Papers Word Alignment
“Word Alignment” 태그가 달린 논문 564편 · 필터 해제
End-to-End Neural Word Alignment Outperforms GIZA++
Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT …
Machine TranslationTranslationWord AlignmentEnd-to-End Slot Alignment and Recognition for Cross-Lingual NLU
Natural language understanding (NLU) in the context of goal-oriented dialog systems typically includes intent classification and slot labeling tasks. Existing methods to expand an NLU system to new languages use machine …
Cross-Lingual TransferGoal-Oriented Dialogintent-classificationIntent Classification+4A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT
We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions from a token in the source sentence to a…
Question AnsweringSentenceWord AlignmentConversational Word Embedding for Retrieval-Based Dialog System
Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversat…
Common Sense ReasoningMachine TranslationRetrievalSentence+2Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing. Hence, attention is being extensively studied to investigate various linguistic capabilities…
Machine TranslationTranslationWord AlignmentSimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly wi…
Machine TranslationMultilingual Word EmbeddingsNMTTranslation+2A Simple Approach to Learning Unsupervised Multilingual Embeddings
Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve…
Bilingual Lexicon InductionDependency ParsingDocument ClassificationWord Alignment+1On the Language Neutrality of Pre-trained Multilingual Representations
Multilingual contextual embeddings, such as multilingual BERT and XLM-RoBERTa, have proved useful for many multi-lingual tasks. Previous work probed the cross-linguality of the representations indirectly using zero-shot …
Language IdentificationTransfer LearningWord AlignmentLocality Preserving Loss: Neighbors that Live together, Align together
We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations. Given two pretrained embedding manifolds, LPL optimizes a model to pr…
Natural Language InferenceSentence EmbeddingsSTStext similarity+1Unsupervised Multilingual Alignment using Wasserstein Barycenter
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the m…
AllMachine TranslationTranslationUnsupervised Machine Translation+1Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks
The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply of vision-and-language problems (such as …
Image RetrievalInductive BiasQuestion AnsweringRetrieval+3How Language-Neutral is Multilingual BERT?
Multilingual BERT (mBERT) provides sentence representations for 104 languages, which are useful for many multi-lingual tasks. Previous work probed the cross-linguality of mBERT using zero-shot transfer learning on morpho…
RetrievalSentenceSentence RetrievalTransfer Learning+1Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
This paper focuses on the problem of unsupervised alignment of hierarchical data such as ontologies or lexical databases. This is a problem that appears across areas, from natural language processing to bioinformatics, a…
Ontology MatchingWord AlignmentImproving Latent Alignment in Text Summarization by Generalizing the Pointer Generator
Pointer Generators have been the de facto standard for modern summarization systems. However, this architecture faces two major drawbacks: Firstly, the pointer is limited to copying the exact words while ignoring possibl…
Text SummarizationWord AlignmentEssentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs
Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at dis…
Paraphrase MiningWord AlignmentAnnotated Guidelines and Building Reference Corpus for Myanmar-English Word Alignment
Reference corpus for word alignment is an important resource for developing and evaluating word alignment methods. For Myanmar-English language pairs, there is no reference corpus to evaluate the word alignment tasks. Th…
Contrastive LearningWord AlignmentJointly Learning to Align and Translate with Transformer Models
The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment…
Machine TranslationTranslationWord AlignmentA Discriminative Neural Model for Cross-Lingual Word Alignment
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model. In experiments based on a small number of labeled examples (~1.7K-5K sentences) we evaluate…
Machine TranslationNERTranslationWord AlignmentInterconnecting lexical resources and word alignment: How do learners get on with particle verbs?
In this paper, we present a prototype for an online exercise aimed at learners of English and Swedish that serves multiple purposes. The exercise allows learners of the aforementioned languages to train their knowledge o…
TranslationWord AlignmentTransformer-based Automatic Post-Editing with a Context-Aware Encoding Approach for Multi-Source Inputs
Recent approaches to the Automatic Post-Editing (APE) research have shown that better results are obtained by multi-source models, which jointly encode both source (src) and machine translation output (mt) to produce pos…
Automatic Post-EditingMachine TranslationSentenceTranslation+1