Related papers: Will it Unblend?
Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…
Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…
This paper investigates the extent to which pretrained German BERT encodes knowledge of noun compound semantics. We comprehensively vary combinations of target tokens, layers, and cased vs. uncased models, and evaluate them by predicting…
Improving our understanding of how information is encoded in vector space can yield valuable interpretability insights. Alongside vector dimensions, we argue that it is possible for the vector norm to also carry linguistic information. We…
Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons. Recently neural network-based language models have been explored, as they as a byproduct generate…
Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…
Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with…
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…
A common problem for automatic speech recognition systems is how to recognize words that they did not see during training. Currently there is no established method of evaluating different techniques for tackling this problem. We propose…
The ability to understand and generate languages sets human cognition apart from other known life forms'. We study a way of combing two of the most successful routes to meaning of language--statistical language models and symbolic semantics…
The Arabic language is a morphologically rich language with relatively few resources and a less explored syntax compared to English. Given these limitations, Arabic Natural Language Processing (NLP) tasks like Sentiment Analysis (SA), Named…
Accurately interpreting words is vital in political science text analysis; some tasks require assuming semantic stability, while others aim to trace semantic shifts. Traditional static embeddings, like Word2Vec effectively capture long-term…
Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes their joint modeling a standard part of training such…
Recently, Natural Language Processing (NLP) has witnessed an impressive progress in many areas, due to the advent of novel, pretrained contextual representation models. In particular, Devlin et al. (2019) proposed a model, called BERT…
Several NLP tasks need the effective representation of text documents. Arora et. al., 2017 demonstrate that simple weighted averaging of word vectors frequently outperforms neural models. SCDV (Mekala et. al., 2017) further extends this…
Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…
Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…
Tokenization and sub-tokenization based models like word2vec, BERT and the GPTs are the state-of-the-art in natural language processing. Typically, these approaches have limitations with respect to their input representation. They fail to…
How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore…
Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper we introduce a…