中文
相关论文

相关论文: A Lexicon for Underspecified Semantic Tagging

200 篇论文

Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering,…

计算与语言 · 计算机科学 2020-01-01 Christian Hadiwinoto , Hwee Tou Ng , Wee Chung Gan

Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague, inconsistent, and require manual relabeling. In response,…

计算与语言 · 计算机科学 2026-03-02 Angie Boggust , Donghao Ren , Yannick Assogba , Dominik Moritz , Arvind Satyanarayan , Fred Hohman

Semantic clusters of a domain form an important feature that can be useful for performing syntactic and semantic disambiguation. Several attempts have been made to extract the semantic clusters of a domain by probabilistic or taxonomic…

cmp-lg · 计算机科学 2008-02-03 Rajeev Agarwal

In the field of machine learning, data understanding is the practice of getting initial insights in unknown datasets. Such knowledge-intensive tasks require a lot of documentation, which is necessary for data scientists to grasp the meaning…

数据库 · 计算机科学 2018-06-14 Markus Schröder , Christian Jilek , Jörn Hees , Andreas Dengel

Prepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence. Supervised corpora for the preposition-sense disambiguation task are small, suggesting a…

计算与语言 · 计算机科学 2016-11-29 Hila Gonen , Yoav Goldberg

Previous models for learning the semantic vectors of items and their groups, such as words, sentences, nodes, and graphs, using distributed representation have been based on the assumption that the basic sense of an item corresponds to one…

机器学习 · 计算机科学 2024-04-30 Yukio Ohsawa , Dingming Xue , Kaira Sekiguchi

Language Identification in textual documents is the process of automatically detecting the language contained in a document based on its content. The present Language Identification techniques presume that a document contains text in one of…

计算与语言 · 计算机科学 2021-06-30 Mohd Zeeshan Ansari , Tanvir Ahmad , Noaima Bari

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We…

计算与语言 · 计算机科学 2014-01-23 Tahira Naseem , Benjamin Snyder , Jacob Eisenstein , Regina Barzilay

We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture…

计算与语言 · 计算机科学 2016-08-26 David Weir , Julie Weeds , Jeremy Reffin , Thomas Kober

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning…

计算与语言 · 计算机科学 2016-08-08 Mohammad Taher Pilehvar , Nigel Collier

Word sense disambiguation has developed as a sub-area of natural language processing, as if, like parsing, it was a well-defined task which was a pre-requisite to a wide range of language-understanding applications. First, I review earlier…

cmp-lg · 计算机科学 2007-05-23 Adam Kilgarriff

Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics…

计算与语言 · 计算机科学 2018-06-15 Jisun An , Haewoon Kwak , Yong-Yeol Ahn

How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis…

人工智能 · 计算机科学 2015-06-25 Stevan Harnad

This paper presents a corpus-based approach to word sense disambiguation that builds an ensemble of Naive Bayesian classifiers, each of which is based on lexical features that represent co--occurring words in varying sized windows of…

计算与语言 · 计算机科学 2007-05-23 Ted Pedersen

The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggles in localizing an…

计算机视觉与模式识别 · 计算机科学 2024-03-27 Qinying Liu , Wei Wu , Kecheng Zheng , Zhan Tong , Jiawei Liu , Yu Liu , Wei Chen , Zilei Wang , Yujun Shen

Argumentation is a process of evaluating and comparing a set of arguments. A way to compare them consists in using a ranking-based semantics which rank-order arguments from the most to the least acceptable ones. Recently, a number of such…

人工智能 · 计算机科学 2016-02-03 Elise Bonzon , Jérôme Delobelle , Sébastien Konieczny , Nicolas Maudet

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain…

计算与语言 · 计算机科学 2023-08-09 Anik Saha , Oktie Hassanzadeh , Alex Gittens , Jian Ni , Kavitha Srinivas , Bulent Yener

Ontologies formalise how the concepts from a given domain are interrelated. Despite their clear potential as a backbone for explainable AI, existing ontologies tend to be highly incomplete, which acts as a significant barrier to their more…

人工智能 · 计算机科学 2021-05-12 Steven Schockaert , Yazmín Ibáñez-García , Víctor Gutiérrez-Basulto

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…

计算与语言 · 计算机科学 2022-06-02 Andrea Lekkas , Peter Schneider-Kamp , Isabelle Augenstein

Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation…

计算与语言 · 计算机科学 2019-06-19 Xiaoye Tan , Rui Yan , Chongyang Tao , Mingrui Wu