Tense, aspect, and agreement in heritage Labrador Inuttitut

2015 ◽  
Vol 5 (1) ◽  
pp. 30-61 ◽  
Author(s):  
Marina Sherkina-Lieber
Keyword(s):  
Semantic Features ◽  
Verb Agreement ◽  
Family Language ◽  
Receptive Bilinguals ◽  
Better Than ◽  
Fluent Speakers

Heritage receptive bilinguals (RBs) are individuals who report understanding but not speaking their family language. This study tests whether semantic features of functional morphemes, namely tense, aspect, and agreement markers, are accessible to them in comprehension. RBs in this study are fluent speakers of English with receptive knowledge of Labrador Inuttitut. Many RBs showed fluent-like comprehension of aspectual suffixes, subject-object-verb agreement suffixes, and past versus future contrasts in tense suffixes, but most could not identify remoteness degrees in tense suffixes. Lowest-proficiency RBs did not show knowledge of any morphemes. Remoteness features are missing from most RBs’ grammars; the same applies to many features in LRBs’ grammars. Some RBs showed inconsistent performance: better than chance, but worse than fluent speakers. The corresponding parts of RBs’ grammars are therefore fluent-like, but access to them is difficult. RBs’ grammars consist of fluent-like parts, parts with reduced access, and incomplete parts.

Object attraction effects during subject-verb agreement in Persian

2018 ◽  
Vol 72 (4) ◽  
pp. 742-752 ◽  
Author(s):  
Aazam Feiz ◽  
Wind Cowles
Keyword(s):  
Sentence Production ◽  
Semantic Features ◽  
Verb Agreement ◽  
Grammatical Errors ◽  
The Subject ◽  
Attraction Effects ◽  
Insight Into ◽  
Attraction Errors

Subject-verb agreement provides insight into how grammatical and semantic features interact during sentence production, and prior studies have found attraction errors when an intervening local noun is grammatically part of the subject. Two major types of theories have emerged from these studies: control based and competition-based. The current study used an subject-object-verb language with optional subject-verb agreement, Persian, to test the competition-based hypothesis that intervening object nouns may also cause attraction effects, even though objects are not part of the syntactic relationship between the subject and verb. Our results, which did not require speakers to make grammatical errors, show that objects can be attractors for agreement, but this effect appears to be dependent on the type of plural marker on the object. These results support competition-based theories of agreement production, in which agreement may be influenced by attractors that are outside the scope of the subject-verb relationship.

scholarly journals Word order, referential expression, and case cues to the acquisition of transitive sentences in Italian

2013 ◽  
Vol 42 (1) ◽  
pp. 1-31 ◽  
Author(s):  
KIRSTEN ABBOT-SMITH ◽  
LUDOVICA SERRATRICE
Keyword(s):  
Word Order ◽  
Low Cost ◽  
Age Groups ◽  
Verb Agreement ◽  
Italian Child ◽  
Cue Conflict ◽  
Better Than ◽  
Difficult Word

ABSTRACTIn Study 1 we analyzed Italian child-directed-speech (CDS) and selected the three most frequent active transitive sentence frames used with overt subjects. In Study 2 we experimentally investigated how Italian-speaking children aged 2;6, 3;6, and 4;6 comprehended these orders with novel verbs when the cues of animacy, gender, and subject–verb agreement were neutralized. For each trial, children chose between two videos (e.g., horse acting on cat versus cat acting on horse), both involving the same action. The children aged 2;6 comprehended S + object-pronoun + V (soprov) significantly better than S + V + object-noun (svonoun). We explain this in terms of cue collaboration between a low cost cue (case) and the firstargument = agent cue which we found to be reliable 76% of the time. The most difficult word order for all age groups was the object-pronoun + V + S (oprovs). We ascribe this difficulty to cue conflict between the two most frequent transitive frames found in CDS, namely V + object-noun and object-pronoun + V.

scholarly journals Distant Supervision for Relation Extraction with Sentence Selection and Interaction Representation

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Tiantian Chen ◽  
Nianbin Wang ◽  
Hongbin Wang ◽  
Haomin Zhan
Keyword(s):  
Large Scale ◽  
Semantic Information ◽  
State Of The Art ◽  
Relation Extraction ◽  
Semantic Features ◽  
Distant Supervision ◽  
Word Level ◽  
Proposed Model ◽  
Relation Prediction ◽  
Better Than

