scholarly journals Constructing Uyghur Commonsense Knowledge Base by Knowledge Projection

2019 ◽  
Vol 9 (16) ◽  
pp. 3318
Author(s):  
Azmat Anwar ◽  
Xiao Li ◽  
Yating Yang ◽  
Yajuan Wang
Keyword(s):  
Semantic Similarity ◽  
Knowledge Bases ◽  
Considerable Effort ◽  
Commonsense Knowledge ◽  
Scoring Model ◽  
Bilingual Dictionary ◽  
Short Period ◽  
Translation Ambiguity ◽  
Back Translation ◽  
Cross Lingual

Although considerable effort has been devoted to building commonsense knowledge bases (CKB), it is still not available for many low-resource languages such as Uyghur because of expensive construction cost. Focusing on this issue, we proposed a cross-lingual knowledge-projection method to construct an Uyghur CKB by projecting ConceptNet’s Chinese facts into Uyghur. We used a Chinese–Uyghur bilingual dictionary to get high-quality entity translation in facts and employed a back-translation method to eliminate the entity-translation ambiguity. Moreover, to tackle the inner relation ambiguity in translated facts, we made a hand-crafted rule to convert the structured facts into natural-language phrases and built the Chinese–Uyghur lingual phrases based on the similarity of phrases that corresponded to the bilingual semantic similarity scoring model. Experimental results show that the accuracy of our semantic similarity scoring model reached 94.75% for our task, and they successfully project 55,872 Chinese facts into Uyghur as well as obtain 67,375 Uyghur facts within a very short period.

scholarly journals Generation of Cross-Lingual Word Vectors for Low-Resourced Languages Using Deep Learning and Topological Metrics in a Data-Efficient Way

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1372
Author(s):  
Sanjanasri JP ◽  
Vijay Krishna Menon ◽  
Soman KP ◽  
Rajendran S ◽  
Agnieszka Wolk
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Semantic Space ◽  
Semantic Interpretation ◽  
Learning Approaches ◽  
Qualitative Comparison ◽  
Bilingual Dictionary ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Cross Lingual

Linguists have been focused on a qualitative comparison of the semantics from different languages. Evaluation of the semantic interpretation among disparate language pairs like English and Tamil is an even more formidable task than for Slavic languages. The concept of word embedding in Natural Language Processing (NLP) has enabled a felicitous opportunity to quantify linguistic semantics. Multi-lingual tasks can be performed by projecting the word embeddings of one language onto the semantic space of the other. This research presents a suite of data-efficient deep learning approaches to deduce the transfer function from the embedding space of English to that of Tamil, deploying three popular embedding algorithms: Word2Vec, GloVe and FastText. A novel evaluation paradigm was devised for the generation of embeddings to assess their effectiveness, using the original embeddings as ground truths. Transferability across other target languages of the proposed model was assessed via pre-trained Word2Vec embeddings from Hindi and Chinese languages. We empirically prove that with a bilingual dictionary of a thousand words and a corresponding small monolingual target (Tamil) corpus, useful embeddings can be generated by transfer learning from a well-trained source (English) embedding. Furthermore, we demonstrate the usability of generated target embeddings in a few NLP use-case tasks, such as text summarization, part-of-speech (POS) tagging, and bilingual dictionary induction (BDI), bearing in mind that those are not the only possible applications.

Knowledge extraction using semantic similarity of concepts from Web of Things knowledge bases

2021 ◽  
Vol 135 ◽  
pp. 101923
Author(s):  
Vamsee Muppavarapu ◽  
Gowtham Ramesh ◽  
Amelie Gyrard ◽  
Mahda Noura
Keyword(s):  
Semantic Similarity ◽  
Knowledge Extraction ◽  
Knowledge Bases ◽  
Web Of Things

scholarly journals A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation

2020 ◽  
Vol 8 ◽  
pp. 93-108 ◽  
Author(s):  
Jian Guan ◽  
Fei Huang ◽  
Zhihao Zhao ◽  
Xiaoyan Zhu ◽  
Minlie Huang
Keyword(s):  
Long Range ◽  
Temporal Order ◽  
State Of The Art ◽  
Knowledge Bases ◽  
Fine Tuning ◽  
Causal Relationships ◽  
Commonsense Knowledge ◽  
Language Generation ◽  
Story Generation ◽  
Global Coherence

