Related papers: Monolingual alignment of word senses and definitio…
Document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. Such aligned data can be used for a variety of NLP tasks from training cross-lingual…
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…
The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques. However, most existing evaluation benchmarks for assessing this criterion are tied to sense inventories…
We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering datasets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones…
Monolingual word alignment is important for studying fine-grained editing operations (i.e., deletion, addition, and substitution) in text-to-text generation tasks, such as paraphrase generation, text simplification, neutralizing biased…
We consider the problem of aligning two sets of continuous word representations, corresponding to languages, to a common space in order to infer a bilingual lexicon. It was recently shown that it is possible to infer such lexicon, without…
Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…
Word Sense Disambiguation (WSD) aims to automatically identify the exact meaning of one word according to its context. Existing supervised models struggle to make correct predictions on rare word senses due to limited training data and can…
NLP research on aligning lexical representation spaces to one another has so far focused on aligning language spaces in their entirety. However, cognitive science has long focused on a local perspective, investigating whether translation…
Bilingual lexicons map words in one language to their translations in another, and are typically induced by learning linear projections to align monolingual word embedding spaces. In this paper, we show it is possible to produce much higher…
We apply cross-lingual Latent Semantic Indexing to the Bilingual Document Alignment Task at WMT16. Reduced-rank singular value decomposition of a bilingual term-document matrix derived from known English/French page pairs in the training…
Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algorithms. This paper…
Recent work in cross-lingual contextual word embedding learning cannot handle multi-sense words well. In this work, we explore the characteristics of contextual word embeddings and show the link between contextual word embeddings and word…
Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…
Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD…
Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon…
This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing…
Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods…