Related papers: Explaining and Improving BERT Performance on Lexic…
Choosing an appropriate tokenization scheme is often a bottleneck in low-resource cross-lingual transfer. To understand the downstream implications of text representation choices, we perform a comparative analysis on language models having…
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…
Classifying semantic relations between entity pairs in sentences is an important task in Natural Language Processing (NLP). Most previous models for relation classification rely on the high-level lexical and syntactic features obtained by…
Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…
Despite the recent progress, little is known about the features captured by state-of-the-art neural relation extraction (RE) models. Common methods encode the source sentence, conditioned on the entity mentions, before classifying the…
Lexical relations describe how concepts are semantically related, in the form of relation triples. The accurate prediction of lexical relations between concepts is challenging, due to the sparsity of patterns indicating the existence of…
In this paper, we compare the performances of traditional machine learning models using feature engineering and word vectors and the state-of-the-art language model BERT using word embeddings on three datasets. We also consider the time and…
Word embeddings, made widely popular in 2013 with the release of word2vec, have become a mainstay of NLP engineering pipelines. Recently, with the release of BERT, word embeddings have moved from the term-based embedding space to the…
Enhancing machine capabilities to answer questions has been a topic of considerable focus in recent years of NLP research. Language models like Embeddings from Language Models (ELMo)[1] and Bidirectional Encoder Representations from…
Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it…
Topic models have been widely used in discovering latent topics which are shared across documents in text mining. Vector representations, word embeddings and topic embeddings, map words and topics into a low-dimensional and dense real-value…
Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length…
This paper uses the BERT model, which is a transformer-based architecture, to solve task 4A, English Language, Sentiment Analysis in Twitter of SemEval2017. BERT is a very powerful large language model for classification tasks when the…
Many NLP tasks have benefited from transferring knowledge from contextualized word embeddings, however the picture of what type of knowledge is transferred is incomplete. This paper studies the types of linguistic phenomena accounted for by…
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…
This study compares the effectiveness and robustness of multi-class categorization of Amazon product data using transfer learning on pre-trained contextualized language models. Specifically, we fine-tuned BERT and XLNet, two bidirectional…
Learning representations that accurately model semantics is an important goal of natural language processing research. Many semantic phenomena depend on syntactic structure. Recent work examines the extent to which state-of-the-art models…
We investigate contract element extraction. We show that LSTM-based encoders perform better than dilated CNNs, Transformers, and BERT in this task. We also find that domain-specific WORD2VEC embeddings outperform generic pre-trained GLOVE…
This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language…