Results 51 to 60 of about 2,562,427 (387)
Linguistic Profiling of a Neural Language Model [PDF]
Proceedings of the 28th International Conference on Computational
Linguistics (COLING 2020), 2020 In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set of probing tasks, each of which corresponds to a distinct sentence-level feature extracted from different levels of
arxiv +1 more source
"Linguistic principles and computational linguistics methods for the purposes of sentiment analysis of Russian texts." [PDF]
Актуальные проблемы филологии и педагогической лингвистики, 2018 "The article focuses on the current results of research project aiming at the design of Russian text classifier according to the criterion of text’s emotional tonality.
Kolmogorova Anastasia V. +2 more
doaj +1 more source
A computational guide to the dichotomy of features and constraints
Glossa, 2017 A contentious issue in the Minimalist literature is whether certain phenomena are best described in terms of features or constraints. Building on recent work in mathematical linguistics, I argue that constraints and features are interchangeable in ...
Thomas Graf
doaj +2 more sources
Improving Topic Models with Latent Feature Word Representations [PDF]
Transactions of the Association for Computational Linguistics, 2015 Probabilistic topic models are widely used to discover latent topics in document collections, while latent feature vector representations of words have been used to obtain high performance in many NLP tasks.
Dat Quoc Nguyen +3 more
semanticscholar +1 more source
Natural Language Processing and Computational Linguistics
International Conference on Computational Logic, 2021 away other aspects of information, such as the speaker’s empathy, distinction of old/new information, emphasis, and so on. To climb up the hierarchy led to loss of information in lower levels of representation. In Tsujii (1986), instead of mapping at the
Jun'ichi Tsujii
semanticscholar +1 more source
Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network
North American Chapter of the Association for Computational Linguistics, 2003 We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on ...
Kristina Toutanova +3 more
semanticscholar +1 more source
How prosody constitutes the actions of formulations in courtrooms
Working Papers em Linguística, 2018 Based on the theoretical and methodological perspectives of Conversation Analysis and Interactional Linguistics, this study investigates how the prosodic feature pitch contributes to the formation and ascription of actions in court hearings, in ...
Ana Cristina Ostermann +2 more
doaj +1 more source
A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena [PDF]
, 2016 Word reordering is one of the most difficult aspects of statistical machine translation (SMT), and an important factor of its quality and efficiency. Despite the vast amount of research published to date, the interest of the community in this problem has
Bisazza, Arianna, Federico, Marcello
core +2 more sources
Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding [PDF]
arXiv, 2022 Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images. Previous attempts typically tackle this problem using pretrained object detectors, but without the flexibility for objects not in the predefined vocabulary.
arxiv
Feature Projection for Improved Text Classification
Annual Meeting of the Association for Computational Linguistics, 2020 In classification, there are usually some good features that are indicative of class labels. For example, in sentiment classification, words like good and nice are indicative of the positive sentiment and words like bad and terrible are indicative of the
Qi Qin, Wenpeng Hu, Bing Liu
semanticscholar +1 more source