Story generation, namely, generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conjecture that this is because of the difficulty of associating relevant commonsense knowledge, understanding the causal relationships, and planning entities and events with proper temporal order. In this paper, we devise a knowledge-enhanced pretraining model for commonsense story generation. We propose to utilize commonsense knowledge from external knowledge bases to generate reasonable stories. To further capture the causal and temporal dependencies between the sentences in a reasonable story, we use multi-task learning, which combines a discriminative objective to distinguish true and fake stories during fine-tuning. Automatic and manual evaluation shows that our model can generate more reasonable stories than state-of-the-art baselines, particularly in terms of logic and global coherence.

scholarly journals Improving Semantic Similarity with Cross-Lingual Resources: A Study in Bangla—A Low Resourced Language

Informatics ◽  
2019 ◽  
Vol 6 (2) ◽  
pp. 19 ◽  
Author(s):  
Rajat Pandit ◽  
Saptarshi Sengupta ◽  
Sudip Kumar Naskar ◽  
Niladri Sekhar Dash ◽  
Mohini Mohan Sardar
Keyword(s):  
Semantic Similarity ◽  
Language Processing ◽  
State Of The Art ◽  
Human Beings ◽  
Human Evaluation ◽  
Evaluation Scores ◽  
Similarity Calculation ◽  
Marked Enhancement ◽  
Cross Lingual ◽  
Standing Problem

Semantic similarity is a long-standing problem in natural language processing (NLP). It is a topic of great interest as its understanding can provide a look into how human beings comprehend meaning and make associations between words. However, when this problem is looked at from the viewpoint of machine understanding, particularly for under resourced languages, it poses a different problem altogether. In this paper, semantic similarity is explored in Bangla, a less resourced language. For ameliorating the situation in such languages, the most rudimentary method (path-based) and the latest state-of-the-art method (Word2Vec) for semantic similarity calculation were augmented using cross-lingual resources in English and the results obtained are truly astonishing. In the presented paper, two semantic similarity approaches have been explored in Bangla, namely the path-based and distributional model and their cross-lingual counterparts were synthesized in light of the English WordNet and Corpora. The proposed methods were evaluated on a dataset comprising of 162 Bangla word pairs, which were annotated by five expert raters. The correlation scores obtained between the four metrics and human evaluation scores demonstrate a marked enhancement that the cross-lingual approach brings into the process of semantic similarity calculation for Bangla.

scholarly journals Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity

2020 ◽  
pp. 1-51
Author(s):  
Ivan Vulić ◽  
Simon Baker ◽  
Edoardo Maria Ponti ◽  
Ulla Petti ◽  
Ira Leviant ◽  
...  
Keyword(s):  
Semantic Similarity ◽  
Large Scale ◽  
Representation Learning ◽  
Data Sets ◽  
Word Embeddings ◽  
Data Set ◽  
Lexical Representations ◽  
Language Data ◽  
Weakly Supervised ◽  
Cross Lingual

We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering data sets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e.g., Welsh, Kiswahili). Each language data set is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs, providing a representative coverage of word classes (nouns, verbs, adjectives, adverbs), frequency ranks, similarity intervals, lexical fields, and concreteness levels. Additionally, owing to the alignment of concepts across languages, we provide a suite of 66 crosslingual semantic similarity data sets. Because of its extensive size and language coverage, Multi-SimLex provides entirely novel opportunities for experimental evaluation and analysis. On its monolingual and crosslingual benchmarks, we evaluate and analyze a wide array of recent state-of-the-art monolingual and crosslingual representation models, including static and contextualized word embeddings (such as fastText, monolingual and multilingual BERT, XLM), externally informed lexical representations, as well as fully unsupervised and (weakly) supervised crosslingual word embeddings. We also present a step-by-step data set creation protocol for creating consistent, Multi-Simlex -style resources for additional languages.We make these contributions—the public release of Multi-SimLex data sets, their creation protocol, strong baseline results, and in-depth analyses which can be be helpful in guiding future developments in multilingual lexical semantics and representation learning—available via aWeb site that will encourage community effort in further expansion of Multi-Simlex to many more languages. Such a large-scale semantic resource could inspire significant further advances in NLP across languages.

