中文
相关论文

相关论文: The Effect of Context on Metaphor Paraphrase Aptne…

200 篇论文

We study the influence of context on sentence acceptability. First we compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a…

计算与语言 · 计算机科学 2020-04-03 Jey Han Lau , Carlos S. Armendariz , Shalom Lappin , Matthew Purver , Chang Shu

We study the role of linguistic context in predicting quantifiers (`few', `all'). We collect crowdsourced data from human participants and test various models in a local (single-sentence) and a global context (multi-sentence) condition.…

计算与语言 · 计算机科学 2018-06-04 Sandro Pezzelle , Shane Steinert-Threlkeld , Raffaela Bernardi , Jakub Szymanik

Previous work has examined the capacity of deep neural networks (DNNs), particularly transformers, to predict human sentence acceptability judgments, both independently of context, and in document contexts. We consider the effect of prior…

人工智能 · 计算机科学 2026-02-25 Hyewon Jang , Nikolai Ilinykh , Sharid Loáiciga , Jey Han Lau , Shalom Lappin

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…

计算与语言 · 计算机科学 2021-06-03 Patrick Fernandes , Kayo Yin , Graham Neubig , André F. T. Martins

The advent of context-aware NMT has resulted in promising improvements in the overall translation quality and specifically in the translation of discourse phenomena such as pronouns. Previous works have mainly focused on the use of past…

计算与语言 · 计算机科学 2020-04-29 KayYen Wong , Sameen Maruf , Gholamreza Haffari

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al. When used in place of original references, the paraphrased versions produce metric…

计算与语言 · 计算机科学 2020-10-21 Markus Freitag , George Foster , David Grangier , Colin Cherry

Semantic feature models have become a popular tool for prediction and interpretation of fMRI data. In particular, prior work has shown that differences in the fMRI patterns in sentence reading can be explained by context-dependent changes…

计算与语言 · 计算机科学 2021-01-14 N. Aguirre-Celis , R. Miikkulainen

Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasized mid-context degradation in question answering, this…

计算与语言 · 计算机科学 2026-02-25 Pietro Bernardelle , Stefano Civelli , Kevin Roitero , Gianluca Demartini

Despite the recent success of automatic metrics for assessing translation quality, their application in evaluating the quality of machine-translated chats has been limited. Unlike more structured texts like news, chat conversations are…

计算与语言 · 计算机科学 2024-03-14 Sweta Agrawal , Amin Farajian , Patrick Fernandes , Ricardo Rei , André F. T. Martins

Compositional vector space models of meaning promise new solutions to stubborn language understanding problems. This paper makes two contributions toward this end: (i) it uses automatically-extracted paraphrase examples as a source of…

计算与语言 · 计算机科学 2018-02-01 Avneesh Saluja , Chris Dyer , Jean-David Ruvini

Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure…

计算与语言 · 计算机科学 2024-02-05 Wafaa Mohammed , Vlad Niculae

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient…

人工智能 · 计算机科学 2025-05-26 Wang Yang , Zirui Liu , Hongye Jin , Qingyu Yin , Vipin Chaudhary , Xiaotian Han

Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its…

计算与语言 · 计算机科学 2019-10-02 Yunsu Kim , Duc Thanh Tran , Hermann Ney

Recommender systems, while a powerful decision making tool, are often operationalized as black box models, such that their AI algorithms are not accessible or interpretable by human operators. This in turn can cause confusion and…

人机交互 · 计算机科学 2024-09-18 Divya Srivastava , Karen M. Feigh

Given a specific discourse, which discourse properties trigger the use of metaphorical language, rather than using literal alternatives? For example, what drives people to say "grasp the meaning" rather than "understand the meaning" within…

计算与语言 · 计算机科学 2022-05-24 Prisca Piccirilli , Sabine Schulte im Walde

Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised…

计算与语言 · 计算机科学 2022-02-01 Xiaofei Sun , Yuxian Meng , Xiang Ao , Fei Wu , Tianwei Zhang , Jiwei Li , Chun Fan

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized…

计算与语言 · 计算机科学 2019-09-27 Weijia Shi , Muhao Chen , Pei Zhou , Kai-Wei Chang

Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…

计算与语言 · 计算机科学 2018-11-15 Hao Xiong , Zhongjun He , Hua Wu , Haifeng Wang

Short feedback responses, such as backchannels, play an important role in spoken dialogue. So far, most of the modeling of feedback responses has focused on their timing, often neglecting how their lexical and prosodic form influence their…

计算与语言 · 计算机科学 2024-09-25 Livia Qian , Gabriel Skantze

Crowdsourced labels play a crucial role in evaluating task-oriented dialogue systems (TDSs). Obtaining high-quality and consistent ground-truth labels from annotators presents challenges. When evaluating a TDS, annotators must fully…

计算与语言 · 计算机科学 2024-04-16 Clemencia Siro , Mohammad Aliannejadi , Maarten de Rijke
‹ 上一页 1 2 3 10 下一页 ›