Distant supervision (DS) has been widely used for relation extraction (RE), which automatically generates large-scale labeled data. However, there is a wrong labeling problem, which affects the performance of RE. Besides, the existing method suffers from the lack of useful semantic features for some positive training instances. To address the above problems, we propose a novel RE model with sentence selection and interaction representation for distantly supervised RE. First, we propose a pattern method based on the relation trigger words as a sentence selector to filter out noisy sentences to alleviate the wrong labeling problem. After clean instances are obtained, we propose the interaction representation using the word-level attention mechanism-based entity pairs to dynamically increase the weights of the words related to entity pairs, which can provide more useful semantic information for relation prediction. The proposed model outperforms the strongest baseline by 2.61 in F1-score on a widely used dataset, which proves that our model performs significantly better than the state-of-the-art RE systems.

scholarly journals Automatic Correction of Real-Word Errors in Spanish Clinical Texts

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2893
Author(s):  
Daniel Bravo-Candel ◽  
Jésica López-Hernández ◽  
José Antonio García-Díaz ◽  
Fernando Molina-Molina ◽  
Francisco García-Sánchez
Keyword(s):  
Deep Learning ◽  
Semantic Features ◽  
Real Word ◽  
Neural Machine Translation ◽  
Clinical Text ◽  
Different Types ◽  
Privacy Issues ◽  
Deep Learning Model ◽  
Better Than ◽  
Types Of Error

Real-word errors are characterized by being actual terms in the dictionary. By providing context, real-word errors are detected. Traditional methods to detect and correct such errors are mostly based on counting the frequency of short word sequences in a corpus. Then, the probability of a word being a real-word error is computed. On the other hand, state-of-the-art approaches make use of deep learning models to learn context by extracting semantic features from text. In this work, a deep learning model were implemented for correcting real-word errors in clinical text. Specifically, a Seq2seq Neural Machine Translation Model mapped erroneous sentences to correct them. For that, different types of error were generated in correct sentences by using rules. Different Seq2seq models were trained and evaluated on two corpora: the Wikicorpus and a collection of three clinical datasets. The medicine corpus was much smaller than the Wikicorpus due to privacy issues when dealing with patient information. Moreover, GloVe and Word2Vec pretrained word embeddings were used to study their performance. Despite the medicine corpus being much smaller than the Wikicorpus, Seq2seq models trained on the medicine corpus performed better than those models trained on the Wikicorpus. Nevertheless, a larger amount of clinical text is required to improve the results.

An empirical study on the contribution of formal and semantic features to the grammatical gender of nouns

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Ali Basirat ◽  
Marc Allassonnière-Tang ◽  
Aleksandrs Berdicevskis
Keyword(s):  
Prediction Accuracy ◽  
Grammatical Gender ◽  
The Other ◽  
Semantic Features ◽  
Gender Identification ◽  
Gender Assignment ◽  
The Difference ◽  
Using Data ◽  
Better Than ◽  
Formal Features

Abstract This study conducts an experimental evaluation of two hypotheses about the contributions of formal and semantic features to the grammatical gender assignment of nouns. One of the hypotheses (Corbett and Fraser 2000) claims that semantic features dominate formal ones. The other hypothesis, formulated within the optimal gender assignment theory (Rice 2006), states that form and semantics contribute equally. Both hypotheses claim that the combination of formal and semantic features yields the most accurate gender identification. In this paper, we operationalize and test these hypotheses by trying to predict grammatical gender using only character-based embeddings (that capture only formal features), only context-based embeddings (that capture only semantic features) and the combination of both. We performed the experiment using data from three languages with different gender systems (French, German and Russian). Formal features are a significantly better predictor of gender than semantic ones, and the difference in prediction accuracy is very large. Overall, formal features are also significantly better than the combination of form and semantics, but the difference is very small and the results for this comparison are not entirely consistent across languages.

scholarly journals Noisy is better than rare: Comprehenders compromise subject-verb agreement to form more probable linguistic structures

2020 ◽  
Author(s):  
Maayan Keshev ◽  
Aya Meltzer-Asscher
Keyword(s):  
Language Use ◽  
Prior Probability ◽  
Near Neighbor ◽  
Sentence Completion ◽  
Noisy Channel ◽  
Verb Agreement ◽  
Online Processing ◽  
Linguistic Structures ◽  
Better Than ◽  
Object Relative

Production and perception errors are common in everyday language use. Recent studies suggest that in order to overcome the flawed speech signal, comprehenders engage in rational noisy-channel processing, which can pull their interpretation towards more probable “near-neighbor” analyses, based on the assumption that an error may have occurred in the transmission of the sentence. We investigate this type of processing using subject/object relative clause ambiguity in Hebrew. In four self-paced reading experiments and a sentence completion experiment, we find that during online processing, readers apply elaborate knowledge regarding the distribution of structures in the language, and that they are willing to compromise subject-verb agreement to refrain from (grammatical but) highly improbable structures. The results suggest that the prior probability of alternative analyses modulates the interpretation of agreement.