scholarly journals Unsupervised Neural Machine Translation with SMT as Posterior Regularization

2019 ◽  
Vol 33 ◽  
pp. 241-248 ◽  
Author(s):  
Shuo Ren ◽  
Zhirui Zhang ◽  
Shujie Liu ◽  
Ming Zhou ◽  
Shuai Ma
Keyword(s):  
Machine Translation ◽  
Language Models ◽  
Translation Process ◽  
Weak Supervision ◽  
Neural Machine Translation ◽  
Back Translation ◽  
Negative Effect ◽  
Model Training ◽  
Cross Lingual ◽  
Pseudo Data

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo data inevitably contain noises and errors that will be accumulated and reinforced in the subsequent training process, leading to bad translation performance. To address this issue, we introduce phrase based Statistic Machine Translation (SMT) models which are robust to noisy data, as posterior regularizations to guide the training of unsupervised NMT models in the iterative back-translation process. Our method starts from SMT models built with pre-trained language models and word-level translation tables inferred from cross-lingual embeddings. Then SMT and NMT models are optimized jointly and boost each other incrementally in a unified EM framework. In this way, (1) the negative effect caused by errors in the iterative back-translation process can be alleviated timely by SMT filtering noises from its phrase tables; meanwhile, (2) NMT can compensate for the deficiency of fluency inherent in SMT. Experiments conducted on en-fr and en-de translation tasks show that our method outperforms the strong baseline and achieves new state-of-the-art unsupervised machine translation performance.

Commonsense Knowledge Representation II

2011 ◽  
pp. 334-336
Author(s):  
Phillip Ein-Dor
Keyword(s):  
Knowledge Representation ◽  
Physical World ◽  
Knowledge Bases ◽  
Real Problem ◽  
Commonsense Knowledge ◽  
The Everyday ◽  
Naive Physics ◽  
Artificial World ◽  
Representation Formalism ◽  
Order Predicate Calculus

Early attempts to implement systems that understand commonsense knowledge did so for very restricted domains. For example, the Planes system [Waltz, 1978] knew real world facts about a fleet of airplanes and could answer questions about them put to it in English. It had, however, no behaviors, could not interpret the facts, draw inferences from them or solve problems, other than those that have to do with understanding the questions. At the other extreme, SHRDLU (Winograd, 1973) understood situations in its domain of discourse (which it perceived visually), accepted commands in natural language to perform behaviors in that domain and solved problems arising in execution of the commands; all these capabilities were restricted, however, to SHRDLU’s artificial world of colored toy blocks. Thus, in implemented systems it appears that there may be a trade off between the degree of realism of the domain and the number of capabilities that can be implemented. In the frames versus logic debate (see Commonsense Knowledge Representation I - Formalisms in this Encyclopedia), the real problem, in Israel’s (1983) opinion, is not the representation formalism itself, but rather that the facts of the commonsense world have not been formulated, and this is more critical than choice of a particular formalism. A notable attempt to formulate the “facts of the commonsense world” is that of Hayes [1978a, 1978b, 1979] under the heading of naïve physics. This work employs first-order predicate calculus to represent commonsense knowledge of the everyday physical world. The author of this survey has undertaken a similar effort with respect to commonsense business knowledge (Ein-Dor and Ginzberg 1989). Some broader attempts to formulate commonsense knowledge bases are cited in the section Commonsense Knowledge Bases.

Sign in / Sign up

Export Citation Format

Share Document