Related papers: MirrorWiC: On Eliciting Word-in-Context Representa…
The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision techniques operate at the word form level, which serves as a…
While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored.…
Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities…
Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…
Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for…
Complex Word Identification (CWI) is an essential step in the lexical simplification task and has recently become a task on its own. Some variations of this binary classification task have emerged, such as lexical complexity prediction…
Due to the recent advances of natural language processing, several works have applied the pre-trained masked language model (MLM) of BERT to the post-correction of speech recognition. However, existing pre-trained models only consider the…
Pre-trained language models (PLMs) have proven to be effective for document re-ranking task. However, they lack the ability to fully interpret the semantics of biomedical and health-care queries and often rely on simplistic patterns for…
Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…
Large Language Models (LLMs) have recently shown remarkable advancement in various NLP tasks. As such, a popular trend has emerged lately where NLP researchers extract word/sentence/document embeddings from these large decoder-only models…
Large Language Models (LLMs) have recently shown remarkable advancement in various NLP tasks. As such, a popular trend has emerged lately where NLP researchers extract word/sentence/document embeddings from these large decoder-only models…
Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…
While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase…
Although pre-trained language models (PLMs) have achieved state-of-the-art performance on various natural language processing (NLP) tasks, they are shown to be lacking in knowledge when dealing with knowledge driven tasks. Despite the many…
Mainstream Word Sense Disambiguation (WSD) approaches have employed BERT to extract semantics from both context and definitions of senses to determine the most suitable sense of a target word, achieving notable performance. However, there…
In recent years BERT shows apparent advantages and great potential in natural language processing tasks. However, both training and applying BERT requires intensive time and resources for computing contextual language representations, which…
While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as understanding object permanence or planning household…
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods. Recent findings have shown that the accuracy and robustness of unsupervised word translation (UWT) can be improved by making use…
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…
Unsupervised representation learning algorithms such as word2vec and ELMo improve the accuracy of many supervised NLP models, mainly because they can take advantage of large amounts of unlabeled text. However, the supervised models only…