Recognition of English information and semantic features based on SVM and machine learning

2020 ◽  
pp. 1-11
Author(s):  
Man Li ◽  
Ruifang Bai
Keyword(s):  
Machine Learning ◽  
Model System ◽  
Machine Learning Algorithms ◽  
Anaphora Resolution ◽  
Semantic Features ◽  
Feature Combination ◽  
Candidate Model ◽  
Current Event ◽  
Semantic Roles ◽  
Better Than

With the deepening of people’s research on event anaphora, a large number of methods will be used in the identification and resolution of event anaphora. Although there has been some progress in the resolution of the current event, the difficult problems have not yet been completely resolved. This study analyzes the English information anaphora resolution based on SVM and machine learning algorithms and uses the CNN three-layer network as the basis to model the structure. Moreover, this study improves the semantic features by adding semantic roles and analyzes and compares the performance of the improved semantic features with those before the improvement. In addition, this study combines semantic features to compare and analyze each feature combination and uses a dual candidate model to improve the system. Finally, this study analyzes the experimental results. The results show that the performance of the system using the dual candidate model is better than that of the single candidate model system.

N-Net: 3D Fully Convolution Network-Based Vertebrae Segmentation from CT Spinal Images

2019 ◽  
Vol 33 (06) ◽  
pp. 1957003 ◽  
Author(s):  
Wenhui Zhou ◽  
Lili Lin ◽  
Guangtao Ge
Keyword(s):  
Surgical Planning ◽  
Global Structure ◽  
Experimental Results ◽  
Semantic Features ◽  
Structure Information ◽  
Residual Structure ◽  
Vertebrae Segmentation ◽  
High Level ◽  
Operative Assessment ◽  
Better Than

Accurate vertebrae segmentation from CT spinal images is crucial for the clinical tasks of diagnosis, surgical planning, and post-operative assessment. This paper describes an [Formula: see text]-shaped 3D fully convolution network (FCN) for vertebrae segmentation: [Formula: see text]-net. In this network, a global structure guidance pathway is designed for fusing the high-level semantic features with the global structure information. Moreover, the residual structure and the skip connection are introduced into traditional 3D FCN framework. These schemes can significantly improve the accuracy of vertebrae segmentation. Experimental results demonstrate the effectiveness and robustness of our method. A high average DICE score of 0.9499 [Formula: see text] 0.02 can be obtained, which is better than those of existing methods.

scholarly journals Research on Multi-label Text Classification Method Based on tALBERT-CNN

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Wenfu Liu ◽  
Jianmin Pang ◽  
Nan Li ◽  
Xin Zhou ◽  
Feng Yue
Keyword(s):  
Language Processing ◽  
Text Classification ◽  
Topic Model ◽  
Classification Method ◽  
Semantic Features ◽  
Context Vector ◽  
Text Information ◽  
Massive Information ◽  
Different Levels ◽  
Better Than

AbstractSingle-label classification technology has difficulty meeting the needs of text classification, and multi-label text classification has become an important research issue in natural language processing (NLP). Extracting semantic features from different levels and granularities of text is a basic and key task in multi-label text classification research. A topic model is an effective method for the automatic organization and induction of text information. It can reveal the latent semantics of documents and analyze the topics contained in massive information. Therefore, this paper proposes a multi-label text classification method based on tALBERT-CNN: an LDA topic model and ALBERT model are used to obtain the topic vector and semantic context vector of each word (document), a certain fusion mechanism is adopted to obtain in-depth topic and semantic representations of the document, and the multi-label features of the text are extracted through the TextCNN model to train a multi-label classifier. The experimental results obtained on standard datasets show that the proposed method can extract multi-label features from documents, and its performance is better than that of the existing state-of-the-art multi-label text classification algorithms.

Sign in / Sign up

Export Citation Format

Share Document