中文
相关论文

相关论文: Coping with Construals in Broad-Coverage Semantic …

200 篇论文

We present a novel document-level model for finding argument spans that fill an event's roles, connecting related ideas in sentence-level semantic role labeling and coreference resolution. Because existing datasets for cross-sentence…

计算与语言 · 计算机科学 2020-05-12 Seth Ebner , Patrick Xia , Ryan Culkin , Kyle Rawlins , Benjamin Van Durme

This paper presents a new task of predicting the coverage of a text document for relation extraction (RE): does the document contain many relational tuples for a given entity? Coverage predictions are useful in selecting the best documents…

计算与语言 · 计算机科学 2021-11-29 Sneha Singhania , Simon Razniewski , Gerhard Weikum

Mathematical notations around the world are diverse. Not as much as requiring computing machines' makers to adapt to each culture, but as much as to disorient a person landing on a web-page with a text in mathematics. In order to understand…

数字图书馆 · 计算机科学 2010-04-30 Paul Libbrecht

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

计算与语言 · 计算机科学 2019-11-12 Zhuosheng Zhang , Rui Wang , Kehai Chen , Masao Utiyama , Eiichiro Sumita , Hai Zhao

The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit discourse relations are often changed to explicit ones and vice-versa in the translation. In this…

计算与语言 · 计算机科学 2017-07-21 Majid Laali , Leila Kosseim

We describe a new sense-tagged corpus for word sense disambiguation. The corpus is constituted of instances of 20 French polysemous verbs. Each verb instance is annotated with three sense labels: (1) the actual translation of the verb in…

计算与语言 · 计算机科学 2026-05-28 Myriam Rakho , Eric Laporte , Matthieu Constant

Modeling thematic fit (a verb--argument compositional semantics task) currently requires a very large burden of labeled data. We take a linguistically machine-annotated large corpus and replace corpus layers with output from higher-quality,…

计算与语言 · 计算机科学 2022-05-05 Yuval Marton , Asad Sayeed

Deverbal nouns are nominal forms of verbs commonly used in written English texts to describe events or actions, as well as their arguments. However, many NLP systems, and in particular pattern-based ones, neglect to handle such nominalized…

计算与语言 · 计算机科学 2023-06-27 Aviv Weinstein , Yoav Goldberg

Is it possible to specify a grammatical representation (descriptors and their application guidelines) to such a degree that it can be consistently applied by different grammarians e.g. for producing a benchmark corpus for parser evaluation?…

cmp-lg · 计算机科学 2016-08-31 Atro Voutilainen , Timo Jarvinen

Superposition or Neuron Polysemanticity are important concepts in the field of interpretability and one might say they are these most intricately beautiful blockers in our path of decoding the Machine Learning black-box. The idea behind…

机器学习 · 计算机科学 2024-12-24 Akanksha Devkar

Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models…

机器学习 · 计算机科学 2021-06-22 Juyong Kim , Pradeep Ravikumar , Joshua Ainslie , Santiago Ontañón

We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations. The representations change significantly when translation and part-of-speech decoders are added. The more decoders a model…

计算与语言 · 计算机科学 2018-01-19 Gino Brunner , Yuyi Wang , Roger Wattenhofer , Michael Weigelt

We describe an inventory of semantic relations that are expressed by prepositions. We define these relations by building on the word sense disambiguation task for prepositions and propose a mapping from preposition senses to the relation…

计算与语言 · 计算机科学 2013-05-27 Vivek Srikumar , Dan Roth

Syntactic structure of sentences in a document substantially informs about its authorial writing style. Sentence representation learning has been widely explored in recent years and it has been shown that it improves the generalization of…

计算与语言 · 计算机科学 2022-02-25 Fereshteh Jafariakinabad , Kien A. Hua

Many natural language processing tasks, e.g., coreference resolution and semantic role labeling, require selecting text spans and making decisions about them. A typical approach to such tasks is to score all possible spans and greedily…

计算与语言 · 计算机科学 2023-08-24 Tianyu Liu , Yuchen Eleanor Jiang , Ryan Cotterell , Mrinmaya Sachan

Dung's abstract argumentation framework consists of a set of interacting arguments and a series of semantics for evaluating them. Those semantics partition the powerset of the set of arguments into two classes: extensions and…

人工智能 · 计算机科学 2015-09-14 Fuan Pu , Jian Luo , Guiming Luo

Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this…

Image captioning has focused on generalizing to images drawn from the same distribution as the training set, and not to the more challenging problem of generalizing to different distributions of images. Recently, Nikolaus et al. (2019)…

计算与语言 · 计算机科学 2021-01-29 Emanuele Bugliarello , Desmond Elliott

Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation…

计算与语言 · 计算机科学 2022-10-13 César González-Gutiérrez , Audi Primadhanty , Francesco Cazzaro , Ariadna Quattoni

A framework and method are proposed for the study of constituent composition in fMRI. The method produces estimates of neural patterns encoding complex linguistic structures, under the assumption that the contributions of individual…

计算与语言 · 计算机科学 2021-10-26 Matthias Lalisse , Paul Smolensky