpus-derived sense…

计算与语言 · 计算机科学 2022-03-22 Matan Eyal , Shoval Sadde , Hillel Taub-Tabib , Yoav Goldberg

Word sense disambiguation (WSD) methods identify the most suitable meaning of a word with respect to the usage of that word in a specific context. Neural network-based WSD approaches rely on a sense-annotated corpus since they do not…

计算与语言 · 计算机科学 2021-02-11 Sm Zobaed , Md Enamul Haque , Md Fazle Rabby , Mohsen Amini Salehi

Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel…

计算与语言 · 计算机科学 2022-09-16 Linlin Liu , Thien Hai Nguyen , Shafiq Joty , Lidong Bing , Luo Si